1. INTRODUCTION. Thinning plays a vital role in image processing and computer vision. It

Size: px
Start display at page:

Download "1. INTRODUCTION. Thinning plays a vital role in image processing and computer vision. It"

Transcription

1 1 1. INTRODUCTION 1.1 Introduction Thinning plays a vital role in image processing and computer vision. It is an important preprocessing step in many applications such as document analysis, image compression, data compression, fingerprint classification, and pattern recognition. Thinning process transforms an input binary image into skeletons with nearly thin lines, curves and arcs. The main objective of thinning is to preserve the important information such as shape, size and topological properties thereby simplifying the later processing steps like extracting features from patterns. Skeleton, initially termed as medial axis, was first introduced by Blum [Blum, 1964]. During these years, several thinning algorithms are developed to address wide variety of problems. These algorithms are classified into iterative and non-iterative algorithms as shown in figure 1.1. This classification is based on the approaches used for thinning [Lam, Lee & Suen, 1992]. Non-iterative algorithms obtain the skeleton in a single pass using the methodologies like distance transforms and run-length coding. Non-iterative algorithms do not consider the surrounding pixels while making decisions. Iterative algorithms either delete or retain the boundary pixels layer by layer successively until the desired skeleton is obtained. The iterative algorithms are further categorized as sequential (boundary pixels

2 2 are processed one by one, layer by layer) and parallel (all the boundary pixels are processed simultaneously layer by layer). Sequential algorithms consume less amounts of memory. In contrast, parallel algorithms require more memory compared to sequential algorithms but are much faster in processing. Parallel algorithms process all the border pixels at once and hence are order independent. Figure 1.1 Classification of thinning algorithms A good thinning algorithm should possess many properties. First, the result of thinning process should be connected and one pixel width. Second, the skeleton should have minimal deviation from the medial (central) axis.

3 3 Third, skeleton should preserve the topological and geometrical properties of the image to be thinned. Fourth, the skeleton produced should not be affected by the noise near the boundaries (i.e. insensitive to noise). Fifth, the algorithm should be efficient in terms of memory requirements and time. Sixth, the skeleton produced should be invariant to the geometrical transformations like rotation and scaling. Finally, the skeleton obtained should be in such a way that one can able to reconstruct the original image. All algorithms may not satisfy all the above characteristics, but a good algorithm aims at satisfying most of them. A number of thinning algorithms have been proposed during the last four decades. In recent past, newly devised algorithms concentrated either on improving the quality of the skeleton obtained or reducing the execution time of the existing algorithms. The time required for thinning depends on the size and the shape complexity of the given image. 1.2 Importance of thinning Thinning plays a crucial role in image analysis and pattern recognition applications. These applications require extracting features of interest like number of endpoints, junction points etc., to distinguish one object from another. Extracting such features from a thin line-like representation (skeleton) is easier and efficient than extracting from the original input image. In addition, from an artificial intelligence perspective,

4 4 thin line representation is believed to be close to the way humans recognize objects. And finally, by reducing an object to only a skeleton, irrelevant features and image noise can be filtered out. 1.3 Basic terminology In spatial domain, digital image is defined as a two-dimensional object with a finite set of intensity values whose elements are referred as picture elements (pixels). Images whose possible intensity values are only black (foreground) represented as 1 and white (background) represented as 0 are referred as binary images. Representation of English alphabet T as a binary image is illustrated in figure 1.2. Figure 1.2 Image Representation Mask is an array of values specifying the relative importance of sub pixels. Most of the thinning algorithms based on spatial domain processing techniques use masks of size 3x3 as shown in figure 1.3. Pixels P1, P2, P3, P4,

5 5 P5, P6, P7 and P8 are 8-neighbors of the candidate pixel Pi denoted as N8 (Pi). Whereas P2, P4, P6 and P8 are 4-neighbors of Pi denoted as N4 (Pi). Thus N8 (Pi) = {P1, P2, P3, P4, P5, P6, P7, P8} N4 (Pi) = {P2, P4, P6, P8} Figure 1.3 Pixel representation of 3X3 mask The pixel connectivity is a way in which pixels relate to their neighbors. If the pixels are connected horizontally and vertically in terms of pixel coordinates, it is termed as 4-connectivity. In 8-connectivity, pixels are connected diagonally besides horizontal and vertical. Two pixels P and Q are said to be 4-connected, if Q is a 4-neighbor of P or 8-connected, if Q is an 8-neighbor of P. Pixel is said to be 4-simple or 8-simple, if we change the pixel from foreground to background, it does not change the 4- connectivity or 8-connectivity of 1's in its neighborhood respectively. Connected Component is an ordered set of foreground pixels such a way that any two successive pixels should be neighbors of each other. Based on the connectivity of the successive pixels the corresponding connected

6 6 component is referred to as either 4-connected component or 8- connected component. The break point is a foreground pixel which breaks the connectedness of the original object if it is changed to background. An edge or border point is a pixel with at least one background 4-neighbor. Redundant points are pixels that are belonging to the skeleton whose removal doesn t affect the pixel connectivity. Iteration refers to processing of all the border pixels which belong to a single layer. Scan (pass or cycle) refers to processing of all the border pixels layer by layer until no more pixels are deleted. By placing a 3x3 mask on the foreground (black) pixel of an image, one can define three spatial domain operators on the 8-Neighborhood of Pi. The first spatial domain operator denoted by BP is the number of foreground pixel in the neighborhood of the candidate pixel. The second operator denoted by AP is the number of 4-connected components (4-CC) in the neighbourhood of a candidate pixel. The 4-connected component is a group of foreground pixels which are 4-connected in clock-wise order of {P1, P2... P8, P1}. One can easily compute the 4-connected component by calculating the number of zero-to-one or one-to-zero transitions. Third operator denoted by CP is the number of 8-connected components (8-CC)

7 7 count in the neighbourhood of the candidate pixel. The sequence of foreground pixels where any two successive pixels are 8-connected is referred to as 8-connected component. A 4-connected component is also an 8-connected component but the converse is not true. The three spatial domain operators BP, AP and CP are illustrated in the example figures 1.4 (a), (b) and (c). Figure 1.4 Illustration of BP, AP and CP values Based on the definitions of BP, AP and CP, an end point can be defined as a pixel whose (BP = 1) or (BP = 2 and AP = 1) or (BP = 2 and AP = 2 and CP = 1) as illustrated in the following figure 1.5 (a), (b) and (c) respectively.

