Discriminative k metrics and the Chan-Vese model for object detection and segmentation
Arthur D. Szlam, Guillermo Sapiro · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
In this work, a modification of the k q-flats framework for pattern classification introduced in [9] is used for pixelwise object detection. We include a preliminary discussion of augmenting this method is with a Chan-Vese-like geometric regularization.