Harun, Nor Hazlyna and Mahmuddin, Massudi and Harun, Hazaruddin (2020) A Hybrid Active Contour and Artificial Bee Colony Algorithm for Segmenting Mixed-Meal Food Images (S/O: 13239). Project Report. UUM. (Submitted)

PDF - Submitted Version Restricted to Registered users only Download (13MB) | Request a copy

Abstract

Active contour (snake) segmentation is extensively used in image processing and analysis applications particularly for identifying object boundaries. This method is adopted for food image segmentation, wherein the boundaries of the foods in an image are the objects of interest. In this research, a region-based active contour, which is regarded as an energy-minimizing process, is used for the purpose of image segmentation. In addition, a modified active contour method is presented in this paper using the artificial bee colony (ABC) algorithm to optimize the weights of the external energy function in the original active contour (AC) method. A stopping method is also introduced to the active contour method, wherein the snake movement of the contour will stop after a certain number of unimproved snake movements. The food image dataset was collected manually for the purpose of this research; this dataset is composed of 102 images of different food types and food positions in each image. This modified active contour method exhibited significant results with regard to less iteration consumption and segmentation quality compared with the original one

Item Type:	Monograph (Project Report)
Additional Information:	GERAN: FRGS
Subjects:	Q Science > QA Mathematics
Divisions:	Research and Innovation Management Centre (RIMC)
Depositing User:	Mdm. Sarkina Mat Saad @ Shaari
Date Deposited:	12 Dec 2024 11:23
Last Modified:	12 Dec 2024 11:23
URI:	https://repo.uum.edu.my/id/eprint/31773

Actions (login required)

View Item