Underwater image edge detection based on K-means algorithm
Yuejiao He, Bing Zheng, Yuzhen Ding, Hua Juan Yang · 2014
Edge detection is widely used in image analysis and processing. The traditional edge-detection algorithms are always ineffective to underwater images due to the absorption and scattering nature of seawater. In this paper a new approach is used to obtain the accurate edges of underwater pipeline. Firstly, we use the dark channel prior method to get the clear original image. Then, we calculate the processed image's gradient, and then the endpoints in the original edge image are detected. Next, the modification K-means clustering algorithm is used to classify the endpoints. Finally, the multiple windows using adaptive gradient magnitude are merged to get the final edge map. The edge detection result is significantly improved.