8 8 Figure 1.5 Example end point cases 1.4 Principles of thinning Binary image thinning algorithms based on the assumption that images to be thinned have only two possible intensity values 0 and 1. Hence all the input images have more than two intensity levels (gray or color) need to be converted to binary images. Normally thresholding technique is used as a preprocessing step to convert the images into binary. If a pixel in the image has intensity less than the threshold value, the corresponding pixel in the resultant image is set to black (1). If the pixel intensity is greater than or equal to the threshold intensity, the resulting pixel is set to white (0). The input images need to be transformed into skeletons containing essential information. This transformation simplifies further processing in most of the pattern recognition problems. The process of obtaining skeletons referred as skeletonization which is a spatial domain processing technique. The skeletonization operates directly on the aggregate of the pixels that compose the image. Skeletons are usually

9 9 obtained through an iterative reduction using a thinning operator called thinning. In this process, pixels whose removal will not affect the shape and size of the image (simple pixels) are iteratively removed until no more pixels can be deleted. Pixels can be removed either one-by-one (sequential) or layer-by-layer (parallel). The endpoint criteria and different spatial processing operators (BP, AP and CP) discussed in section 1.2 are used to make the decisions about pixel deletions. These combinations can be converted into a set of masks termed as templates which can be matched against the candidate pixel neighborhood. These templates can be rewritten into rules in the form of if the neighborhood matches with the input template, then change it into resultant template. The latter approaches are termed as rule-based approaches. 1.5 Issues involved in thinning The hardest task of thinning algorithms is to obtain the skeleton near the central axis. To tackle this problem, existing algorithms in the literature used the technique of dividing the entire process into sub-cycles (passes). The second major task of thinning is excessive erosion. To overcome this problem, approaches like smoothing templates and flagmap techniques, are used. The third major task is the connectivity preservation. Parallel algorithms are more vulnerable to discontinuities compared to sequential

10 10 algorithms. Thus to preserve connectivity in parallel algorithms, one should adopt a method to retain the pixel that cause discontinuity. Fourth, redundant points do not make contribution to the connectivity and thus should be removed to improve the thinning ratio. Unfortunately, most of the thinning algorithms can not delete all the redundant pixels. The number of redundant pixels in a skeleton is inversely proportional to the quality of the skeleton. The quality of the obtained skeleton can be judged based on how well it enhances the later processing steps. Thus defining the skeleton of an object uniquely is difficult. This vagueness causes difficulties in evaluating and comparing different thinning algorithms. But there are some properties of skeletons such as thinness, connectivity and sensitivity which are measured using mathematical equations. 1.6 Motivation for the present work There are some limitations in existing thinning algorithms. Parallel algorithms use non-isotropic way to find end points that result in producing nearly similar skeletons for specific orientations like multiples of right angles (90 0 ). Whereas for other angles they produce different skeletons which may be with unnecessary information such as spurs or ridges. These are the bottlenecks for the recognition processes. Some thinning algorithms are developed to suit the specific needs (script dependent) of the application where they can be applied but these algorithms fail for other application areas. Within the same application domain, algorithm that works best for

11 11 most of the patterns fails for other types of patterns which are similar in appearance. Sometimes the resultant skeleton may contain more than one pixel and cause discontinuities if it thins further. These limitations motivated us for the further investigation and to find the possible solution to overcome the above limitations. 1.7 Background of the problem In the literature, novel approaches are proposed to improve the performance of the existing thinning methods. Some algorithms result in good skeletons for specialized patterns they are concentrating on, but produce poor skeletons for other types of patterns. For example, thinning algorithms for patterns containing only straight lines may not be suitable for thinning patterns composed of only curves (Telugu Handwritten Characters). Further the finger print patterns require specialized algorithms as the small ridges and furrows can influence the recognition process. Devising a generalized thinning algorithm which can produce satisfactory results for all varieties of pattern shapes is very difficult [Fu, Ya- Ching & Pavlidis, 1999]. But the thinning algorithms developed recently [Ahmad and ward, 2002][Peter I,Rocket,2005][Gabor Nemeth and Kalman Palagyi,2009] aimed at more than one application area but are not completely generalized.

