LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE 1 S.Manikandan, 2 S.Abirami, 2 R.Indumathi, 2 R.Nandhini, 2 T.Nanthini 1 Assistant Professor, VSA group of institution, Salem. 2 BE(ECE), VSA group of institutions indhubatchvsa@gmail.com Abstract- The face is the identity of a person. The methods to exploit this physical feature have seen a great change since the advent of image processing techniques. The attendance is taken in every schools, colleges and library. Traditional approach for attendance is professor calls student name & record attendance. It takes some time to record attendance. For face identification and verification using range images, two new representations are proposed. These include the face helix/antihelix representation obtained from the detection algorithm and the local surface patch (LSP) representation computed at feature points. A local surface descriptor is characterized by a centroid, a local surface type, and a 2D histogram. This work describes the efficient algorithm that automatically marks the attendance without human intervention. This attendance is recorded by using a camera attached in front of classroom that is continuously capturing images of students, detect the faces in images and compare the detected faces with the database and mark the attendance. Keywords - Face recognition, attendance management, local surface path 1. INTRODUCTION: Biometrics deal with recognition of individuals based on their physiological or behavioral characteristics. They have done extensive studies on biometrics such as fingerprint, face, palm print, iris, and gait. Face, a viable new class of biometrics, has certain advantages over face and fingerprint, which are the two most common biometrics in both academic research and industrial applications. For example, the face is rich in features; it is a stable structure that does not change much with age and it does not change its shape with facial expressions. Furthermore, face is larger in size compared to fingerprints but smaller as compared to face and it can be easily captured from a distance without a fully cooperative subject although it can sometimes be hidden with hair, cap, turban, muffler, scarf, and faces. The face is made up of standard features like the face. These include the outer rim (helix) and ridges antihelix parallel to the helix, the lobe, the concha, and the tragus the small prominence of cartilage over the meatus. In this paper, we use the helix/antihelix for face recognition. They have developed several biometrics techniques using the 2D intensity images. The performance of these techniques is greatly affected by the pose variation and imaging conditions. However, an face can be imaged in 3D using a range sensor which provides a registered color and range image pair a range image is relatively insensitive to illuminations and
it contains surface shape information related to the anatomical structure, which makes it possible to develop a robust 3D face biometrics. However, those who have been a part of the classes when attendance registers were used know how easy it was to abuse such a method of attendance and mark bogus attendances for each other. Of course, technology had to play its role in this field just as well as it has done in other fields. The attendance monitoring system was created and it changed the way attendances were marked. The attendance monitoring system has made the lives of teachers and employers easier by making attendance marking procedure. When it comes to schools and universities, the attendance monitoring system is a great help for parents and teachers both. Parents are never uninformed of the dependability of their children in the class if the university is using an attendance monitoring system. The edges from the 2D color image are combined with the step edges from the range image to locate regions-of-interest (ROIs) which may contain an face. In the second step, to locate the face accurately, the reference 3D face shape model, which is represented by a set of discrete 3D vertices on the face helix and the antihelix parts, is adapted to individual face images by following a new global-to-local registration procedure instead of training an active shape model built from a large set of faces to the shape variation. 2. RELATED WORKS: Continuous observation improves the performance for the estimation of the attendance. We Constructed the lecture attendance system based on face recognition, and applied the system to classroom lecture. This review the related works in the field of attendance management and face recognition. Then, it introduces our system structure and plan. Finally, experiments are implemented to provide as evidence to support our plan [1]. The result shows that continuous observation improved the performance for the estimation of the attendance. The system is implemented using a non-intrusive digital camera installed on a classroom, which scans the room, detects and extracts all faces from the acquired images [2, 3]. After faces have been extracted, they are compared with an existing database of student images and upon successful recognition a student attendance list is generated and saved on a database. This addresses problems such as real time face detection on environments with multiple objects, face recognition algorithms as well as social and pedagogical issues with the applied techniques [4]. It also has several applications in areas such as content-based image retrieval, video coding, video conferencing, crowd surveillance, and intelligent human computer interfaces. However, it was not until recently that the face detection problem received considerable attention among face. The human face is a dynamic object and has a high degree of variability in its appearance, which makes face detection a difficult problem in computer vision [5, 6]. A wide variety of
techniques have been proposed, ranging from simple edge-based algorithms to composite highlevel approaches utilizing advanced pattern recognition methods [7]. The stage of face recognition is to isolate the actual face region in a digital face image. The face region is approximated by two circles, one for the face/sclera boundary and another for the face/pupil boundary [8]. The fields and face normally occlude the upper and lower parts of the face region. Canny edge detection is used to create an edge map. The boundary of the face is located by using canny edge detection technique [9, 10]. These parameters are the center coordinates x and y, the radius r, which are able to define any circle according to the equation, 3. PROPOSED SYSTEM The image acquisition step is considered to be one of the most sensitive and important for the quality of image to be processed, data extracted from raw input determines the performance of the entire system to a large extent. Careful selection of data further helps improve the performance of the system and avoiding undesirable measurements. As image of the face to be analyzed must be acquired first in digital form suitable for analysis so we are using database available in public domain. Here in this module the image is converted to some form suitable for rest of processing like conversion of gray scale to binary image. Before performing face pattern matching, the boundaries of the face should be located. In other words, we are supposed to detect the part of the image that extends from inside the limbos the border between the sclera and the face to the outside of the beginner. Input face images Analyzing face image local surface patch Extract face image to pixels Attendance monitoring system Attendance storage Fig 1. Architecture diagram
