Efficient Fuzzy C-Means Architecture for Image Segmentation.docVIP

Sensors 2011, 11, 6697-6718; doi:10.3390/s110706697 OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Ef?cient Fuzzy C-Means Architecture for Image Segmentation Hui-Ya Li, Wen-Jyi Hwang and Chia-Yen Chang ? Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei 116, Taiwan; E-Mails: royalfay@ (H.-Y.L.); edi?er5757@.tw (C.-Y.C.) ? Author to whom correspondence should be addressed; E-Mail: whwang@.tw; Tel.: +886-2-7734-6670; Fax: +886-2-2932-2378. Received: 2 June 2011; in revised form: 20 June 2011 / Accepted: 24 June 2011 / Published: 27 June 2011 Abstract: This paper presents a novel VLSI architecture for image segmentation. The architecture is based on the fuzzy c-means algorithm with spatial constraint for reducing the misclassi?cation rate. In the architecture, the usual iterative operations for updating the membership matrix and cluster centroid are merged into one single updating process to evade the large storage requirement. In addition, an ef?cient pipelined circuit is used for the updating process for accelerating the computational speed. Experimental results show that the the proposed circuit is an effective alternative for real-time image segmentation with low area cost and low misclassi?cation rate. Keywords: fuzzy c-means; image segmentation; fuzzy clustering; fuzzy hardware; FPGA; recon?gurable computing; system on programmable chip 1. Introduction Image segmentation plays an important role in computer vision and image analysis. The segmentation results can be used to identify regions of interest and objects in the scene, which is very bene?cial to the subsequent image analysis or annotation. The fuzzy c-means algorithm (FCM) [1] is one of the most used technique for image segmentation. The accuracy of FCM is due to the employment of fuzziness for the clustering of each image pixel. This enables the fuzzy clustering methods to retain more information from the original image