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 |