Abstract
Contour pixels distinguish objects from the background. Tracing and extracting contour pixels are widely used for smart/wearable image sensor devices, because these are simple and useful for detecting objects. In this paper, we present a novel contour-tracing algorithm for fast and accurate contour following. The proposed algorithm classifies the type of contour pixel, based on its local pattern. Then, it traces the next contour using the previous pixel’s type. Therefore, it can classify the type of contour pixels as a straight line, inner corner, outer corner and inner-outer corner, and it can extract pixels of a specific contour type. Moreover, it can trace contour pixels rapidly because it can determine the local minimal path using the contour case. In addition, the proposed algorithm is capable of the compressing data of contour pixels using the representative points and inner-outer corner points, and it can accurately restore the contour image from the data. To compare the performance of the proposed algorithm to that of conventional techniques, we measure their processing time and accuracy. In the experimental results, the proposed algorithm shows better performance compared to the others. Furthermore, it can provide the compressed data of contour pixels and restore them accurately, including the inner-outer corner, which cannot be restored using conventional algorithms.
Highlights
A contour is defined as a segment that is one pixel wide and one or more pixels in length, and a boundary is defined as an unbroken contour [1]
Pixel-following methods, such as the simple boundary follower (SBF) [4,5,6], modified SBF (MSBF) [3], improved SBF (ISBF) [7], Moore-neighbor tracing (MNT) [20], the radial sweep algorithm (RSA) [9] and the Theo Pavlidis algorithm (TPA) [8], have simple rules for tracing contour pixels based on a chain code
We focus on a contour-tracing algorithm that is suitable for cases involving a relatively small number of objects and that require real-time tracing, such as augmented reality (AR), mixed reality (MR) and recognition image-based code in small-scale images, e.g., a mobile computing environment
Summary
A contour is defined as a segment that is one pixel wide and one or more pixels in length, and a boundary is defined as an unbroken contour [1]. A contour tracing algorithm can be evaluated based on the following four criteria: (1) the accuracy of contour tracing; (2) processing time; (3) data size to save the traced contour information; and (4) the ability to accurately restore and enlarge the original contour using the saved data. We propose a novel contour-tracing algorithm based on pixel following that overcomes the above-mentioned problems, i.e.,: (1) it provides fast and accurate results for contour-pixel tracing; (2) contour information can be compressed to reduce the memory size; and (3) it accurately restores the compressed data to the original contour image.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
