Conference Paper

Sparsely Encoded Local Descriptor for face recognition

Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci. (CAS), Beijing, China
DOI: 10.1109/FG.2011.5771389 Conference: Automatic Face & Gesture Recognition and Workshops (FG 2011), 2011 IEEE International Conference on
Source: IEEE Xplore


In this paper, a novel Sparsely Encoded Local Descriptor (SELD) is proposed for face recognition. Compared with K-means or Random-projection tree based previous methods, sparsity constraint is introduced in our dictionary learning and sequent image encoding, which implies more stable and discriminative face representation. Sparse coding also leads to an image descriptor of summation of sparse coefficient vectors, which is quite different from existing code-words appearance frequency(/histogram)-based descriptors. Extensive experiments on both FERET and challenging LFW database show the effectiveness of the proposed SELD method. Especially on the LFW dataset, recognition accuracy comparable to the best known results is achieved.

Download full-text


Available from: Zhen Cui, Aug 27, 2014
  • Source
    • "Answer: We thank the reviewer's comment. We have made a more comprehensive discussion of previous work [2] and [4] to address the difference and the novelty of our method in Section II. To be more specific, we have replaced Section II with the following text: A recent work \cite{guoWCD12} measures similarity and dissimilarity scores of sparse codes from an image pair based on a reference set of images to build an augmented dictionary. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this letter, a local sparse representation is proposed for face components to describe the local structure and characteristics of the face image for face verification. We first learn a dictionary from collected local patches of face images. Then, a novel local descriptor is presented by using sparse coefficients obtained by the learned dictionary and local face patches from face components to represent the entire human face. We demonstrate the performance of the proposed local sparse representation method on several publicly available datasets. Extensive experiments on both CMU PIE dataset and the challenging LFW database have shown the effectiveness of the proposed method.
    Full-text · Article · Feb 2013 · IEEE Signal Processing Letters
  • [Show abstract] [Hide abstract]
    ABSTRACT: Conventional representation methods try to express the test sample as a weighting sum of training samples and exploit the deviation between the test sample and the weighting sum of the training samples from each class (also referred to as deviation between the test sample and each class) to classify the test sample. In particular, the methods assign the test sample to the class that has the smallest deviation among all the classes. This paper analyzes the relationship between face images under different poses and, for the first time, devises a bidirectional representation method-based pattern classification (BRBPC) method for face recognition across pose. BRBPC includes the following three steps: the first step uses the procedure of conventional representation methods to express the test sample and calculates the deviation between the test sample and each class. The second step first expresses the training sample of a class as a weighting sum of the test sample and the training samples from all the other classes and then obtains the corresponding deviation (referred to as complementary deviation). The third step uses the score-level fusion to integrate the scores, that is, deviations generated from the first and second steps for final classification. The experimental results show that BRBPC classifies more accurately than conventional representation methods.
    No preview · Article · Oct 2012 · Neural Computing and Applications
  • [Show abstract] [Hide abstract]
    ABSTRACT: Tracking by individual features, such as color or motion, is the main reason why most tracking algorithms are not as robust as expected. In order to better describe the object, multi-feature fusion is very necessary. In this paper we introduce a graph grammar based method to fuse the low level features and apply them to object tracking. Our tracking algorithm consists of two phases: key point tracking and tracking by graph grammar rules. The key points are computed using salient level set components. All key points, as well as the colors and the tangent directions, are fed to a Kalman filter for object tracking. Then the graph grammar rules are used to dynamically examine and adjust the tracking procedure to make it robust.
    No preview · Conference Paper · Jan 2012
Show more