Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification

Jinjun KUANG, Yi CHAI

Summary :

This paper presents a novel scale-rotation invariant generative model (SRIGM) and a kernel sparse representation classification (KSRC) method for scene categorization. Recently the sparse representation classification (SRC) methods have been highly successful in a number of image processing tasks. Despite its popularity, the SRC framework lucks the abilities to handle multi-class data with high inter-class similarity or high intra-class variation. The kernel random coordinate descent (KRCD) algorithm is proposed for ₁ minimization in the kernel space under the KSRC framework. It allows the proposed method to obtain satisfactory classification accuracy when inter-class similarity is high. The training samples are partitioned in multiple scales and rotated in different resolutions to create a generative model that is invariant to scale and rotation changes. This model enables the KSRC framework to overcome the high intra-class variation problem for scene categorization. The experimental results show the proposed method obtains more stable performances than other existing state-of-art scene categorization methods.

• Publication: IEICE TRANSACTIONS on Information Vol.E96-D No.3 pp.758-761
• Publication Date: 2013/03/01
• Online ISSN: 1745-1361
• DOI: 10.1587/transinf.E96.D.758
• Type of Manuscript: LETTER
• Category: Image Recognition, Computer Vision

Authors

Jinjun KUANG
Yi CHAI

Keyword

kernel sparse representation,  scale-rotation invariant generative model,  scene categorization