Towards effective codebookless model for image classification. (November 2016)

• Record Type: Journal Article
• Authors: Wang, Qilong; Li, Peihua; Zhang, Lei; Zuo, Wangmeng
• Is Part Of: Pattern recognition. Volume 59(2016:Nov.)
• Page Start: 63
• Page End: 71
• Publication Date: 2016-11
• Subjects: Codebookless model -- Image classification -- Bag-of-features -- Riemannian manifold; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.03.004
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade. Different from the widely used BoF methods which model images with a pre-trained codebook, the alternative codebook-free image modeling method, which we call codebookless model (CLM), attracts little attention. In this paper, we present an effective CLM that represents an image with a single Gaussian for classification. By embedding Gaussian manifold into a vector space, we show that the simple incorporation of our CLM into a linear classifier achieves very competitive accuracy compared with state-of-the-art BoF methods (e.g., Fisher Vector). Since our CLM lies in a high-dimensional Riemannian manifold, we further propose a joint learning method of low-rank transformation with support vector machine (SVM) classifier on the Gaussian manifold, in order to reduce computational and storage cost. To study and alleviate the side effect of background clutter on our CLM, we also present a simple yet effective partial background removal method based on saliency detection. Experiments are extensively conducted on eight widely used databases to demonstrate the effectiveness and efficiency of our CLM method. Abstract : Highlights: We show that codebookless model (CLM) is a very competitive alternative to the mainstream BoF model. Two well-motivated parameters are introduced to further improve our CLM. A joint low-rank learning and SVM is proposed on Gaussian manifold. The comprehensive experiments demonstrated the promising performance of our CLM.