Online Training for Face Recognition System Using Improved PCA

<p>The main problem in face recognition system based on half-face pattern is how to anticipate poses and illuminance variations to improve recognition rate. To solve this problem, we can use two lenses on stereo vision camera in face recognition system. Stereo vision camera has left and right lenses that can be used to produce a 2D image of each lens. Stereo vision camera in face recognition has capability to produce two of 2D face images with a different angle. Both angle of the face image will produce a detailed image of the face and better lighting levels on each of the left and right lenses. In this study, we proposed a face recognition technique, using 2 lens on a stereo vision camera namely symmetrical half-join. Symmetrical half-join is a method of normalizing the image of the face detection on each of the left and right lenses in stereo vision camera, then cropping and merging at each image. Tests on face recognition rate based on the variety of poses and variations in illumination shows that the symmetrical half-join method is able to provide a high accuracy of face recognition and can anticipate variations in given pose and illumination variations. The proposed model is able to produce 86% -97% recognition rate on a variety of poses and variations in angles between 0 °- 22.5 °. The variation of illuminance measured using a lux meter can result in 90% -100% recognition rate for the category of at least dim lighting levels (above 10 lux).</p>

Download Full-text

Face Recognition Based on Symmetrical Half-Join Method using Stereo Vision Camera

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v6i6.pp2818-2827 ◽

2016 ◽

Vol 6 (6) ◽

pp. 2818

Author(s):

Edy Winarno ◽

Agus Harjoko ◽

Aniati Murni Arymurthy ◽

Edi Winarko

Keyword(s):

Face Recognition ◽

Stereo Vision ◽

Recognition Rate ◽

Recognition System ◽

Face Images ◽

Face Recognition System ◽

Proposed Model ◽

The Face ◽

Left And Right ◽

Recognition Technique

<p>The main problem in face recognition system based on half-face pattern is how to anticipate poses and illuminance variations to improve recognition rate. To solve this problem, we can use two lenses on stereo vision camera in face recognition system. Stereo vision camera has left and right lenses that can be used to produce a 2D image of each lens. Stereo vision camera in face recognition has capability to produce two of 2D face images with a different angle. Both angle of the face image will produce a detailed image of the face and better lighting levels on each of the left and right lenses. In this study, we proposed a face recognition technique, using 2 lens on a stereo vision camera namely symmetrical half-join. Symmetrical half-join is a method of normalizing the image of the face detection on each of the left and right lenses in stereo vision camera, then cropping and merging at each image. Tests on face recognition rate based on the variety of poses and variations in illumination shows that the symmetrical half-join method is able to provide a high accuracy of face recognition and can anticipate variations in given pose and illumination variations. The proposed model is able to produce 86% -97% recognition rate on a variety of poses and variations in angles between 0 °- 22.5 °. The variation of illuminance measured using a lux meter can result in 90% -100% recognition rate for the category of at least dim lighting levels (above 10 lux).</p>

Download Full-text

Face Liveness Detection using Feature Fusion Using Block Truncation Code Technique

International Journal on Recent and Innovation Trends in Computing and Communication ◽

10.17762/ijritcc.v7i8.5348 ◽

2019 ◽

Vol 7 (8) ◽

pp. 19-22

Author(s):

Prasad A. Jagdale ◽

Sudeep D. Thepade

Keyword(s):

Face Recognition ◽

Feature Fusion ◽

Recognition System ◽

Security System ◽

Major Drawback ◽

Liveness Detection ◽

Face Images ◽

Face Recognition System ◽

Confidential Data ◽

Finger Recognition

Nowadays the system which holds private and confidential data are being protected using biometric password such as finger recognition, voice recognition, eyries and face recognition. Face recognition match the current user face with faces present in the database of that security system and it has one major drawback that it never works better if it doesn’t have liveness detection. These face recognition system can be spoofed using various traits. Spoofing is accessing a system software or data by harming the biometric recognition security system. These biometric systems can be easily attacked by spoofs like peoples face images, masks and videos which are easily available from social media. The proposed work mainly focused on detecting the spoofing attack by training the system. Spoofing methods like photo, mask or video image can be easily identified by this method. This paper proposed a fusion technique where different features of an image are combining together so that it can give best accuracy in terms of distinguish between spoof and live face. Also a comparative study is done of machine learning classifiers to find out which classifiers gives best accuracy.

Download Full-text