The modern information age confronts humanity with various challenges that did not exist to the same extent in earlier times. Two such challenges are the organization of society and its security.
The ever increasing human population and its mobility in all its facets caused an increasing demand for enhanced ways of transferring data and sharing information, which in turn, through complex communication structures, gained its own mobility. Identification and authentication method is importance of security and organization beyond of increased in environment and been developed into the technology in various area. The technology had been developed for this method such as entrance in building, day to day affairs like withdrawing money from bank account or dealing with the post office or criminal investigation. This few example can illustrate that been developed by identity and authentication method on doing in modern society.
Still, most of these methods, with all application on biometric term had been separate or expand to society. Biometric identity authentication systems are based on characteristic of the person, such as face, voice, fingerprint, iris, gait, hand geometry or signature. Base in human and voice recognition, these method require the user to remember a password or generally require a human action in the course of biometric identity authentication system.
With well controlled pose and illumination, the modern of face recognition had reached an identification rate of greater than 90% for lagers database but in this rate, it no comparable to method using keys or password nor can direct comparison abilities of human concierge. But in this biometric, could be successfully employed from supported other technique or even replaces them of lower security requirements.
The new authentication task always keeps appearing by more classical face recognition application in the modern information age. The research always observe or created some software that the computer can be employed in intelligent PCs, for instance to automatically brig up a user's individual desktop environment.
The developer had going further whereby the human can interact with the machine. The developer still research and believe that they can make intelligent man machine interface and intelligent interaction with the robot. Automatic recognition is a vast and modern research area of computer vision, reaching from recognition of faces, facial expressions and gestures over related topics such as automatically detecting, locating and tracking faces, as well as extraction of face orientation and facial features, to such supporting fields as the handling of uncontrolled and uncontrollable conditions like illumination and shadows, and the 3D reconstruction of faces in particular, or the generation of new views from given imagery in general.
The main problem of face recognition is large variability of the recorded images due to pose, illumination conditions, facial expressions, use of cosmetics, different hairstyle, presence of glasses, and beard. It also involves of complex task in detection and location of faces in a cluttered background followed by normalization and recognition. The human face is a very challenging pattern to detect and recognize, because all faces have the same structure, at the same time there are a lot of environmental and personal factors affecting facial appearance.
Intrapersonal variability factor can make more variability due, if the images of the same individual taken at different times. But there are different with extrapersonal variability that the images of different individual due to gender, race, age and individual variations. One way of coping with intrapersonal variations is including in the training set images with such variations. Using of cosmetics and presence of glasses or beard, and this facial expression may not be successful in case of illumination or pose variations. The aging on human face had big problem in face recognition because different of facial expression. In forensic, there were using mug-shot matching forensic applications to recognition the face individual even after some years but robust recognition system cannot match the face perfectly. This is a very challenging task, which has not been successfully addressed yet.
Recent public facial recognition benchmarks have shown that in general, the identification performance decreases linearly in the logarithm of number of people in the gallery database. Also, in a demographic point of view, it was found that the recognition rates for males were higher than for females, and that the recognition rates for older people were higher than for younger people. These tests also revealed that while the best recognition techniques were successful on large face databases recorded in well-controlled environments, their performance was seriously deteriorated in uncontrolled environments, mainly due to variations in illumination and head rotations. Such variations have proven to be one of the biggest problems of face recognition systems.
The problem of coping with illumination variations is increasingly appreciated by the scientific community and several techniques have been proposed that may be roughly classified into two main categories. The first category contains techniques seeking illumination insensitive representations of face images. Several representations were seen to be relatively insensitive to illumination variability, likely the direction of the image gradient or the sum of gradient of ratios between probe and gallery images.
The second approach relies on the development of generative appearance models, able to reconstruct novel gallery images resembling the illumination in the probe images. Some of these techniques utilize a large number of example images of the same person under different illumination conditions to reconstruct novel images. Other approaches utilize a 3D range image and albedo map of the person's face to render novel images under arbitrary illumination, while others are based on a combination of the above. Finally, a third more recent approach is based on computer graphics techniques for relighting the probe image so that it resembles the illumination in gallery images.
Based on the previous study, there are lots of researches that have been applied in areas of face recognition. From some previous development there are three types of recognition algorithms, likes frontal, profile and view tolerant recognition. On this type of recognition algorithms depending on both kind of imagery are available and it also on the according the recognition algorithms too. The frontal recognition usually applies classical approaches to tackle the problem at hand. View tolerant algorithms usually more sophisticated fashion which includes physics, geometry and statistics. However, there are still available for other researcher to study further more on this research domain. The further research can be focused on to minimize the noise of the sample image that will be used. In this research, the image will be used for classification because the image will be use will provides the important characteristics for object identification. The performance of the SVM classifier for the classification of extracted features will be studied.
The aim of this study is
- To highlight the lack of standard performance evaluation measures for face detection purposes.
- To propose a method for the evaluation and comparison of existing face detection algorithms in an unbiased manner.
- To apply the proposed method on an existing face detection algorithm.
Objectives of the Project
The objective of this study is:
To apply the proposed technique on existing face detection algorithm
- To compare of existing face detection algorithm between support vector machines (SVM) and eigenspaces
- To demonstrate the characteristic of the proposed detailed collection of experiment
- To study how the recognition performance is affected by variation of model parameters
- To developed some prototype using face recognition
The scope of this study is:
- Recognize all part in the face
- This research is focus on the face image size 112x92 pixel resolution that are taken from AT&T "The Database of Faces"( formerly "The ORL Database of Faces").
- Matlab 7.0 software will be used in this study.
- Ten different images of each of 40 distinct subjects will be use in this study.
Significance Of The Study
This study evaluates the performance of face detection algorithm that will be used to provide with algorithm to obtain an impartial and empirical evaluation and comparison of any two method. It is important to consider using of a standard and representative test set for evaluation or standard terminology for representation of result. In addition, the aims of this research are to study the classification technique using SVM classifier to evaluate the performance.
Organization of the report
This report consists of five chapters. The first chapter presents introduction to the project and the background of problem on why is the study is being conducted. It also gives the objectives and scope of the study as well as the significance of the project. Chapter 2 presents the literature review of the research are related with face detection, feature extraction technique and also SVM classifier. Chapter 3 discuss about the methodology and the framework that will be used in this study. Chapter 4 presents the initial result of the research that is discussed. The last chapter is the achievement and the future work what will be implemented later.