{"title":"局部微分激励二值共现模式(LDEBCoP):一种新的纹理和生物医学图像检索描述符","authors":"G. V. S. Kumar, P. Mohan","doi":"10.9790/0661-1903053748","DOIUrl":null,"url":null,"abstract":"This paper presents a novel pattern based feature descriptor named as Local Differential Excitation Binary Cooccurrence Pattern (LDEBCoP) for texture and biomedical image retrieval. The proposed method exploits the local structure information using differential excitation. Further, to produce more compact local binary patterns the adjacent neighbourhood pixel pairs are considered in the computation of differential excitation. In the proposed method, the co-occurrence of pixel pairs in local binary map have been observed using gray level co-occurrence matrix(GLCM) in different directions and distances for better feature representation. Previous methods have utilized histogram to obtain the frequency information of local pattern map but cooccurrence of pixel pairs is more robust than frequency of patterns. The performance of proposed method is compared with the state of the art pattern based techniques on the results obtained using various bench mark image databases viz., KTH-TIPS, OUTEX texture database, NEMA−CT database and VIA/I– ELCAP database which also includes region of interest CT images.","PeriodicalId":91890,"journal":{"name":"IOSR journal of computer engineering","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Local Differential Excitation Binary Co-occurrence Pattern (LDEBCoP): A New Descriptor for Texture and Bio-Medical Image Retrieval\",\"authors\":\"G. V. S. Kumar, P. Mohan\",\"doi\":\"10.9790/0661-1903053748\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a novel pattern based feature descriptor named as Local Differential Excitation Binary Cooccurrence Pattern (LDEBCoP) for texture and biomedical image retrieval. The proposed method exploits the local structure information using differential excitation. Further, to produce more compact local binary patterns the adjacent neighbourhood pixel pairs are considered in the computation of differential excitation. In the proposed method, the co-occurrence of pixel pairs in local binary map have been observed using gray level co-occurrence matrix(GLCM) in different directions and distances for better feature representation. Previous methods have utilized histogram to obtain the frequency information of local pattern map but cooccurrence of pixel pairs is more robust than frequency of patterns. The performance of proposed method is compared with the state of the art pattern based techniques on the results obtained using various bench mark image databases viz., KTH-TIPS, OUTEX texture database, NEMA−CT database and VIA/I– ELCAP database which also includes region of interest CT images.\",\"PeriodicalId\":91890,\"journal\":{\"name\":\"IOSR journal of computer engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IOSR journal of computer engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.9790/0661-1903053748\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IOSR journal of computer engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.9790/0661-1903053748","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Local Differential Excitation Binary Co-occurrence Pattern (LDEBCoP): A New Descriptor for Texture and Bio-Medical Image Retrieval
This paper presents a novel pattern based feature descriptor named as Local Differential Excitation Binary Cooccurrence Pattern (LDEBCoP) for texture and biomedical image retrieval. The proposed method exploits the local structure information using differential excitation. Further, to produce more compact local binary patterns the adjacent neighbourhood pixel pairs are considered in the computation of differential excitation. In the proposed method, the co-occurrence of pixel pairs in local binary map have been observed using gray level co-occurrence matrix(GLCM) in different directions and distances for better feature representation. Previous methods have utilized histogram to obtain the frequency information of local pattern map but cooccurrence of pixel pairs is more robust than frequency of patterns. The performance of proposed method is compared with the state of the art pattern based techniques on the results obtained using various bench mark image databases viz., KTH-TIPS, OUTEX texture database, NEMA−CT database and VIA/I– ELCAP database which also includes region of interest CT images.