12 Problem statement This research work focuses on the development of parallel binary image thinning algorithms which are order independent, rotation invariant and scale invariant. Besides this, they are size and shape preserving. The proposed algorithms produce one pixel wide connected skeletons on a wide variety of image patterns ranging from linear to non-linear. We want to make the thinning algorithm independent of application areas ranging from thinning characters of different languages to finger prints. The performance and results obtained are compared with existing thinning algorithms in terms of excessive erosion, connectivity, thickness and symmetry of the skeletons, endpoint preservation, and visual quality after skeletonization. 1.9 Objective of the work For the task like character recognition, thinning operation is used as a pre-processing step. An effective thinning helps in better recognition performance. In the recent past, most of the researchers have concentrated on reducing the thinning time of the algorithm than the resulting skeleton shape [T.Y.Zhang and C. Y.suen, 1984]. A few of them focused on the quality of the skeleton produced [Gabor Nemeth and Kalman Palagyi, 2009]. It is difficult to produce an algorithm which can simultaneously focus on both thinning time and skeleton quality. Hence, the main objective of the proposed work is to develop a robust thinning algorithm that focuses simultaneously on both these factors. Besides these it also considers the

13 13 order-independent, rotation-invariant properties and preserves topological and geometrical properties of the obtained skeletons Scope of the work The research work carried out in this thesis is not limited to thinning particular types of binary image patterns. The proposed algorithm is generic in nature and considers varieties of image patterns varying from characters of different languages to objects of linear and non-linear shapes and finger print images. Further proposed algorithm considers achieving one pixel wide connected skeletons around the medial axis Organization of the thesis The thesis is organized as follows. Chapters 2 deals with literature survey which reviews the existing iterative and non-iterative thinning algorithms. Chapter 3 gives a detailed description of the implementation of i) an efficient two-pass approach ii) improved two-pass approach and iii) rule based order independent algorithms for binary images. Topology preserving and making the implementation time efficient are also discussed in this chapter. A detailed analysis and comparison of these algorithms is explained in chapter 4. The analysis and comparison are based on the results of both simple input patterns and real images. Finally, the conclusions are summarized in chapter 5.

Morphological segmentation of histology cell images

Morphological segmentation of histology cell images Morphological segmentation of histology cell images A.Nedzved, S.Ablameyko, I.Pitas Institute of Engineering Cybernetics of the National Academy of Sciences Surganova, 6, 00 Minsk, Belarus E-mail abl@newman.bas-net.by

More information

Face detection is a process of localizing and extracting the face region from the

Face detection is a process of localizing and extracting the face region from the Chapter 4 FACE NORMALIZATION 4.1 INTRODUCTION Face detection is a process of localizing and extracting the face region from the background. The detected face varies in rotation, brightness, size, etc.

More information

The Role of Size Normalization on the Recognition Rate of Handwritten Numerals

The Role of Size Normalization on the Recognition Rate of Handwritten Numerals The Role of Size Normalization on the Recognition Rate of Handwritten Numerals Chun Lei He, Ping Zhang, Jianxiong Dong, Ching Y. Suen, Tien D. Bui Centre for Pattern Recognition and Machine Intelligence,

More information

Classification of Fingerprints. Sarat C. Dass Department of Statistics & Probability

Classification of Fingerprints. Sarat C. Dass Department of Statistics & Probability Classification of Fingerprints Sarat C. Dass Department of Statistics & Probability Fingerprint Classification Fingerprint classification is a coarse level partitioning of a fingerprint database into smaller

More information

Introduction. Chapter 1

Introduction. Chapter 1 1 Chapter 1 Introduction Robotics and automation have undergone an outstanding development in the manufacturing industry over the last decades owing to the increasing demand for higher levels of productivity

More information

Recognition of Handwritten Digits using Structural Information

Recognition of Handwritten Digits using Structural Information Recognition of Handwritten Digits using Structural Information Sven Behnke Martin-Luther University, Halle-Wittenberg' Institute of Computer Science 06099 Halle, Germany { behnke Irojas} @ informatik.uni-halle.de

More information

Palmprint Recognition. By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap

Palmprint Recognition. By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap Palmprint Recognition By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap Palm print Palm Patterns are utilized in many applications: 1. To correlate palm patterns with medical disorders, e.g. genetic

More information

Part-Based Recognition

Part-Based Recognition Part-Based Recognition Benedict Brown CS597D, Fall 2003 Princeton University CS 597D, Part-Based Recognition p. 1/32 Introduction Many objects are made up of parts It s presumably easier to identify simple

More information

Canny Edge Detection

Canny Edge Detection Canny Edge Detection 09gr820 March 23, 2009 1 Introduction The purpose of edge detection in general is to significantly reduce the amount of data in an image, while preserving the structural properties

More information

ECE 533 Project Report Ashish Dhawan Aditi R. Ganesan

ECE 533 Project Report Ashish Dhawan Aditi R. Ganesan Handwritten Signature Verification ECE 533 Project Report by Ashish Dhawan Aditi R. Ganesan Contents 1. Abstract 3. 2. Introduction 4. 3. Approach 6. 4. Pre-processing 8. 5. Feature Extraction 9. 6. Verification

More information

Binary Image Scanning Algorithm for Cane Segmentation

Binary Image Scanning Algorithm for Cane Segmentation Binary Image Scanning Algorithm for Cane Segmentation Ricardo D. C. Marin Department of Computer Science University Of Canterbury Canterbury, Christchurch ricardo.castanedamarin@pg.canterbury.ac.nz Tom

More information

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta Vol. 8, No. 2 ISSN 2064-7964 EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

More information

Automatic Extraction of Signatures from Bank Cheques and other Documents

Automatic Extraction of Signatures from Bank Cheques and other Documents Automatic Extraction of Signatures from Bank Cheques and other Documents Vamsi Krishna Madasu *, Mohd. Hafizuddin Mohd. Yusof, M. Hanmandlu ß, Kurt Kubik * *Intelligent Real-Time Imaging and Sensing group,

More information

SIGNATURE VERIFICATION

SIGNATURE VERIFICATION SIGNATURE VERIFICATION Dr. H.B.Kekre, Dr. Dhirendra Mishra, Ms. Shilpa Buddhadev, Ms. Bhagyashree Mall, Mr. Gaurav Jangid, Ms. Nikita Lakhotia Computer engineering Department, MPSTME, NMIMS University

