2016 3rd International Conference on Information Science and Control Engineering (ICISCE 2016)

71 / 2016-03-18 13:54:48

Underwater Image Segmentation Methods Based on MCA and Adaptive Level Set Evolution

5286,9589,9590,9591

Noise and uneven gray levels in underwater image cause the low segment precision, this paper presents a segmentation method based on morphological component analysis (MCA) and adaptive level set evolution. MCA method is used to sparse decompose the image into texture and cartoon parts. The cartoon part contains the mainly information with less noise, which is good for segmentation. In order to obtain the image’s weaken edges, we combine the threshold piecewise function with the adaptive level set evolution’s variable right coefficient and halting speed function, and use the new method to segment the image’s cartoon part as the final result. At last, we use this paper method compare with the other adaptive level set evolution method to segment the different underwater images, the result can prove the paper’s method is more effective for the underwater image processing.