Structured Image Segmentation

Extracting Image Regions by Structured Edge Prediction

Yi-Ting Chen Jimei Yang Ming-Hsuan Yang

UC Merced

Abstract

We present two approaches to extract regions from structured edge detection. While the state-of-the-art algorithm based on globalized probability of boundary (gPb) generates a hierarchical region tree, it entails significant computational load. In this work, we exploit an efficient algorithm for structured edge prediction to extract regions. To generate high quality regions, we develop a novel algorithm to link the structured edge and gPb hierarchical image segmentation framework with steerable filters. The extracted regions are grouped by the proposed hierarchical grouping method to generate object proposals for effective detection and recognition problems. We demonstrate the effectiveness of our region generation for image segmentation on the BSDS500 database, and region generation for object proposals on the PASCAL VOC 2007 benchmark database. Experimental results show that the proposed algorithm achieves the comparable or superior quality to the state-of-the-art methods.

Paper and Related Material

"Extracting Image Regions by Structured Edge Prediction"

Yi-Ting Chen, Jimei Yang and Ming-Hsuan Yang

IEEE Winter Conference on Applications of Computer Vision (WACV), 2015

[paper] [poster] [Code on Github]

Bibtex

@inproceedings{Chen-WACV-2015, author = {Yi-Ting Chen and Jimei Yang and Ming-Hsuan Yang}, title = {Extracting Image Regions by Structured Edge Prediction}, booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)}, year = {2015} }