Improved accuracy of superpixel segmentation by region merging method

详细信息    查看全文

• 作者：Song Zhu ; Danhua Cao ; Yubin Wu ; Shixiong Jiang
• 关键词：image processing ; image segmentation ; superpixels ; region merging
• 刊名：Frontiers of Optoelectronics
• 出版年：2016
• 出版时间：December 2016
• 年：2016
• 卷：9
• 期：4
• 页码：633-639
• 全文大小：
• 刊物类别：Engineering
• 刊物主题：Electrical Engineering; Physics, general; Biomedical Engineering;
• 出版者：Higher Education Press
• ISSN：2095-2767
• 卷排序：9

文摘

Superpixel as an important pre-processing technique has been successfully used in many vision applications. In this paper, we proposed a region merging method to improve superpixel segmentation accuracy with low computational cost. We first segmented the image into many accurate small regions, and then progressively agglomerated them until the desired region number was reached. The region merging weight was derived from a novel energy function, which encourages the superpixel with color consistency and similar size. Experimental results on the Berkeley BSDS500 data set showed that our region merging method can significantly improve the accuracy of superpixel segmentation. Moreover, the region merging method only need 50 ms to process a 481 × 321 image on a single Intel i3 CPU at 2.5 GHz.