Improvement of complete malaria cell image segmentation

2017 Twelfth International Conference on Digital Information Management (ICDIM) Pub Date : 2017-09-01 DOI:10.1109/ICDIM.2017.8244655

Monlica Wattana, Tipwalee Boonsri

{"title":"Improvement of complete malaria cell image segmentation","authors":"Monlica Wattana, Tipwalee Boonsri","doi":"10.1109/ICDIM.2017.8244655","DOIUrl":null,"url":null,"abstract":"Blood smear evaluation continues to be a noteworthy method for diagnosing malaria infection. However, obtaining complete malaria cells for analysis is still a problem because the clarity and the brightness of most images are different. So, there are errors in malaria cell detection. Therefore, this study presented the method for adjusting red blood cell images to the optimum brightness level by improving the partial contrast stretching technique. Then S component in the HSI color space was used to detect the red blood cells infected with the malaria. It was also incorporated with a∗ component in CIE L∗a∗b∗ color space to obtain a complete malaria cell. In the experiment, 52 images of thin blood film were used. The results revealed that the accuracy of the detection of malaria-infected red blood cells from the S component was 80.76 percent while the accuracy of the proposed method in this study was accounted for 98.08 percent. Therefore, the proposed method was effective for malaria cell image segmentation, and complete cell images were obtained.","PeriodicalId":144953,"journal":{"name":"2017 Twelfth International Conference on Digital Information Management (ICDIM)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Twelfth International Conference on Digital Information Management (ICDIM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDIM.2017.8244655","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 6

Abstract

Blood smear evaluation continues to be a noteworthy method for diagnosing malaria infection. However, obtaining complete malaria cells for analysis is still a problem because the clarity and the brightness of most images are different. So, there are errors in malaria cell detection. Therefore, this study presented the method for adjusting red blood cell images to the optimum brightness level by improving the partial contrast stretching technique. Then S component in the HSI color space was used to detect the red blood cells infected with the malaria. It was also incorporated with a∗ component in CIE L∗a∗b∗ color space to obtain a complete malaria cell. In the experiment, 52 images of thin blood film were used. The results revealed that the accuracy of the detection of malaria-infected red blood cells from the S component was 80.76 percent while the accuracy of the proposed method in this study was accounted for 98.08 percent. Therefore, the proposed method was effective for malaria cell image segmentation, and complete cell images were obtained.

查看原文本刊更多论文

完全疟疾细胞图像分割的改进

血液涂片评价仍然是诊断疟疾感染的一种值得注意的方法。然而，获得完整的疟疾细胞用于分析仍然是一个问题，因为大多数图像的清晰度和亮度是不同的。所以疟疾细胞的检测是有错误的。因此，本研究提出了通过改进部分对比度拉伸技术将红细胞图像调整到最佳亮度水平的方法。然后利用HSI颜色空间中的S分量检测感染疟疾的红细胞。它还与CIE L * a * b *颜色空间中的一个*分量合并以获得一个完整的疟疾细胞。实验中使用了52张血液薄膜图像。结果表明，S组分检测疟疾感染红细胞的准确率为80.76%，而本研究提出的方法的准确率为98.08%。因此，该方法对疟疾细胞图像分割是有效的，获得了完整的细胞图像。

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分钟内获得全文求助全文

来源期刊

2017 Twelfth International Conference on Digital Information Management (ICDIM)

自引率

0.00%

发文量