Sparse coding represents a signal sparsely by using an overcomplete dictionary, and obtains promising performance in practical computer vision applications, especially for signal restoration tasks such as image denoising and image inpainting. In recent years, many discriminative sparse coding algorithms have been developed for classification problems, but they cannot naturally handle visual dat...

As one of the most important state-of-the-art classification techniques, Support Vector Machine (SVM) has been widely adopted in many real-world applications, such as object detection, face recognition, text categorization, etc., due to its competitive practical performance and elegant theoretical interpretation. However, it treats all samples independently, and ignores the fact that, in many r...

Face recognition has received a great deal of attention from the scientific and industrial communities over the past several decades owing to its wide range of applications in information security and access control, law enforce, surveillance and more generally image understanding. A general partial face recognition method based on Multi-Key point Descriptors (MKD) that does not require face al...

Target detection from hyperspectral images is an important problem but encounters a critical challenge of simultaneously reducing spectral redundancy and preserving the discriminative information. Recently, the joint sparse representation and multi-task learning (JSR-MTL) approach was proposed to address the challenge. However, it does not fully explore the prior class label information of the ...

Title of dissertation: FACE RECOGNITION AND VERIFICATION IN UNCONSTRAINED ENVIRIONMENTS Huimin Guo Doctor of Philosophy, 2012 Dissertation directed by: Professor Larry S. Davis Department of Computer Science Face recognition has been a long standing problem in computer vision. General face recognition is challenging because of large appearance variability due to factors including pose, ambient ...

As an emerging biometric technology, finger vein recognition has attracted much attention in recent years. However, single-sample is a practical and longstanding challenge this field, referring to only one image per class the training set. In recognition, illumination variations under low contrast lack of information intra-class severely affect performance. Despite its high robustness against n...

We present the discriminative recurrent sparse auto-encoder model, comprising a recurrent encoder of rectified linear units, unrolled for a fixed number of iterations, and connected to two linear decoders that reconstruct the input and predict its supervised classification. Training via backpropagation-through-time initially minimizes an unsupervised sparse reconstruction error; the loss functi...

Sparse coding with dictionary learning (DL) has shown excellent classification performance. Despite the considerable number of existing works, how to obtain features on top of which dictionaries can be better learned remains an open and interesting question. Many current prevailing DL methods directly adopt well-performing crafted features. While such strategy may empirically work well, it igno...

Abstract. In context of document classification, where in a corpus of documents their label tags are readily known, an opportunity lies in utilizing label information to learn document representation spaces with better discriminative properties. To this end, in this paper application of a Variational Bayesian Supervised Nonnegative Matrix Factorization (supervised vbNMF) with label-driven spars...

Recent research has shown the effectiveness of using sparse coding(Sc) to solve many computer vision problems. Motivated by the fact that kernel trick can capture the nonlinear similarity of features, which may reduce the feature quantization error and boost the sparse coding performance, we propose Kernel Sparse Representation(KSR). KSR is essentially the sparse coding technique in a high dime...