{"title":"A Multi-Focus Image Fusion Algorithm Based on Non-Uniform Rectangular Partition with Morphology Operation","authors":"Xiaoyu Liu, U. KinTak","doi":"10.1109/ICWAPR.2018.8521331","DOIUrl":null,"url":null,"abstract":"Due to the shooting environment or the camera, photos may be taken at different focal points and merged into a clear photo for later use by fusion technology. This paper presents an efficient multi-focus image fusion method based on Non-uniform Rectangular Partition (NURP) [1] with morphological operations [2]. Under a certain control error, the left and right focus of the images are divided into non-uniform rectangles whose dimensions are different from different focuses for the same pixel. The NURP can roughly determine the focused and unfocused separation lines of the image according to their partition grid sizes between left and right focus images. The morphological close and open operations are performed on the fusion edge separation line to delete some noise information and keep the useful information along the edge line so that it become more close to the real separation line. Finally, the final fusion pixels are determined according to the edge boundary line to form the final fused image. Experimental results show that the proposed algorithm can enhance the spatial details of the fusion image, improve its visual quality, and obtain better objective evaluation indicators.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICWAPR.2018.8521331","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Due to the shooting environment or the camera, photos may be taken at different focal points and merged into a clear photo for later use by fusion technology. This paper presents an efficient multi-focus image fusion method based on Non-uniform Rectangular Partition (NURP) [1] with morphological operations [2]. Under a certain control error, the left and right focus of the images are divided into non-uniform rectangles whose dimensions are different from different focuses for the same pixel. The NURP can roughly determine the focused and unfocused separation lines of the image according to their partition grid sizes between left and right focus images. The morphological close and open operations are performed on the fusion edge separation line to delete some noise information and keep the useful information along the edge line so that it become more close to the real separation line. Finally, the final fusion pixels are determined according to the edge boundary line to form the final fused image. Experimental results show that the proposed algorithm can enhance the spatial details of the fusion image, improve its visual quality, and obtain better objective evaluation indicators.