Fast genre classification of web images using global and local features. Issue 3 (6th September 2018)

• Record Type: Journal Article
• Authors: Liu, Guo‐Shuai; Wang, Rui‐Qi; Yin, Fei; Ogier, Jean‐Marc; Liu, Cheng‐Lin
• Is Part Of: CAAI transactions on intelligence technology. Volume 3:Issue 3(2018)
• Page Start: 161
• Page End: 168
• Publication Date: 2018-09-06
• Subjects: support vector machines -- image texture -- feature extraction -- image classification -- image colour analysis -- cameras; support vector machine classifier -- first‐stage classifier -- SVM classifier -- second‐stage classifier -- camera‐captured paper documents -- global feature extraction -- local texture feature extraction -- natural scene imaging -- fast genre web image classification -- born‐digital imaging -- nontext image discriminations -- text image discriminations -- image colour analysis -- image fusion -- bag‐of‐words framework -- Intel(R) Xeon(R) central processing unit -- frequency 2.9 GHz; (B6135E) Image recognition -- (B7230G) Image sensors -- (C5260B) Computer vision and image processing techniques -- (C6170K) Knowledge engineering techniques; Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/trit.2018.1018
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract : To effectively mine the contents embedded in web images, it is useful to classify the images into different types so that they can be fed to different procedures for detailed analysis. The authors herein propose a hierarchical algorithm for efficiently classifying web images into four classes. Their algorithm consists of two stages: the first stage extracts global features reflecting the distributions of color, edge and gradient, and uses a support vector machine (SVM) classifier for preliminary classification. Images assigned low confidence by the first stage classifier are processed by the second stage, which further extracts local texture features represented in the bag‐of‐words framework and uses another SVM classifier for final classification. In addition, they design two fusion strategies to train the second‐stage classifier and generate the final prediction depending on the usage of local features in the second stage. To validate the effectiveness of proposed method, they built a database containing more than 55, 000 images from various sources. On their test image set, they obtained an overall classification accuracy of 98.4% and the processing speed is over 27 fps on an Intel(R) Xeon(R) central processing unit (2.90 GHz).