Gabor Features for Offline Arabic Handwriting Recognition

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

Document Image Retrieval using Signatures as Queries

Cursive Handwriting Recognition for Document Archiving

Signature verification using Kolmogorov-Smirnov. statistic

Signature Segmentation from Machine Printed Documents using Conditional Random Field

Unconstrained Handwritten Character Recognition Using Different Classification Strategies

Recognition Method for Handwritten Digits Based on Improved Chain Code Histogram Feature

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

Numerical Field Extraction in Handwritten Incoming Mail Documents

NAVIGATING SCIENTIFIC LITERATURE A HOLISTIC PERSPECTIVE. Venu Govindaraju

Recognition of Handwritten Digits using Structural Information

ECE 533 Project Report Ashish Dhawan Aditi R. Ganesan

DIAGONAL BASED FEATURE EXTRACTION FOR HANDWRITTEN ALPHABETS RECOGNITION SYSTEM USING NEURAL NETWORK

Signature Segmentation and Recognition from Scanned Documents

Online Farsi Handwritten Character Recognition Using Hidden Markov Model

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

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

Analecta Vol. 8, No. 2 ISSN

RFID and Camera-based Hybrid Approach to Track Vehicle within Campus

III. SEGMENTATION. A. Origin Segmentation

Using Lexical Similarity in Handwritten Word Recognition

Handwritten Signature Verification using Neural Network

Face Recognition in Low-resolution Images by Using Local Zernike Moments

Introduction to Pattern Recognition

Signature Region of Interest using Auto cropping

Keywords image processing, signature verification, false acceptance rate, false rejection rate, forgeries, feature vectors, support vector machines.

High-Performance Signature Recognition Method using SVM

Recognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang

Bayesian Network Modeling of Hangul Characters for On-line Handwriting Recognition

Handwritten Character Recognition from Bank Cheque

Learning is a very general term denoting the way in which agents:

AN APPROACH ON RECOGNITION OF HAND-WRITTEN LETTERS

DESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD

Off-line Handwriting Recognition by Recurrent Error Propagation Networks

Offline Recognition of Unconstrained Handwritten Texts Using HMMs and Statistical Language Models. Alessandro Vinciarelli, Samy Bengio and Horst Bunke

Galaxy Morphological Classification

FACE RECOGNITION BASED ATTENDANCE MARKING SYSTEM

Leveraging Ensemble Models in SAS Enterprise Miner

2 Signature-Based Retrieval of Scanned Documents Using Conditional Random Fields

The Delicate Art of Flower Classification

CS 2750 Machine Learning. Lecture 1. Machine Learning. CS 2750 Machine Learning.

Handwritten digit segmentation: a comparative study

Face Recognition For Remote Database Backup System

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

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

Image Classification for Dogs and Cats

8 Visualization of high-dimensional data

SIGNATURE VERIFICATION

Novelty Detection in image recognition using IRF Neural Networks properties

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

Efficient online learning of a non-negative sparse autoencoder

PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION

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

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

Machine Learning Introduction

Machine Learning CS Lecture 01. Razvan C. Bunescu School of Electrical Engineering and Computer Science

Morphological analysis on structural MRI for the early diagnosis of neurodegenerative diseases. Marco Aiello On behalf of MAGIC-5 collaboration

IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS

Some Research Challenges for Big Data Analytics of Intelligent Security

Recognition. Sanja Fidler CSC420: Intro to Image Understanding 1 / 28

SPEAKER IDENTIFICATION FROM YOUTUBE OBTAINED DATA

DATA MINING TECHNIQUES AND APPLICATIONS

Automatic Traffic Estimation Using Image Processing

A new normalization technique for cursive handwritten words

AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION

Maschinelles Lernen mit MATLAB

Is a Data Scientist the New Quant? Stuart Kozola MathWorks

Towards better accuracy for Spam predictions

Unsupervised Estimation of Writing Style Models for Improved Unconstrained Off-line Handwriting Recognition

A Study of Automatic License Plate Recognition Algorithms and Techniques

Blog Post Extraction Using Title Finding

Automatic Extraction of Signatures from Bank Cheques and other Documents

Programming Exercise 3: Multi-class Classification and Neural Networks

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

Relative Permeability Measurement in Rock Fractures

Signature Verification Competition for Online and Offline Skilled Forgeries (SigComp2011)

