A projection twin SVM-based active contour model for image segmentation

This paper presents an alternative criterion derived from the least squares projection twin support vector machine (LSPTSVM) for image segmentation. The proposed model treats image segmentation as pattern classification problem, and hence tries to seek the projected axis and center for the foreground and background intensities respectively. With level set representation, the discriminative function of LSTSVM is incorporated into the energy function of the active contour model (ACM), and drives the contour evolution accordingly. Experiment results demonstrate that our model holds the higher segmentation accuracy and more noise robustness, compared with the stand-alone CV and LSPTSVM models.