An improved levelset method using saliency map as initial seed

摘要

Image segmentation is a challenging task in computer vision and image understanding, which partitions an input image in to several segments. Segmentation techniques try to detect objects from the background by exploiting image features such as texture, intensity, color etc. This paper introduces an enhanced Level set based method for segmentation using the saliency map as the initialization. A high quality saliency map is generated by combining the maps from HDCT and MB algorithms, the resultant saliency map is then given to the Level set module for segmentation. The effectiveness of the saliency based level set method against normal level set segmentation is evaluated and confirmed on MSRA dataset based on standard performance measures such as Miss Classification Error, FPR, FNR, TPR, accuracy and precision.