Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Discovering Recurrent Image Semantics from Class Discrimination | Hindawi Publishing Corporation EURASIP Journal on Applied Signal Processing Volume 2006 Article iD 76093 Pages 1-11 DOI ASP 2006 76093 Discovering Recurrent Image Semantics from Class Discrimination Joo-Hwee Lim1 and Jesse S. Jin2 1 Institute for Infocomm Research 21 Heng Mui Keng Terrace Singapore 119613 2 School of Design Communication and Information Technology Faculty of Science and Information Technology University of Newcastle Callaghan NSW 2308 Australia Received 17 August 2004 Revised 1 March 2005 Accepted 5 April 2005 Supervised statistical learning has become a critical means to design and learn visual concepts . faces foliage buildings etc. in content-based indexing systems. The drawback of this approach is the need of manual labeling of regions. While several automatic image annotation methods proposed recently are very promising they usually rely on the availability and analysis of associated text descriptions. In this paper we propose a hybrid learning framework to discover local semantic regions and generate their samples for training of local detectors with minimal human intervention. A multiscale segmentation-free framework is proposed to embed the soft presence of discovered semantic regions and local class patterns in an image independently for indexing and matching. Based on 2400 heterogeneous consumer images with 16 semantic queries both similarity matching based on individual index and integrated similarity matching have outperformed a feature fusion approach by 26 and 37 in average precisions respectively. Copyright 2006 Hindawi Publishing Corporation. All rights reserved. 1. INTRODUCTION Using supervised pattern classifiers to learn image semantics and ensemble of pattern classifiers to enhance system performance have become an active trend in content-based analysis research 1-4 . One of the most notable efforts by the IBM Research Group 4 5 deployed numerous SVM classifiers in multistage optimization for the learning and .
