Image segmentation, human visual system, Markov random fields, just-noticeable difference
This paper presents a novel image segmentation algorithm driven by human visual system (HVS) properties. Quality metrics for evaluating the segmentation result, from both region-based and boundary-based perspectives, are integrated into an objective function. The objective function encodes the HVS properties into a Markov random fields (MRF) framework, where the just-noticeable difference (JND) model is employed when calculating the difference between the image contents. Experiments are carried out to compare the performances of three variations of the presented algorithm and several representative segmentation algorithms available in the literature. Results are very encouraging and show that the presented algorithms outperform the state-of-the-art image segmentation algorithms.
Peng, Renbin and Varshney, Pramod, "A Human Visual System-Driven Image Segmentation Algorithm" (2011). Electrical Engineering and Computer Science - Technical Reports. 21.