Face Recognition Using Cca on Nonlinear Features
نویسندگان
چکیده
The face recognition (FR) system plays a vital role in commercial & law enforcement applications. Image resolution is an important factor affecting face recognition performance. The performance of face recognition system degrades by low resolution of face images. To address this problem, a super resolution (SR) method was introduced by Hua Huang and Huiting He [7], which uses Canonical correlation analysis (CCA) [8], [9] to establish the super resolution subspaces between the principal component analysis (PCA) based features of HR & LR face images. However finding nonlinear relations among features can increase the descriptive power of the data and may result in increase of recognition rate. In this paper a kernel-PCA (KPCA) is applied to extract base features over which CCA is used to obtain super resolution features. The implementation of SR Method using KPCA is compared with the PCA approach of the above referred super resolution method for LR face images, and found an increase of 1.25% (96.87%-95.62%) for ORL Database and 1.5% (94.50%-93.00%) for UMIST Database in recognition.
منابع مشابه
Super-resolution for Face Recognition Based on Correlated Features and Nonlinear Mappings
For the problem of low recognition rate on low resolution face images, a super-resolution method for face recognition based on correlated features and nonlinear mappings is proposed in this paper. Canonical correlation analysis (CCA) is applied to establish the correlated subspaces between the features of high and low resolution face images, and radial base functions (RBFs) are employed to cons...
متن کاملFace Recognition by Cognitive Discriminant Features
Face recognition is still an active pattern analysis topic. Faces have already been treated as objects or textures, but human face recognition system takes a different approach in face recognition. People refer to faces by their most discriminant features. People usually describe faces in sentences like ``She's snub-nosed'' or ``he's got long nose'' or ``he's got round eyes'' and so like. These...
متن کاملIR and visible-light face recognition using canonical correlation analysis
This paper proposes a novel multispectral feature extraction method according to the idea of canonical correlation analysis (CCA). Instead of extracting two groups of features with the same pattern (modality) as usual, the work explores another type of application of CCA that for extracting most correlated features from different face modalities to form effective discriminant vectors for recogn...
متن کاملUsing articulatory measurements to learn better acoustic features
We summarize recent work on learning improved acoustic features, using articulatory measurements that are available for training but not at test time. The goal is to improve recognition using articulatory information, but without explicitly solving the difficult acoustics-to-articulation inversion problem. We formulate the problem as learning a (linear or nonlinear) transformation of standard a...
متن کاملHolistic and Gabor-local Feature-fusion for Face Recognition using Canonical Correlation Analysis (CCA)
Abstrak – In this paper, we propose a feature fusion method based on Canonical Correlation Analysis (CCA) for combining two feature extractors to increase robustness of face recognition against pose and illumination changes. At first holistic features, eigenfaces (PCA) and Gabor phase congruency image (GPCI) features are extracted from facial images respectively and then CCA finds the transform...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013