More information

Open Access A Facial Expression Recognition Algorithm Based on Local Binary Pattern and Empirical Mode Decomposition

Open Access A Facial Expression Recognition Algorithm Based on Local Binary Pattern and Empirical Mode Decomposition Send Orders for Reprints to reprints@benthamscience.ae The Open Electrical & Electronic Engineering Journal, 2014, 8, 599-604 599 Open Access A Facial Expression Recognition Algorithm Based on Local Binary

More information

Locating and Decoding EAN-13 Barcodes from Images Captured by Digital Cameras

Locating and Decoding EAN-13 Barcodes from Images Captured by Digital Cameras Locating and Decoding EAN-13 Barcodes from Images Captured by Digital Cameras W3A.5 Douglas Chai and Florian Hock Visual Information Processing Research Group School of Engineering and Mathematics Edith

More information

Visual Structure Analysis of Flow Charts in Patent Images

Visual Structure Analysis of Flow Charts in Patent Images Visual Structure Analysis of Flow Charts in Patent Images Roland Mörzinger, René Schuster, András Horti, and Georg Thallinger JOANNEUM RESEARCH Forschungsgesellschaft mbh DIGITAL - Institute for Information

More information

How To Fix Out Of Focus And Blur Images With A Dynamic Template Matching Algorithm

How To Fix Out Of Focus And Blur Images With A Dynamic Template Matching Algorithm IJSTE - International Journal of Science Technology & Engineering Volume 1 Issue 10 April 2015 ISSN (online): 2349-784X Image Estimation Algorithm for Out of Focus and Blur Images to Retrieve the Barcode

More information

MAVIparticle Modular Algorithms for 3D Particle Characterization

MAVIparticle Modular Algorithms for 3D Particle Characterization MAVIparticle Modular Algorithms for 3D Particle Characterization version 1.0 Image Processing Department Fraunhofer ITWM Contents Contents 1 Introduction 2 2 The program 2 2.1 Framework..............................

More information

Minnesota Academic Standards

Minnesota Academic Standards A Correlation of to the Minnesota Academic Standards Grades K-6 G/M-204 Introduction This document demonstrates the high degree of success students will achieve when using Scott Foresman Addison Wesley

More information

Printed Circuit Board Defect Detection using Wavelet Transform

Printed Circuit Board Defect Detection using Wavelet Transform Research Article International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347-5161 2014 INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Amit

More information

Categorical Data Visualization and Clustering Using Subjective Factors

Categorical Data Visualization and Clustering Using Subjective Factors Categorical Data Visualization and Clustering Using Subjective Factors Chia-Hui Chang and Zhi-Kai Ding Department of Computer Science and Information Engineering, National Central University, Chung-Li,

More information

Digital image processing

Digital image processing 746A27 Remote Sensing and GIS Lecture 4 Digital image processing Chandan Roy Guest Lecturer Department of Computer and Information Science Linköping University Digital Image Processing Most of the common

More information

Current Standard: Mathematical Concepts and Applications Shape, Space, and Measurement- Primary

Current Standard: Mathematical Concepts and Applications Shape, Space, and Measurement- Primary Shape, Space, and Measurement- Primary A student shall apply concepts of shape, space, and measurement to solve problems involving two- and three-dimensional shapes by demonstrating an understanding of:

More information

BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES

BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES 123 CHAPTER 7 BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES 7.1 Introduction Even though using SVM presents

More information

Sharpening through spatial filtering

Sharpening through spatial filtering Sharpening through spatial filtering Stefano Ferrari Università degli Studi di Milano stefano.ferrari@unimi.it Elaborazione delle immagini (Image processing I) academic year 2011 2012 Sharpening The term

More information

Poker Vision: Playing Cards and Chips Identification based on Image Processing

Poker Vision: Playing Cards and Chips Identification based on Image Processing Poker Vision: Playing Cards and Chips Identification based on Image Processing Paulo Martins 1, Luís Paulo Reis 2, and Luís Teófilo 2 1 DEEC Electrical Engineering Department 2 LIACC Artificial Intelligence

More information

STATIC SIGNATURE RECOGNITION SYSTEM FOR USER AUTHENTICATION BASED TWO LEVEL COG, HOUGH TRANSFORM AND NEURAL NETWORK

STATIC SIGNATURE RECOGNITION SYSTEM FOR USER AUTHENTICATION BASED TWO LEVEL COG, HOUGH TRANSFORM AND NEURAL NETWORK Volume 6, Issue 3, pp: 335343 IJESET STATIC SIGNATURE RECOGNITION SYSTEM FOR USER AUTHENTICATION BASED TWO LEVEL COG, HOUGH TRANSFORM AND NEURAL NETWORK Dipti Verma 1, Sipi Dubey 2 1 Department of Computer

More information

Fingerprint s Core Point Detection using Gradient Field Mask

Fingerprint s Core Point Detection using Gradient Field Mask Fingerprint s Core Point Detection using Gradient Field Mask Ashish Mishra Assistant Professor Dept. of Computer Science, GGCT, Jabalpur, [M.P.], Dr.Madhu Shandilya Associate Professor Dept. of Electronics.MANIT,Bhopal[M.P.]

More information

Grade 5 Math Content 1

Grade 5 Math Content 1 Grade 5 Math Content 1 Number and Operations: Whole Numbers Multiplication and Division In Grade 5, students consolidate their understanding of the computational strategies they use for multiplication.

