FCE-based color image segmentation

This paper presents a fuzzy color extractor based algorithm to segment color images into meaningful regions. The algorithm proposes a strategy for selecting seeds of color extraction and uses the region growing method to stop the iteration of extraction process. This algorithm automatically determines the number of clusters that represent the segmented color regions. The algorithm is applied to segment a number of image samples to evaluate its performance in comparison with existing approaches.

[1]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Licheng Jiao,et al.  Non-local spatial spectral clustering for image segmentation , 2010, Neurocomputing.

[3]  Jianwei Zhang,et al.  Fuzzy color extractor based algorithm for segmenting an odor source in near shore ocean conditions , 2008, 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence).

[4]  Wei Li,et al.  Vision-Based Behavior Control of Autonomous Systems by Fuzzy Reasoning , 1998, Sensor Based Intelligent Robots.

[5]  Dante Mújica-Vargas,et al.  A fuzzy clustering algorithm with spatial robust estimation constraint for noisy color image segmentation , 2013, Pattern Recognit. Lett..

[6]  Yongqiang Wang,et al.  Recognizing white line markings for vision-guided vehicle navigation by fuzzy reasoning , 1997, Pattern Recognit. Lett..

[7]  Witold Pedrycz,et al.  Advances in Fuzzy Clustering and its Applications , 2007 .

[8]  Yongqiang Wang,et al.  Road recognition for navigation of an autonomous vehicle by fuzzy reasoning , 1996, Proceedings of IEEE 5th International Fuzzy Systems.