Final phase of proposed work is accept subject code or reject the subject code it depends on identification and verification modes are two main goals of every security system based on the needs of the environment. In the verification stage, the system checks if the user data that was entered is correct or not username and password but in the identification stage, the system tries to discover who the subject is without any input information. 3.1 normalization based on local surface patch: The matrix must be larger than the matrix template for the normalization to be meaningful. The values of template cannot all be the same. The resulting matrix contains the correlation coefficients, which can range in value from -1.0 to 1.0. The function should return one argument, LSP, that is the same size as the original LSP and that satisfies the positivity and normalization constraints. From the preprocessed image we extract the intensity features of each pixel. Each pixel will be computed with mean intensity value. The intensity of the each pixel will be computed using the intensity estimation function. Each pixel intensity values like red, green, blue values are extracted and mean intensity value will be computed for each pixel. Algorithm: Step1: start Step2: read face area points TpList. Step3: initialize probability set Ps. Step4: for each face available For each pixels set Tps for each face Image For each interest point Tp i from Ips Compute total matches Tpm = ΣTp i Tp t Put attendance in database End End Compute probability Pb i = size of Ipm/size of Ip i (Tps). End. Step5: select the face image with more probability. Step6: Assign the attendance. Step7: stop. 3.2 Attendance system using pixel analysis: It has considerable potential as a personal identification technique. There are two basic features in ear images, they are ridges and creases. Ridges are formed by the arrangement of the mastoid in the dermal papillary layer. They come into being during the three-to four months of the fetal
stage and are fixed in the face. In this method is used to compare the ear image resolution. This approach seemed to be an adequate method to be used in face recognition due to its simplicity, speed and learning capability. Once the training set has been built, recognitions were done near real time over this demo face library in less than one second. Much of the previous work on automated face recognition has ignored the issue of just what aspects of the face stimulus are important for face recognition. This suggests the use of an information theory approach of coding and decoding of Face images, emphasizing the significant local and global features. Such features may or may not be directly related to our intuitive notion of face features such as the eyes, nose, lips, and hair. In the language of information theory, the relevant information in a face image is extracted, encoded as efficiently as possible, and then compared with a database of models encoded similarly. 4. RESULT AND DISCUSSION We show in this section a set of experimental results to present the performance of the proposed system, the experiment was implemented using Mat lab Versions. This section presents results of experiment applied face detection based attendance system. Starting with sliding overlapping window 18 x 27, by overlap scanning the window, where different overlap parameter used 1,2 up to the half pixels, in our experiment 9 pixel is the half of the window it might be maximum overlap, then each part of the unknown test image is scanned using slide window and detected the LSP features and put attendance based in the face image. However the face recognition based attendance system is tested. The experiment results shows that our face detection system based attendance are able to detect and classify pattern features accurately under different overlap sliding scan window over the unknown face input test image. System Detect Rate False Detect Rate Lecture attendance system 41.3% 1200 / 227580 Viola Jones algorithm 72.9 % 1100 / 98459 Efficient Image Enhancement local surface patch(proposed) 89.5 % 990/ 115576 96.5 % 212 / 85230
5. CONCLUSION This paper proposes a new algorithm for face detection based attendance system, in order to obtain the attendance, positions and face images in attendance, we proposed the attendance management system based on face recognition in the mat lab. The system estimates the attendance and the position of each student by continuous observation and recording. The result of our preliminary experiment shows continuous observation improved the performance for estimation of the attendance. It can be implemented in which the orientation of the face is first determined, and then the most suitable recognition method is selected, Also the current recognition system acquires face images only from face files located on magnetic mediums. Camera and scanner support should be implemented for greater flexibility. REFERENCES [1] BIOMETRICS: Personal Identification in Network Society, A. Jain et al., eds. Kluwer Academic, 1999. [2] A. Iannarelli, Ear Identification. Paramont Publishing, 1989. [3] M. Burge and W. Burger, Ear Biometrics in Computer Vision, Proc. Int l Conf. Pattern Recognition, vol. 2, pp. 822-826, 2000. [4] D. Hurley, M. Nixon, and J. Carter, Force Field Feature Extraction for Ear Biometrics, Computer Vision and Image Understanding, vol. 98, no. 3, pp. 491-512, 2005. [5] K. Chang, K.W. Bowyer, S. Sarkar, and B. Victor, Comparison and Combination of Ear and Face Images in Appearance-Based Biometrics, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 9, pp. 1160-1165, Sept. 2003. [6] B. Bhanu and H. Chen, Human Ear Recognition in 3D, Proc. Workshop Multimodal User Authentication, pp. 91-98, 2003. [7] H. Chen and B. Bhanu, Contour Matching for 3D Ear Recognition, Proc. Seventh IEEE Workshop Application of Computer Vision, vol. 1, pp. 123-128, 2005. [8] P. Yan and K.W. Bowyer, Multi-Biometrics 2D and 3D Ear Recognition, Proc. Audio and Video-Based Biometric Person Authentication, pp. 503-512, 2005. [9] P. Yan and K.W. Bowyer, Empirical Evaluation of Advanced Ear Biometrics, Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshop Empirical Evaluation Methods in Computer Vision, 2005. [10] P. Yan and K.W. Bowyer, Ear Biometrics Using 2D and 3D Images, Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshop Advanced 3D Imaging for Safety and Security, 2005.