Details Enhancement In Low Contrast Region Of Inspection Image Based On Fuzzy Rough Set

2021 International Conference on Culture-oriented Science & Technology (ICCST) Pub Date : 2021-11-01 DOI:10.1109/ICCST53801.2021.00100

Junbao Zheng, Junpeng Ji, Xiu Liu

{"title":"Details Enhancement In Low Contrast Region Of Inspection Image Based On Fuzzy Rough Set","authors":"Junbao Zheng, Junpeng Ji, Xiu Liu","doi":"10.1109/ICCST53801.2021.00100","DOIUrl":null,"url":null,"abstract":"In the large dynamic range of inspection images, low-density objects mostly exist in the areas with low contrast, which makes it difficult to identify or show them. The existing image enhancement algorithms mostly do not consider this characteristic of the X-ray inspection image. To solve the detail enhancement problem for quarantine inspection, an fuzzy rough set method is proposed to extract the low-density quarantine objects in X-ray inspection image. Firstly, after negative operating and noise filtering, the inspection image is divided into two parts with rough set method, one is the region of interest that may have the low-density quarantine object, and the other on the contrary. Then, within the region of interest, a fuzzy degree is used to determine the probability of a certain pixel to belong to the quarantine target. Finally, according to the pixel classification results, some pixel values are adjusted in HSV space to show quarantine target distinctly. The capability of detail enhancement in low-contrast region of high dynamic image is also evaluated with the experiments on simulation data and real X-ray images.","PeriodicalId":222463,"journal":{"name":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Culture-oriented Science & Technology (ICCST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCST53801.2021.00100","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

In the large dynamic range of inspection images, low-density objects mostly exist in the areas with low contrast, which makes it difficult to identify or show them. The existing image enhancement algorithms mostly do not consider this characteristic of the X-ray inspection image. To solve the detail enhancement problem for quarantine inspection, an fuzzy rough set method is proposed to extract the low-density quarantine objects in X-ray inspection image. Firstly, after negative operating and noise filtering, the inspection image is divided into two parts with rough set method, one is the region of interest that may have the low-density quarantine object, and the other on the contrary. Then, within the region of interest, a fuzzy degree is used to determine the probability of a certain pixel to belong to the quarantine target. Finally, according to the pixel classification results, some pixel values are adjusted in HSV space to show quarantine target distinctly. The capability of detail enhancement in low-contrast region of high dynamic image is also evaluated with the experiments on simulation data and real X-ray images.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于模糊粗糙集的检测图像低对比度区域细节增强

在大动态范围的检测图像中，低密度目标多存在于对比度较低的区域，难以识别或显示。现有的图像增强算法大多没有考虑到x射线检测图像的这一特性。为了解决检疫检测中的细节增强问题，提出了一种模糊粗糙集方法提取x射线检测图像中的低密度检疫目标。首先，对检测图像进行负运算和噪声滤波后，采用粗糙集方法将检测图像分成两部分，一部分是可能存在低密度隔离对象的感兴趣区域，另一部分是可能存在低密度隔离对象的感兴趣区域。然后，在感兴趣的区域内，使用模糊度来确定某个像素属于隔离目标的概率。最后，根据像素分类结果，在HSV空间中调整一些像素值，使隔离目标更加清晰。通过仿真数据和真实x射线图像的实验，对高动态图像低对比度区域的细节增强能力进行了评价。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2021 International Conference on Culture-oriented Science & Technology (ICCST)

自引率

0.00%

发文量