Joint Dictionary Learning via Split Bregman Iteration for Large-Scale Image Classification

This paper aims at the hierarchical learning for large-scale image classification. Due to flexibility and capability, sparse representation is widely used in object recognition. The hierarchy is introduced to joint dictionary learning for large scale image classification. Because the joint dictionary learning model is non-quadratic, Split Bregman Iteration is used to solve the shared dictionary and the class-specified dictionary. Moreover, the deep feature generated by Inception-v3 is used for image representation. When a query image is input, two label prediction schemes are investigated: SVM and residual. The proposed approach is implemented on three benchmark datasets: ILSVRC2010, Oxford Flower image set and Caltech 256 and the experimental results demonstrate that our approach is better than the original joint dictionary learning method and achieves excellent accuracy compared with other handcrafted features.