Publication: Curve slope estimation and perpendicular line detection for computing automatic footprint chippaux-smirak index
0
0
Issued Date
2021
Resource Type
Language
eng
File Type
application/pdf
Other identifier(s)
2-s2.0-85112806559
Rights Holder(s)
มหาวิทยาลัยศรีนครินทรวิโรฒ
Bibliographic Citation
ECTI-CON 2021 - 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology: Smart Electrical System and Technology, Proceedings. Vol , No. (2021), p.285-289
Suggested Citation
Choorat P., Pornpromvinit K., Pikunthong V., Tidchai V., Aksornniem S. Curve slope estimation and perpendicular line detection for computing automatic footprint chippaux-smirak index. ECTI-CON 2021 - 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology: Smart Electrical System and Technology, Proceedings. Vol , No. (2021), p.285-289. doi:10.1109/ECTI-CON51831.2021.9454822 Retrieved from: https://hdl.handle.net/20.500.14740/7793
Abstract
Approaches for automatic computing footprint Chippaux-Smirak Index by using Curve Slope Estimation and Perpendicular Line Detection methods are proposed in this paper. First, the k-mean clustering and the Circular Hough Transform approaches are applied to divide the footprint image into left and right sides and then removed the toe prints. Then, the horizontal integral intensity projection method is applied to obtain the position of the anterior and the posterior aspect of the toeless footprints. All boundary points of the footprint are located by the Morphological Gradient method. Subsequently, the slope of a curve at the point of tangency and the straight-lines which plane of the Lateral Calcaneal on the outside of the footprint image are then estimated. Finally, the length of the straight-line at the narrowest point on the foot arch, the length of the straight-line at the widest point at the metatarsals, and the footprint Chippaux-Smirak Index value were calculated by applying the Euclidean method. Footprint arch type are then classified by using the cutoff value of the Chippaux-Smirak Index. In this experiment, the average accuracy for automatic computing Chippaux-Smirak Index values in the footprint image is 90.17% and the accuracy for classification of the footprint arch type is 87.86% in comparison with the manual computation from the expert. © 2021 IEEE.