A modified fast fuzzy C-means algorithm based on the spatial information for underwater image segmentation

A novel fuzzy C-means algorithm based on spatial neighbor information is proposed. With the Euclidean distance and the weighted spatial distance, a novel objective function has been established which contains neighbor information. Experimental results indicate that this algorithm can get the high qualified segmentation, but spends much time. As the mission of the vision system of autonomous underwater vehicle (AUV), it should deal with the information about the object in the complex environment rapidly and exactly for AUV to use the obtained result for the next task. So, aiming at realizing a clustering quickly on the basis of high qualified segmentation, the algorithm mentioned above is modified using the relative information loss of the re-sampled image to the original image. Experimental results show that the novel algorithm can get a better segmentation result and the processing time of each image is reduced and can enhance efficiency and satisfy the request of highly real-time effectiveness of AUV.