Open AccessCorrelation of Surface Binary Segmentation and Object Contour Sizing Threshold in Clustering Image Processing
Author(s) -
Mannan Hassan,
Weiliang Kong,
RA Rahim,
Nur Farhan Kahar,
M. N. Junita
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1755/1/012044
Subject(s) - contouring , artificial intelligence , binary image , segmentation , computer vision , sizing , image segmentation , computer science , cluster analysis , object (grammar) , image processing , binary number , pattern recognition (psychology) , segmentation based object categorization , focus (optics) , scale space segmentation , image (mathematics) , mathematics , computer graphics (images) , optics , art , visual arts , physics , arithmetic
Image segmentation and contouring plays a significant role in computer vision. It aims at extracting meaningful objects contained in an image. Obtaining an appropriate threshold value yield a higher accuracy in identifying the specified object of interest. A min-max threshold value was examined for surface binary segmentation and object contour sizing. The binary segmentation threshold (T) suggested to be in the range of 155 to 250 in order to get an appropriate result and the acceptable range for frame divider is between 150 to 250. These results can assist researchers to focus on the applicable threshold value in image processing especially for video analysis.