Bayesian Edge Detector Using Deformable Directivity-Aware Sampling Window

• Main Authors: Ren-Jie Huang, Jung-Hua Wang, Chun-Shun Tseng, Zhe-Wei Tu, Kai-Chun Chiang
• Format: Article
• Language: English
• Published: MDPI AG 2020-09-01
• Series: Entropy
• Subjects: Bayesian; edge detector; entropy; gestalt theory; EM algorithm
• Online Access: https://www.mdpi.com/1099-4300/22/10/1080

Conventional image entropy merely involves the overall pixel intensity statistics which cannot respond to intensity patterns over spatial domain. However, spatial distribution of pixel intensity is definitely crucial to any biological or computer vision system, and that is why gestalt grouping rules involve using features of both aspects. Recently, the increasing integration of knowledge from gestalt research into visualization-related techniques has fundamentally altered both fields, offering not only new research questions, but also new ways of solving existing issues. This paper presents a Bayesian edge detector called <i>GestEdge</i>, which is effective in detecting gestalt edges, especially useful for forming object boundaries as perceived by human eyes. <i>GestEdge</i> is characterized by employing a directivity-aware sampling window or mask that iteratively deforms to <i>probe</i> or <i>explore</i> the existence of principal direction of sampling pixels; when convergence is reached, the window covers pixels best representing the directivity in compliance with the similarity and proximity laws in gestalt theory. During the iterative process based on the unsupervised Expectation-Minimization (EM) algorithm, the shape of the sampling window is optimally adjusted. Such a deformable window allows us to exploit the similarity and proximity among the sampled pixels. Comparisons between <i>GestEdge</i> and other edge detectors are shown to justify the effectiveness of <i>GestEdge</i> in extracting the gestalt edges.