Automatic Pigment Network Classification Using a Combination of Classical Texture Descriptors and CNN Features

Melinda Pap, B. Harangi, A. Hajdu
{"title":"Automatic Pigment Network Classification Using a Combination of Classical Texture Descriptors and CNN Features","authors":"Melinda Pap, B. Harangi, A. Hajdu","doi":"10.1109/CBMS.2017.63","DOIUrl":null,"url":null,"abstract":"The presence of atypical (irregular) pigment networks can be a symptom of melanoma malignum in skin lesions, thus, their proper recognition is a critical task. For object classification problems, the application of deep convolutional neural nets (CNN) receives priority attention nowadays for their high recognition rate. The descriptive features found by CNNs are more hidden than the classically applied ones for texture recognition. In this paper, we investigate whether CNN features outperform the classical texture descriptors in the classification of typical/atypical pigment network. Beyond performing this analysis, we have also found that the aggregation of CNN and classical features within a joint classification framework had a superior performance. Specifically, the union of the CNN and classical feature sets leads to a much higher stability in classification performance for various classifiers. As for quantitative figures, we have reached 90.44% recognition accuracy using a specific subset of this combined feature set obtained by linear forward feature selection and using a Bayes Net as classifier.","PeriodicalId":141105,"journal":{"name":"2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CBMS.2017.63","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

The presence of atypical (irregular) pigment networks can be a symptom of melanoma malignum in skin lesions, thus, their proper recognition is a critical task. For object classification problems, the application of deep convolutional neural nets (CNN) receives priority attention nowadays for their high recognition rate. The descriptive features found by CNNs are more hidden than the classically applied ones for texture recognition. In this paper, we investigate whether CNN features outperform the classical texture descriptors in the classification of typical/atypical pigment network. Beyond performing this analysis, we have also found that the aggregation of CNN and classical features within a joint classification framework had a superior performance. Specifically, the union of the CNN and classical feature sets leads to a much higher stability in classification performance for various classifiers. As for quantitative figures, we have reached 90.44% recognition accuracy using a specific subset of this combined feature set obtained by linear forward feature selection and using a Bayes Net as classifier.
结合经典纹理描述符和CNN特征的色素网络自动分类
非典型(不规则)色素网络的存在可能是皮肤病变恶性黑色素瘤的症状,因此,正确识别它们是一项关键任务。对于目标分类问题,深度卷积神经网络(CNN)以其较高的识别率而备受关注。cnn发现的描述性特征比传统的纹理识别更隐蔽。在本文中,我们研究了CNN特征在典型/非典型颜料网络分类中是否优于经典纹理描述符。除了进行此分析之外,我们还发现,在联合分类框架内,CNN和经典特征的聚合具有更优越的性能。具体来说,CNN与经典特征集的结合使得各种分类器的分类性能具有更高的稳定性。对于定量图形,我们使用线性前向特征选择获得的组合特征集的特定子集,并使用贝叶斯网络作为分类器,识别准确率达到90.44%。
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信