More information

3D Scanner using Line Laser. 1. Introduction. 2. Theory

3D Scanner using Line Laser. 1. Introduction. 2. Theory . Introduction 3D Scanner using Line Laser Di Lu Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute The goal of 3D reconstruction is to recover the 3D properties of a geometric

More information

The Scientific Data Mining Process

The Scientific Data Mining Process Chapter 4 The Scientific Data Mining Process When I use a word, Humpty Dumpty said, in rather a scornful tone, it means just what I choose it to mean neither more nor less. Lewis Carroll [87, p. 214] In

More information

A Study of Automatic License Plate Recognition Algorithms and Techniques

A Study of Automatic License Plate Recognition Algorithms and Techniques A Study of Automatic License Plate Recognition Algorithms and Techniques Nima Asadi Intelligent Embedded Systems Mälardalen University Västerås, Sweden nai10001@student.mdh.se ABSTRACT One of the most

More information

Big Ideas in Mathematics

Big Ideas in Mathematics Big Ideas in Mathematics which are important to all mathematics learning. (Adapted from the NCTM Curriculum Focal Points, 2006) The Mathematics Big Ideas are organized using the PA Mathematics Standards

More information

Assessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall

Assessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Automatic Photo Quality Assessment Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Estimating i the photorealism of images: Distinguishing i i paintings from photographs h Florin

More information

The Basics of FEA Procedure

The Basics of FEA Procedure CHAPTER 2 The Basics of FEA Procedure 2.1 Introduction This chapter discusses the spring element, especially for the purpose of introducing various concepts involved in use of the FEA technique. A spring

More information

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic

More information

DEVELOPMENT OF HYBRID VECTORIZING SOFTWARE FOR DIGITIZATION OF CADASTRAL MAPS

DEVELOPMENT OF HYBRID VECTORIZING SOFTWARE FOR DIGITIZATION OF CADASTRAL MAPS DEVELOPMENT OF HYBRID VECTORIZING SOFTWARE FOR DIGITIZATION OF CADASTRAL MAPS Byoungjun SEO, Jaejoon JEONG, Jaebin LEE and Prof. Yongil KIM, Korea ABSTRACT The Cadastral map is a basic data that prescribes

More information

A SECURE EMAIL CLIENT APPLICATION USING RETINAL IMAGE MATCHING

A SECURE EMAIL CLIENT APPLICATION USING RETINAL IMAGE MATCHING A SECURE EMAIL CLIENT APPLICATION USING RETINAL IMAGE MATCHING ANKITA KANTESH 1, SUPRIYA S. BEHERA 2, JYOTI BHOITE 3, ANAMIKA KUMARI 4 1,2,3,4 B.E, University of Pune Abstract- As technology advances,

More information

EXPLORING SPATIAL PATTERNS IN YOUR DATA

EXPLORING SPATIAL PATTERNS IN YOUR DATA EXPLORING SPATIAL PATTERNS IN YOUR DATA OBJECTIVES Learn how to examine your data using the Geostatistical Analysis tools in ArcMap. Learn how to use descriptive statistics in ArcMap and Geoda to analyze

More information

Bildverarbeitung und Mustererkennung Image Processing and Pattern Recognition

Bildverarbeitung und Mustererkennung Image Processing and Pattern Recognition Bildverarbeitung und Mustererkennung Image Processing and Pattern Recognition 1. Image Pre-Processing - Pixel Brightness Transformation - Geometric Transformation - Image Denoising 1 1. Image Pre-Processing

More information

Circle Object Recognition Based on Monocular Vision for Home Security Robot

Circle Object Recognition Based on Monocular Vision for Home Security Robot Journal of Applied Science and Engineering, Vol. 16, No. 3, pp. 261 268 (2013) DOI: 10.6180/jase.2013.16.3.05 Circle Object Recognition Based on Monocular Vision for Home Security Robot Shih-An Li, Ching-Chang

More information

Multimodal Biometric Recognition Security System

Multimodal Biometric Recognition Security System Multimodal Biometric Recognition Security System Anju.M.I, G.Sheeba, G.Sivakami, Monica.J, Savithri.M Department of ECE, New Prince Shri Bhavani College of Engg. & Tech., Chennai, India ABSTRACT: Security

More information

Fast Sequential Summation Algorithms Using Augmented Data Structures

Fast Sequential Summation Algorithms Using Augmented Data Structures Fast Sequential Summation Algorithms Using Augmented Data Structures Vadim Stadnik vadim.stadnik@gmail.com Abstract This paper provides an introduction to the design of augmented data structures that offer

More information

Major Work of the Grade

Major Work of the Grade Counting and Cardinality Know number names and the count sequence. Count to tell the number of objects. Compare numbers. Kindergarten Describe and compare measurable attributes. Classify objects and count

More information

jorge s. marques image processing

jorge s. marques image processing image processing images images: what are they? what is shown in this image? What is this? what is an image images describe the evolution of physical variables (intensity, color, reflectance, condutivity)

More information

Handwritten Character Recognition from Bank Cheque

Handwritten Character Recognition from Bank Cheque International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-4, Special Issue-1 E-ISSN: 2347-2693 Handwritten Character Recognition from Bank Cheque Siddhartha Banerjee*

More information

Static Environment Recognition Using Omni-camera from a Moving Vehicle

Static Environment Recognition Using Omni-camera from a Moving Vehicle Static Environment Recognition Using Omni-camera from a Moving Vehicle Teruko Yata, Chuck Thorpe Frank Dellaert The Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 USA College of Computing

