International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 04 Issue: 07 | July -2017
p-ISSN: 2395-0072
www.irjet.net
ROTATION INVARIANT FACE RECOGNITION USING RLBP, LPQ AND CONTOURLET TRANSFORM Karam Chand1, Dr. Deepak Saini2 1M.Tech.
Scholar, Department of Electronics and Communication Engineering, Punjabi University, Patiala Professor, Department of Electronics and Communication Engineering, Punjabi University, Patiala ------------------------------------------------------------------------***----------------------------------------------------------------------either human or computer-based face identification tasks. ABSTRACT: Rotation invariant face recognition is an 2Assistant
Beyond security tasks, face recognition is important for other applications, such as user identification for preventing voter fraud or unlocking computers, or even for digital cameras for knowing which areas should be kept in focus. Overall, although face recognition is a difficult task, it is necessary for many day-today tasks.
important area of research because of its many real-world applications, especially in creating a more robust recognition system for commercial and government technologies. Their diffusion is mainly supported by governments, forensics and law enforcement agencies with the aim of improving the public security or in general a sense of security; in fact, the biometric identification does not directly improve the security but acts as deterrent to illegal activities. In this work, we also consider illumination variable database. In this first we located face as region of interest. Only LBP and LPQ features have been used for feature extraction. There are variants of LBP features i.e. RLBP (Rotated local binary pattern) etc. which has been proved better. The existed work has been implemented on only those datasets which have face in them. After this LDA has been used to reduce feature set by taking negative loglikelihood from each Contour let-WLD, RLBP and LPQ descripted image histograms. After this KNN has been used for classification purposes. The experimental results show excellent accuracy rates in overall testing of input data.
Face recognition methods typically confronts many realworld challenges, including the pose (out-of-plane rotation); the presence or absence of structural components like beards, mustaches, glasses; and the face appearance that is directly affected by a person’s facial expression. Occlusion is also an obstacle in face recognition, as faces may be partially occluded by other objects. Imaging conditions, lighting, and resolution are also in the list of possible difficulties a face recognition system has to attenuate and if possible eliminate. Orientation (in-plane rotation) is a new and important challenge in face recognition, which occurs when the face appearance may vary for different rotations about the camera’s optical axis. Most of face recognition methods suffer if input images are rotated, and new domains and applications demand face recognition to be more robust. Everyday pictures do not always show faces in an upright position in front of the camera, and thus different applications may need to recognize people from any picture and not just a typical picture face posture. A person could lie on bed so the face is rotated with a tilt of 90°, or could be hanging from a back stretcher having the whole body upside down.
KEYWORDS: LBP,RLBP, CONTOURLET, KNN. I. INTRODUCTION Face detection [1] is one of the fundamental techniques which enable human-computer interaction in a natural way. It is a very complicated topic which involves face alignment, face modeling, face relighting, face recognition, face verification/authentication, head pose tracking, facial expression tracking/recognition, gender/age recognition and so on. Face detection is also a core research topic in humancomputer interaction areas. Only when the face is accurately detected, the computers can truly understand people’s thoughts and intentions. For human beings, they can easily detect people’s human faces without hesitation. But for computers, face detection is a very complicated process which involved many aspects.
2. LITERATURE SURVEY Gonzalez-Diaz et al. (2014) [2] proposed a probabilistic generative model that concurrently tackles the problems of image retrieval and region-of-interest (ROI) segmentation. Specifically, the proposed model takes into account several properties of the matching process between two objects in different images, namely: objects undergoing a Geometric transformation, typical spatial location of the region of interest, and visual similarity. In this manner, their approach improves the reliability of detected true matches between any pair of images. Furthermore, by taking advantage of the
As the number of areas monitored by security cameras has grown, only automated tools such as face recognition can identify which images contain faces, which is essential to cut down on the number of images which must be considered by
© 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 3280