Abstract
In this paper, we propose a fast labeling algorithm based on block-based concepts. Because the number of memory access points directly affects the time consumption of the labeling algorithms, the aim of the proposed algorithm is to minimize neighborhood operations. Our algorithm utilizes a block-based view and correlates a raster scan to select the necessary pixels generated by a block-based scan mask. We analyze the advantages of a sequential raster scan for the block-based scan mask, and integrate the block-connected relationships using two different procedures with binary decision trees to reduce unnecessary memory access. This greatly simplifies the pixel locations of the block-based scan mask. Furthermore, our algorithm significantly reduces the number of leaf nodes and depth levels required in the binary decision tree. We analyze the labeling performance of the proposed algorithm alongside that of other labeling algorithms using high-resolution images and foreground images. The experimental results from synthetic and real image datasets demonstrate that the proposed algorithm is faster than other methods.
Highlights
Connected-component labeling algorithms form the basis of research in areas of computer and machine vision that involve locating objects for visual applications
In real-time applications that analyze the features of detected objects in the background subtraction algorithm, the labeling algorithm classifies the foreground pixels of each group using the connectivity of pixels neighboring the processed pixel
When the background subtraction algorithm is applied to high-resolution images, the labeling algorithm has to process more decisions regarding neighboring relationships between foreground pixels in real time
Summary
Connected-component labeling algorithms form the basis of research in areas of computer and machine vision that involve locating objects for visual applications. Grana et al [19] proposed the Block-Based Decision Table (BBDT) algorithm, in which OR-decision tables optimize past results relating to binary decision trees by selecting 16 pixels from the 20-pixel scan mask (i.e., excluding pixels a, f, l, and q) This block-based scan mask extends the area under consideration for foreground pixels by reducing neighbor operations. The leaf nodes of the binary decision trees enable the proposed algorithm to determine the neighbor operations for each simplified block-based scan mask.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