More information

Building an Advanced Invariant Real-Time Human Tracking System

Building an Advanced Invariant Real-Time Human Tracking System UDC 004.41 Building an Advanced Invariant Real-Time Human Tracking System Fayez Idris 1, Mazen Abu_Zaher 2, Rashad J. Rasras 3, and Ibrahiem M. M. El Emary 4 1 School of Informatics and Computing, German-Jordanian

More information

Classroom Tips and Techniques: The Student Precalculus Package - Commands and Tutors. Content of the Precalculus Subpackage

Classroom Tips and Techniques: The Student Precalculus Package - Commands and Tutors. Content of the Precalculus Subpackage Classroom Tips and Techniques: The Student Precalculus Package - Commands and Tutors Robert J. Lopez Emeritus Professor of Mathematics and Maple Fellow Maplesoft This article provides a systematic exposition

More information

2.2 Creaseness operator

2.2 Creaseness operator 2.2. Creaseness operator 31 2.2 Creaseness operator Antonio López, a member of our group, has studied for his PhD dissertation the differential operators described in this section [72]. He has compared

More information

3)Skilled Forgery: It is represented by suitable imitation of genuine signature mode.it is also called Well-Versed Forgery[4].

3)Skilled Forgery: It is represented by suitable imitation of genuine signature mode.it is also called Well-Versed Forgery[4]. Volume 4, Issue 7, July 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A New Technique

More information

A Learning Based Method for Super-Resolution of Low Resolution Images

A Learning Based Method for Super-Resolution of Low Resolution Images A Learning Based Method for Super-Resolution of Low Resolution Images Emre Ugur June 1, 2004 emre.ugur@ceng.metu.edu.tr Abstract The main objective of this project is the study of a learning based method

More information

Automatic Detection of PCB Defects

Automatic Detection of PCB Defects IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 6 November 2014 ISSN (online): 2349-6010 Automatic Detection of PCB Defects Ashish Singh PG Student Vimal H.

More information

WORK SCHEDULE: MATHEMATICS 2007

WORK SCHEDULE: MATHEMATICS 2007 , K WORK SCHEDULE: MATHEMATICS 00 GRADE MODULE TERM... LO NUMBERS, OPERATIONS AND RELATIONSHIPS able to recognise, represent numbers and their relationships, and to count, estimate, calculate and check

More information

Colour Image Segmentation Technique for Screen Printing

Colour Image Segmentation Technique for Screen Printing 60 R.U. Hewage and D.U.J. Sonnadara Department of Physics, University of Colombo, Sri Lanka ABSTRACT Screen-printing is an industry with a large number of applications ranging from printing mobile phone

More information

Traditional Drawing Tools

Traditional Drawing Tools Engineering Drawing Traditional Drawing Tools DRAWING TOOLS DRAWING TOOLS 1. T-Square 2. Triangles DRAWING TOOLS HB for thick line 2H for thin line 3. Adhesive Tape 4. Pencils DRAWING TOOLS 5. Sandpaper

More information

Subspace Analysis and Optimization for AAM Based Face Alignment

Subspace Analysis and Optimization for AAM Based Face Alignment Subspace Analysis and Optimization for AAM Based Face Alignment Ming Zhao Chun Chen College of Computer Science Zhejiang University Hangzhou, 310027, P.R.China zhaoming1999@zju.edu.cn Stan Z. Li Microsoft

More information

Overview. 1. Introduction. 2. Parts of the Project. 3. Conclusion. Motivation. Methods used in the project Results and comparison

Overview. 1. Introduction. 2. Parts of the Project. 3. Conclusion. Motivation. Methods used in the project Results and comparison Institute of Integrated Sensor Systems Dept. of Electrical Engineering and Information Technology An Image Processing Application on QuickCog and Matlab Door-Key Recognition System Lei Yang Oct, 2009 Prof.

More information

Knowledge Discovery and Data Mining. Structured vs. Non-Structured Data

Knowledge Discovery and Data Mining. Structured vs. Non-Structured Data Knowledge Discovery and Data Mining Unit # 2 1 Structured vs. Non-Structured Data Most business databases contain structured data consisting of well-defined fields with numeric or alphanumeric values.

More information

Generating Named Road Vector Data from Raster Maps

Generating Named Road Vector Data from Raster Maps Generating Named Road Vector Data from Raster Maps Yao-Yi Chiang 1 and Craig A. Knoblock 2 1 University of Southern California, Information Sciences Institute and Spatial Sciences Institute 4676 Admiralty

More information

Solving Simultaneous Equations and Matrices

Solving Simultaneous Equations and Matrices Solving Simultaneous Equations and Matrices The following represents a systematic investigation for the steps used to solve two simultaneous linear equations in two unknowns. The motivation for considering

More information

PARAMETRIC MODELING. David Rosen. December 1997. By carefully laying-out datums and geometry, then constraining them with dimensions and constraints,

PARAMETRIC MODELING. David Rosen. December 1997. By carefully laying-out datums and geometry, then constraining them with dimensions and constraints, 1 of 5 11/18/2004 6:24 PM PARAMETRIC MODELING David Rosen December 1997 The term parametric modeling denotes the use of parameters to control the dimensions and shape of CAD models. Think of a rubber CAD

More information

Two novel characteristics in palmprint verification: datum point invariance and line feature matching

Two novel characteristics in palmprint verification: datum point invariance and line feature matching Pattern Recognition 32 (1999) 691 702 Two novel characteristics in palmprint verification: datum point invariance and line feature matching Dapeng Zhang*, Wei Shu Department of Computing, Hong Kong Polytechnic

More information

Introduction to Pattern Recognition

Introduction to Pattern Recognition Introduction to Pattern Recognition Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2009 CS 551, Spring 2009 c 2009, Selim Aksoy (Bilkent University)

