標題: INCORPORATING TEXTURE INFORMATION INTO REGION-BASED UNSUPERVISED IMAGE SEGMENTATION USING TEXTURAL SUPERPIXELS
作者: Hsu, Chih-Yu
Hsieh, Yi-Yu
Lo, Kuo-Hua
Chuang, Jen-Hui
資訊工程學系
Department of Computer Science
關鍵字: Unsupervised image segmentation;Superpixel;Texture
公開日期: 2014
摘要: Recently, an unsupervised image segmentation framework, Segmentation by Aggregating Superpixels (SAS) is proposed and shown to be very promising. However, the texture cues, which have been shown to be very effective in many researches, are not used. In this paper, we propose an effective method for incorporating texture information into the SAS framework, using superpixels. To extract texture information, our algorithm first uses texture filtering and subsequently GMM clustering. Then, we develop an edge-aware low-pass filtering to generate multiple-scale textural superpixels (TXSPs) from the clustering results. Finally, by joining TXSPs with the superpixel set originally used in SAS, the incorporation of texture information is accomplished. Our method achieves superior performance on the Berkeley Segmentation Dataset (BSDS300) under several evaluation criteria when compared to other benchmark algorithms.
URI: http://hdl.handle.net/11536/134979
ISBN: 978-1-4799-5751-4
ISSN: 1522-4880
期刊: 2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
起始頁: 4323
結束頁: 4327
顯示於類別:會議論文