A Partially Supervised Metric Multidimensional Scaling Algorithm for Textual Data Visualization

The Artificial Prediction Market

Blood Vessel Classification into Arteries and Veins in Retinal Images

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

Multimodal Biometric Recognition Security System

Intrusion Detection via Machine Learning for SCADA System Protection

Moment-based Image Normalization for Handwritten Text Recognition

Data Mining and Knowledge Discovery in Databases (KDD) State of the Art. Prof. Dr. T. Nouri Computer Science Department FHNW Switzerland

Simplified Machine Learning for CUDA. Umar

Azure Machine Learning, SQL Data Mining and R

Data, Measurements, Features

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

Script and Language Identification for Handwritten Document Images. Judith Hochberg Kevin Bowers * Michael Cannon Patrick Kelly

ScienceDirect. Brain Image Classification using Learning Machine Approach and Brain Structure Analysis

MHI3000 Big Data Analytics for Health Care Final Project Report

A Dynamic Approach to Extract Texts and Captions from Videos

The Visual Internet of Things System Based on Depth Camera

Establishing the Uniqueness of the Human Voice for Security Applications

siftservice.com - Turning a Computer Vision algorithm into a World Wide Web Service

The Scientific Data Mining Process

Research on Chinese financial invoice recognition technology

Visual Structure Analysis of Flow Charts in Patent Images

Practical Data Science with Azure Machine Learning, SQL Data Mining, and R

An Efficient Geometric feature based License Plate Localization and Stop Line Violation Detection System

Transcription:

Gabor Features for Offline Arabic Handwriting Recognition Jin Chen, Huaigu Cao, Rohit Prasad, Anurag Bhardwaj, Prem Natarajan 9 June 2010 Workshop on Document Analysis and Systems 2010

Outline Introduction Handwriting recognition overview Proposed Gabor features for handwriting recognition Experimental results

Introduction Goal: Improve accuracy of offline Arabic handwriting recognition Challenges: Unconstrained offline handwriting recognition has significantly different writing styles Shapes of the same character glyph vary across writers and even for the same writer Need: Develop features and classifiers that are effective in discriminating handwritten glyphs

Script-Independent Glyph Modeling Using HMMs Hidden Markov Models (HMMs) can model a feature vector as a function of one independent variable Independent variable is time in speech, for text images the independent variable is position within the text line Modeling framework allows for cursive scripts implicitly Does not require pre-segmentation of line images presegmented into words/sub-words/characters Training data simply consists of text image lines with corresponding transcripts Manual segmentation into words or characters is NOT required Note: A glyph is the stroke-segment that corresponds to a writing unit such as a character, a sub-word, or a word

Novel Extension - Stochastic Segment Modeling (SSM) Integrates evidence from different features and recognition approaches HMM generates fuzzy stochastic segments (2-D character images) Apply 2-D classification to the fuzzy segments We use Support Vector Machines (SVM) for 2-D character classification

Common Features for Character Recognition Gradient-Structural-Concavity (GSC) [Favata 94] Concatenate gradient, structural, and concavity features 95% classification accuracy on the NIST handwritten character database Contour Code [Verma 04] Use the rate of slope changes along the contour profile, along with the numbers of ascenders/descenders, start/end points, etc. 85% recognition rate on the BAC handwritten character database Character-SIFT [Zhang 09] Compute dynamic gradient histograms in the elastic-meshing and concatenate them into features 94% recognition rate on the HCL2000 Chinese database

Gabor Filtering based Feature Extraction Limitations of existing features GSC features do not capture width of the stroke Contour features are sensitive to artifacts such as broken strokes and pepper noise Extract features using the output of Gabor filtering Gabor filters are frequency-domain band-pass filters that select the signal at a specific orientation and frequency Captures stroke width and orientations Filtering output is robust to noise artifacts

Overview of Gabor Filtering A 2-D Gabor filter is a complex sinusoidal plane modulated by a Gaussian in the spatial domain: where R1 and R2 are: denotes the wavelength of a Gabor filter denotes the orientation of the filter

Overview of Gabor Filtering (2) In the frequency domain, a Gabor filter is defined as: where K is a constant, F1 and F2 are: Carrier Envelope Gabor Filter http://www.cs.umd.edu/class/spring2005/cmsc838s/assignment-projects/gabor-filter-visualization/report.pdf