More information

CATIA Wireframe & Surfaces TABLE OF CONTENTS

CATIA Wireframe & Surfaces TABLE OF CONTENTS TABLE OF CONTENTS Introduction... 1 Wireframe & Surfaces... 2 Pull Down Menus... 3 Edit... 3 Insert... 4 Tools... 6 Generative Shape Design Workbench... 7 Bottom Toolbar... 9 Tools... 9 Analysis... 10

More information

High-Performance Signature Recognition Method using SVM

High-Performance Signature Recognition Method using SVM High-Performance Signature Recognition Method using SVM Saeid Fazli Research Institute of Modern Biological Techniques University of Zanjan Shima Pouyan Electrical Engineering Department University of

More information

Machine vision systems - 2

Machine vision systems - 2 Machine vision systems Problem definition Image acquisition Image segmentation Connected component analysis Machine vision systems - 1 Problem definition Design a vision system to see a flat world Page

More information

How To Filter Spam Image From A Picture By Color Or Color

How To Filter Spam Image From A Picture By Color Or Color Image Content-Based Email Spam Image Filtering Jianyi Wang and Kazuki Katagishi Abstract With the population of Internet around the world, email has become one of the main methods of communication among

More information

Extend Table Lens for High-Dimensional Data Visualization and Classification Mining

Extend Table Lens for High-Dimensional Data Visualization and Classification Mining Extend Table Lens for High-Dimensional Data Visualization and Classification Mining CPSC 533c, Information Visualization Course Project, Term 2 2003 Fengdong Du fdu@cs.ubc.ca University of British Columbia

More information

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 69 Class Project Report Junhua Mao and Lunbo Xu University of California, Los Angeles mjhustc@ucla.edu and lunbo

More information

Jiří Matas. Hough Transform

Jiří Matas. Hough Transform Hough Transform Jiří Matas Center for Machine Perception Department of Cybernetics, Faculty of Electrical Engineering Czech Technical University, Prague Many slides thanks to Kristen Grauman and Bastian

More information

Galaxy Morphological Classification

Galaxy Morphological Classification Galaxy Morphological Classification Jordan Duprey and James Kolano Abstract To solve the issue of galaxy morphological classification according to a classification scheme modelled off of the Hubble Sequence,

More information

WIN32TRACE USER S GUIDE

WIN32TRACE USER S GUIDE WIN32TRACE USER S GUIDE Win32Trace is a program for converting raster (bitmap) images into vector images. These vector images can then be easily rescaled and are useful in many applications. For example,

More information

System approach to a raster-tovector

System approach to a raster-tovector Eugene Bodansky ESRI ebodansky@esri.com System approach to a raster-tovector conversion How to design a good commercial conversion system Plan of the presentation The main goal of vectorization system

More information

3D Model of the City Using LiDAR and Visualization of Flood in Three-Dimension

3D Model of the City Using LiDAR and Visualization of Flood in Three-Dimension 3D Model of the City Using LiDAR and Visualization of Flood in Three-Dimension R.Queen Suraajini, Department of Civil Engineering, College of Engineering Guindy, Anna University, India, suraa12@gmail.com

More information

HISTOGRAMS, CUMULATIVE FREQUENCY AND BOX PLOTS

HISTOGRAMS, CUMULATIVE FREQUENCY AND BOX PLOTS Mathematics Revision Guides Histograms, Cumulative Frequency and Box Plots Page 1 of 25 M.K. HOME TUITION Mathematics Revision Guides Level: GCSE Higher Tier HISTOGRAMS, CUMULATIVE FREQUENCY AND BOX PLOTS

More information

Scope and Sequence KA KB 1A 1B 2A 2B 3A 3B 4A 4B 5A 5B 6A 6B

Scope and Sequence KA KB 1A 1B 2A 2B 3A 3B 4A 4B 5A 5B 6A 6B Scope and Sequence Earlybird Kindergarten, Standards Edition Primary Mathematics, Standards Edition Copyright 2008 [SingaporeMath.com Inc.] The check mark indicates where the topic is first introduced

More information

Algorithm for License Plate Localization and Recognition for Tanzania Car Plate Numbers

Algorithm for License Plate Localization and Recognition for Tanzania Car Plate Numbers Algorithm for License Plate Localization and Recognition for Tanzania Car Plate Numbers Isack Bulugu Department of Electronics Engineering, Tianjin University of Technology and Education, Tianjin, P.R.

More information

A Method of Caption Detection in News Video

A Method of Caption Detection in News Video 3rd International Conference on Multimedia Technology(ICMT 3) A Method of Caption Detection in News Video He HUANG, Ping SHI Abstract. News video is one of the most important media for people to get information.

More information

Object Recognition and Template Matching

Object Recognition and Template Matching Object Recognition and Template Matching Template Matching A template is a small image (sub-image) The goal is to find occurrences of this template in a larger image That is, you want to find matches of

More information

Tracking and Recognition in Sports Videos

Tracking and Recognition in Sports Videos Tracking and Recognition in Sports Videos Mustafa Teke a, Masoud Sattari b a Graduate School of Informatics, Middle East Technical University, Ankara, Turkey mustafa.teke@gmail.com b Department of Computer

More information

Glencoe. correlated to SOUTH CAROLINA MATH CURRICULUM STANDARDS GRADE 6 3-3, 5-8 8-4, 8-7 1-6, 4-9

Glencoe. correlated to SOUTH CAROLINA MATH CURRICULUM STANDARDS GRADE 6 3-3, 5-8 8-4, 8-7 1-6, 4-9 Glencoe correlated to SOUTH CAROLINA MATH CURRICULUM STANDARDS GRADE 6 STANDARDS 6-8 Number and Operations (NO) Standard I. Understand numbers, ways of representing numbers, relationships among numbers,

