文献类型：会议论文

英文题名：AUTOMATIC IMAGE REGION ANNOTATION THROUGH SEGMENTATION BASED VISUAL SEMANTIC ANALYSIS AND DISCRIMINATIVE CLASSIFICATION

作者：Zhang, Jing[1];Gao, Yangwei[1];Feng, Shengwei[1];Yuan, Yubo[1];Lee, Chin-Hui[2]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai, Peoples R China;[2]Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA

会议论文集：41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

会议日期：MAR 20-25, 2016

会议地点：Shanghai, PEOPLES R CHINA

语种：英文

外文关键词：image segmentation; texture enhanced JSEG; region annotation; automatic image annotation; MFoM

摘要：We propose a new framework for automatic image annotation (AIA) of regions through segmentation based semantic analysis and discriminative classification. Given a test image, it is first segmented by a proposed texture-enhanced JSEG algorithm. Then these regions are represented by an extended bag-of-words model in which a feature vector, based on a visual lexicon with its vocabulary consisting of a visual word or a co-occurrence of multiple visual words, is constructed to represent the region content. Finally a concept classifier learned by a maximal figure-of-merit algorithm is used to predict the region labels. These models are discriminatively trained from image regions with multiple associations between regions and concepts. Experiments on a subset of the Corel 5K data set illustrate that our proposed approach to region AIA achieves more accurate annotation results than some sate-of-the-art algorithms.