Title: Research on the image segmentation of icing line based on NSCT and 2-D OSTU
Authors: Lin Qi; Jing Wang; Can Dong Li; Wei Liu
Addresses: School of Information Science and Engineering, Hebei University of Science and Technology, 26 Yuxiang Road, Yuhua District, Hebei, Shijiazhuang, 050018, China ' Department of Computer Science, Tangshan Normal University, 156 Construction of North Road, High-tech Development District, Hebei, Tangshan, 063000 China ' School of Information Science and Engineering, Hebei University of Science and Technology, 26 Yuxiang Road, Yuhua District, Hebei, Shijiazhuang,050018, China ' Department of Mathematics, Hebei Vocational College of Chemical and Pharmaceutical Technology, 88 Fangxing Road, Yuhua District, Hebei, Shijiazhuang 050026, China
Abstract: In allusion to increased noise and blurring of icing line images, this paper has proposed a segmentation method based on NSCT and 2-D Otsu, using NSCT to implement de-noising processing of image, and introducing combined threshold methods of improved genetic algorithm and 2-D Otsu algorithm for image segmentation, and has described the specific algorithm. The results show that this method can effectively realise the de-noising processing of icing images, making accurate extraction of the target, which has reduced the search time, convenient for real time applications.
Keywords: NSCT; 2-D Otsu; image segmentation; icing line; improved genetic algorithm.
DOI: 10.1504/IJCAT.2018.091642
International Journal of Computer Applications in Technology, 2018 Vol.57 No.2, pp.112 - 120
Received: 28 Feb 2017
Accepted: 28 Feb 2017
Published online: 10 May 2018 *