More information

Medical Image Segmentation of PACS System Image Post-processing *

Medical Image Segmentation of PACS System Image Post-processing * Medical Image Segmentation of PACS System Image Post-processing * Lv Jie, Xiong Chun-rong, and Xie Miao Department of Professional Technical Institute, Yulin Normal University, Yulin Guangxi 537000, China

More information

RESEARCH PAPERS FACULTY OF MATERIALS SCIENCE AND TECHNOLOGY IN TRNAVA SLOVAK UNIVERSITY OF TECHNOLOGY IN BRATISLAVA

RESEARCH PAPERS FACULTY OF MATERIALS SCIENCE AND TECHNOLOGY IN TRNAVA SLOVAK UNIVERSITY OF TECHNOLOGY IN BRATISLAVA RESEARCH PAPERS FACULTY OF MATERIALS SCIENCE AND TECHNOLOGY IN TRNAVA SLOVAK UNIVERSITY OF TECHNOLOGY IN BRATISLAVA 2010 Number 29 3D MODEL GENERATION FROM THE ENGINEERING DRAWING Jozef VASKÝ, Michal ELIÁŠ,

More information

Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data

Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data CMPE 59H Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data Term Project Report Fatma Güney, Kübra Kalkan 1/15/2013 Keywords: Non-linear

More information

Implementation of Canny Edge Detector of color images on CELL/B.E. Architecture.

Implementation of Canny Edge Detector of color images on CELL/B.E. Architecture. Implementation of Canny Edge Detector of color images on CELL/B.E. Architecture. Chirag Gupta,Sumod Mohan K cgupta@clemson.edu, sumodm@clemson.edu Abstract In this project we propose a method to improve

More information

An Algorithm for Classification of Five Types of Defects on Bare Printed Circuit Board

An Algorithm for Classification of Five Types of Defects on Bare Printed Circuit Board IJCSES International Journal of Computer Sciences and Engineering Systems, Vol. 5, No. 3, July 2011 CSES International 2011 ISSN 0973-4406 An Algorithm for Classification of Five Types of Defects on Bare

More information

COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS

COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS B.K. Mohan and S. N. Ladha Centre for Studies in Resources Engineering IIT

More information

Taking Inverse Graphics Seriously

Taking Inverse Graphics Seriously CSC2535: 2013 Advanced Machine Learning Taking Inverse Graphics Seriously Geoffrey Hinton Department of Computer Science University of Toronto The representation used by the neural nets that work best

More information

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network Proceedings of the 8th WSEAS Int. Conf. on ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING & DATA BASES (AIKED '9) ISSN: 179-519 435 ISBN: 978-96-474-51-2 An Energy-Based Vehicle Tracking System using Principal

More information

Image Compression through DCT and Huffman Coding Technique

Image Compression through DCT and Huffman Coding Technique International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015 INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Rahul

More information

Clustering & Visualization

Clustering & Visualization Chapter 5 Clustering & Visualization Clustering in high-dimensional databases is an important problem and there are a number of different clustering paradigms which are applicable to high-dimensional data.

More information

GEOGRAPHIC INFORMATION SYSTEMS

GEOGRAPHIC INFORMATION SYSTEMS GIS GEOGRAPHIC INFORMATION SYSTEMS FOR CADASTRAL MAPPING Chapter 7 2015 Cadastral Mapping Manual 7-0 GIS - GEOGRAPHIC INFORMATION SYSTEMS What is GIS For a long time people have sketched, drawn and studied

More information

5. A full binary tree with n leaves contains [A] n nodes. [B] log n 2 nodes. [C] 2n 1 nodes. [D] n 2 nodes.

5. A full binary tree with n leaves contains [A] n nodes. [B] log n 2 nodes. [C] 2n 1 nodes. [D] n 2 nodes. 1. The advantage of.. is that they solve the problem if sequential storage representation. But disadvantage in that is they are sequential lists. [A] Lists [B] Linked Lists [A] Trees [A] Queues 2. The

More information

A Binary Adaptable Window SoC Architecture for a StereoVision Based Depth Field Processor

A Binary Adaptable Window SoC Architecture for a StereoVision Based Depth Field Processor A Binary Adaptable Window SoC Architecture for a StereoVision Based Depth Field Processor Andy Motten, Luc Claesen Expertise Centre for Digital Media Hasselt University tul IBBT Wetenschapspark 2, 50 Diepenbeek,

More information

A Simple Feature Extraction Technique of a Pattern By Hopfield Network

A Simple Feature Extraction Technique of a Pattern By Hopfield Network A Simple Feature Extraction Technique of a Pattern By Hopfield Network A.Nag!, S. Biswas *, D. Sarkar *, P.P. Sarkar *, B. Gupta **! Academy of Technology, Hoogly - 722 *USIC, University of Kalyani, Kalyani

More information

Implementation of OCR Based on Template Matching and Integrating it in Android Application

Implementation of OCR Based on Template Matching and Integrating it in Android Application International Journal of Computer Sciences and EngineeringOpen Access Technical Paper Volume-04, Issue-02 E-ISSN: 2347-2693 Implementation of OCR Based on Template Matching and Integrating it in Android

More information

Intrusion Detection System using Log Files and Reinforcement Learning

Intrusion Detection System using Log Files and Reinforcement Learning Intrusion Detection System using Log Files and Reinforcement Learning Bhagyashree Deokar, Ambarish Hazarnis Department of Computer Engineering K. J. Somaiya College of Engineering, Mumbai, India ABSTRACT

More information