A Classification Algorithm of Ultrasonic Thyroid Standard Planes Using LBP and HOG Features

2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID) Pub Date : 2019-10-01 DOI:10.1109/ICASID.2019.8925122

Yihong Wu, Peizhong Liu

{"title":"A Classification Algorithm of Ultrasonic Thyroid Standard Planes Using LBP and HOG Features","authors":"Yihong Wu, Peizhong Liu","doi":"10.1109/ICASID.2019.8925122","DOIUrl":null,"url":null,"abstract":"To improve the performance of thyroid standard plane scanning, this paper proposes a classification algorithm for classifying thyroid ultrasound images using texture features. Firstly, the region of interest of ultrasound images is chosen in the preprocessing process step. Secondly, the local binary patterns (LBP) features and the histograms of oriented gradients (HOG) features of the images are extracted. Then the obtained feature vectors are spliced as the input of the support vector machine (SVM) which is used to classify the thyroid standard plane images. In the experiment, there are 4,574 thyroid standard plane images are used in this paper, which are divided into 8 categories, of which 3,655 pictures for training, and 919 pictures for testing. The experimental results show that the classification accuracy is up to 88.58%, which show a fact that the proposed algorithm has a good discriminating ability for the standard eight-category thyroid plane images, which can assist the doctor to diagnose to a certain extent.","PeriodicalId":422125,"journal":{"name":"2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASID.2019.8925122","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

Abstract

To improve the performance of thyroid standard plane scanning, this paper proposes a classification algorithm for classifying thyroid ultrasound images using texture features. Firstly, the region of interest of ultrasound images is chosen in the preprocessing process step. Secondly, the local binary patterns (LBP) features and the histograms of oriented gradients (HOG) features of the images are extracted. Then the obtained feature vectors are spliced as the input of the support vector machine (SVM) which is used to classify the thyroid standard plane images. In the experiment, there are 4,574 thyroid standard plane images are used in this paper, which are divided into 8 categories, of which 3,655 pictures for training, and 919 pictures for testing. The experimental results show that the classification accuracy is up to 88.58%, which show a fact that the proposed algorithm has a good discriminating ability for the standard eight-category thyroid plane images, which can assist the doctor to diagnose to a certain extent.

查看原文本刊更多论文

基于LBP和HOG特征的超声甲状腺标准平面分类算法

为了提高甲状腺标准平面扫描的性能，本文提出了一种利用纹理特征对甲状腺超声图像进行分类的算法。首先，在预处理过程中选择超声图像的感兴趣区域。其次，提取图像的局部二值模式(LBP)特征和定向梯度直方图(HOG)特征;然后将得到的特征向量拼接作为支持向量机(SVM)的输入，用于甲状腺标准平面图像的分类。在实验中，本文使用了4574张甲状腺标准平面图像，分为8类，其中用于训练的图像为3655张，用于测试的图像为919张。实验结果表明，分类准确率高达88.58%，表明本文算法对标准甲状腺平面八类图像具有较好的判别能力，可以在一定程度上辅助医生诊断。

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

2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)

自引率

0.00%

发文量