Underwater Image Segmentation Methods Based on MCA and Adaptive Level Set Evolution
Jisong Bai, Yongjie Pang, Qiang Zhang, Yinghao Zhang · 2016
Underwater image contains a lot of noise and non uniform gray levels. That characteristic causes the image has a low segmentation precision. A segmentation method based on morphological component analysis (MCA) and adaptive level set evolution is proposed in this paper to enhance the precision. 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. A new adaptive level set evolution method is presented to obtain the weaken edges of the cartoon part. The new method combines the threshold piecewise function with variable right coefficient and halting speed function, and the new function is suit for the cartoon part image segmentation. In order to prove the segmentation method which is presented in this paper is more effective than some other methods, we take several real underwater images as test objects, and the results are satisfactory.