{"title":"一种改进的保亮度动态直方图均衡化方法","authors":"Fan Yang, Renjie Li","doi":"10.1109/AICIT55386.2022.9930196","DOIUrl":null,"url":null,"abstract":"Histogram equalization is an effective image enhancement method for improving image contrast, and several equalization methods have been developed. Brightness-preserving dynamic histogram equalization (BPDHE) is a sub-histogram-based equalization method, and there is scope for optimising the performance of BPDHE in the segmentation process of some image histograms and in maintaining image structure and information entropy. Therefore, this paper presents a method to improve BPDHE. First, the image is subjected to bilinear interpolation. Then, the probability density function of the grey level of the image is divided into two parts according to its mean value. Finally, different methods are used to find local maximums for each of these two parts. In this paper, Absolute Mean Brightness Error (AMBE), Structure Similarity Index Measure (SSIM), Information Entropy (Entropy) and Peak Signal to Noise Ratio (PSNR) are used to compare with the different methods. The results show that the method proposed in this paper effectively enhances the contrast of the image while preserving the image brightness. In the average of evaluation metrics of the sample images, SSIM, Entropy and PSNR were 0.219, 2.0811 and 6.6201 higher than those of BPDHE, respectively.","PeriodicalId":231070,"journal":{"name":"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Improved Method for Brightness Preserving Dynamic Histogram Equalization\",\"authors\":\"Fan Yang, Renjie Li\",\"doi\":\"10.1109/AICIT55386.2022.9930196\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Histogram equalization is an effective image enhancement method for improving image contrast, and several equalization methods have been developed. Brightness-preserving dynamic histogram equalization (BPDHE) is a sub-histogram-based equalization method, and there is scope for optimising the performance of BPDHE in the segmentation process of some image histograms and in maintaining image structure and information entropy. Therefore, this paper presents a method to improve BPDHE. First, the image is subjected to bilinear interpolation. Then, the probability density function of the grey level of the image is divided into two parts according to its mean value. Finally, different methods are used to find local maximums for each of these two parts. In this paper, Absolute Mean Brightness Error (AMBE), Structure Similarity Index Measure (SSIM), Information Entropy (Entropy) and Peak Signal to Noise Ratio (PSNR) are used to compare with the different methods. The results show that the method proposed in this paper effectively enhances the contrast of the image while preserving the image brightness. In the average of evaluation metrics of the sample images, SSIM, Entropy and PSNR were 0.219, 2.0811 and 6.6201 higher than those of BPDHE, respectively.\",\"PeriodicalId\":231070,\"journal\":{\"name\":\"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)\",\"volume\":\"26 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AICIT55386.2022.9930196\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AICIT55386.2022.9930196","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An Improved Method for Brightness Preserving Dynamic Histogram Equalization
Histogram equalization is an effective image enhancement method for improving image contrast, and several equalization methods have been developed. Brightness-preserving dynamic histogram equalization (BPDHE) is a sub-histogram-based equalization method, and there is scope for optimising the performance of BPDHE in the segmentation process of some image histograms and in maintaining image structure and information entropy. Therefore, this paper presents a method to improve BPDHE. First, the image is subjected to bilinear interpolation. Then, the probability density function of the grey level of the image is divided into two parts according to its mean value. Finally, different methods are used to find local maximums for each of these two parts. In this paper, Absolute Mean Brightness Error (AMBE), Structure Similarity Index Measure (SSIM), Information Entropy (Entropy) and Peak Signal to Noise Ratio (PSNR) are used to compare with the different methods. The results show that the method proposed in this paper effectively enhances the contrast of the image while preserving the image brightness. In the average of evaluation metrics of the sample images, SSIM, Entropy and PSNR were 0.219, 2.0811 and 6.6201 higher than those of BPDHE, respectively.