100 lines of code for shape-based object localization. (December 2016)

• Record Type: Journal Article
• Authors: Halawani, Alaa; Li, Haibo
• Is Part Of: Pattern recognition. Volume 60(2016:Dec.)
• Page Start: 458
• Page End: 472
• Publication Date: 2016-12
• Subjects: Object detection -- Boundary localization -- Deformable templates -- Dynamic programming -- Contour segments -- One-pixel segment (OPS); Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.06.003
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: We introduce a simple and effective concept for localizing objects in densely cluttered edge images based on shape information. The shape information is characterized by a binary template of the object's contour, provided to search for object instances in the image. We adopt a segment-based search strategy, in which the template is divided into a set of segments. In this work, we propose our own segment representation that we call one-pixel segment (OPS), in which each pixel in the template is treated as a separate segment. This is done to achieve high flexibility that is required to account for intra-class variations. OPS representation can also handle scale changes effectively. A dynamic programming algorithm uses the OPS representation to realize the search process, enabling a detailed localization of the object boundaries in the image. The concept's simplicity is reflected in the ease of implementation, as the paper's title suggests. The algorithm works directly with very noisy edge images extracted using the Canny edge detector, without the need for any preprocessing or learning steps. We present our experiments and show that our results outperform those of very powerful, state-of-the-art algorithms. Abstract : Highlights: New segment-based representation that we call OPS. Used to achieve high flexibility that is required to account for intra-class variations. OPS representation is fed to a dynamic programming algorithm for robust detection. Very competitive localization results under extensive noise and clutter. The ability to accurately localize detailed object boundaries.