Related Work in Gabor Filter Based Features [Wang 05] Set λ according to the stroke width Extract features only using the real part of the filtering response; positive and negative responses are treated separately 98.9% accuracy on Chinese handwritten character database 99.1% recognition accuracy on MNIST digit database [Ge 02] Set λ according to the stroke width Extract features using the magnitude of the filtering 2M sample database with a vocabulary of 4616 Chinese handwritten characters 97.5% recognition accuracy

Proposed Gabor Features Features are computed from the magnitude response of real and imaginary parts Step 1: Apply Gabor filters at 2 different frequencies and 4 different orientations Step 2: Partition the filter response into 8 x 8 grids Step 3: Count # of strong responses in each grid and concatenate them into a 512 dimensional vector: 8 x 8 (grid) x 2 (frequency) x 4 (orientation)

Experiments with Gabor Features Performed Part-of-Word (PAW) classification experiments to assess the efficacy of Gabor features Used Support Vector Machines (SVM) for classification and compared performance with GSC and Graph based features Dataset: Applied Media Analytics (AMA) Arabic database [AMA 07] Selected 34 most frequent PAW classes and run noise removal: Median filtering Slant correction Rule-line removal Training set: 6498 PAWs Testing set: 848 PAWs Sample images from the AMA databases

Features for Comparison GSC (512-dim) Gradient: gradient value and orientation for each bin, and then count pixels that have the same gradient Structure: real-valued features estimated from pixel neighborhood using a codebook of predefined shapes Concavity: coarse pixel density, large strokes, and concavity of different orientations Graph features (208-dim) Binarize and then apply stroke thinning to acquire a single-pixel wide representation of the image Traverse the skeleton to count the number of patterns, including 5 node types, 3 edge types, and 5 segment types

Experimental Results Comparison with GSC and Graph Features Feature Set % Classification Accuracy GSC 81.6 Graph 68.2 Proposed Gabor 82.7 Gabor I [Wang 05] (positive and negative real part) Gabor II (positive real part only) 76.2 79.8

Experimental Results Combination of Features Feature Set % Classification Accuracy GSC 81.6 Proposed Gabor + GSC 84.3 Gabor + Graph 82.8 Graph + GSC 79.7 Gabor I + GSC 82.7 Gabor II + GSC 82.7

Conclusions Experimental results demonstrate that Gabor features are useful for offline Arabic PAW classification Ongoing work: integrating Gabor features into the HMM and SSM framework Training set: 658K lines, 3.7M words Development set: 14K lines, 89K words Testing set: 14K lines, 89K words Recognition System %Word Error Rate HMM 26.5 SSM with Gabor 26.0 SSM with GSC 25.7 SSM with Gabor + GSC 25.7

Thank You!

Statistical Significance Test GSC+Gabor is statistically significantly better than using GSC along: GSC+Gabor (A): 715/848 GSC (B): 692/848 Null hypothesis (H0): Ra = Rb Alternative hypothesis (H1): Ra > Rb n 01 = # of samples misclassified by A but not by B n 10 = # of samples misclassified by B but not by A [Diertterich 98] Test Statistic Z 2 ~ χ 2 (1): n 01 = 25, n 10 = 48, Z = 2.57 > 1.96, the confidence level is 95%.

Reference 1. [Favata, 94 ] Handprinted character/digit recognition using a multiple feature/resolution philosophy. International Workshop on Frontiers in Handwriting Recognition, 1994. p57-p66. 2. [Verma, 04 ] A novel approach for structural feature extraction: contour vs. direction. Pattern Recognition Letters. 25(9): 975-988, 2004. 3. [Zhang, 09 ] Character-SIFT: a novel feature for offline handwritten Chinese character recognition. Proc. of ICDAR. 2009. 4. [Wang, 05 ] Gabor filter-based feature extraction for character recognition. Pattern Recognition. 38: 369-379, 2005. 5. [Ge, 02 ] Offline recognition of Chinese handwritten characters using Gabor features, CDHMM modeling and MCE training. Proc. of ICASSP, 2002. 6. [AMA, 07 ] Applied Media Analysis, Arabic-Handwritten-1.0. http://appliedmediaanalysis.com/datasets.htm. 2007. 7. [Natarajan, 09 ] Stochastic Segment Modeling for Offline Handwriting Recognition. Proc. of ICDAR. 2009. 8. [Dietterich, 98 ] Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10:1895 1923.