{"title":"基于卷积神经网络的跨光谱图像斑块相似度研究","authors":"Patricia L. Suárez, A. Sappa, B. Vintimilla","doi":"10.1109/ECMSM.2017.7945888","DOIUrl":null,"url":null,"abstract":"The ability to compare image regions (patches) has been the basis of many approaches to core computer vision problems, including object, texture and scene categorization. Hence, developing representations for image patches have been of interest in several works. The current work focuses on learning similarity between cross-spectral image patches with a 2 channel convolutional neural network (CNN) model. The proposed approach is an adaptation of a previous work, trying to obtain similar results than the state of the art but with a low-cost hardware. Hence, obtained results are compared with both classical approaches, showing improvements, and a state of the art CNN based approach.","PeriodicalId":358140,"journal":{"name":"2017 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":"{\"title\":\"Cross-spectral image patch similarity using convolutional neural network\",\"authors\":\"Patricia L. Suárez, A. Sappa, B. Vintimilla\",\"doi\":\"10.1109/ECMSM.2017.7945888\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The ability to compare image regions (patches) has been the basis of many approaches to core computer vision problems, including object, texture and scene categorization. Hence, developing representations for image patches have been of interest in several works. The current work focuses on learning similarity between cross-spectral image patches with a 2 channel convolutional neural network (CNN) model. The proposed approach is an adaptation of a previous work, trying to obtain similar results than the state of the art but with a low-cost hardware. Hence, obtained results are compared with both classical approaches, showing improvements, and a state of the art CNN based approach.\",\"PeriodicalId\":358140,\"journal\":{\"name\":\"2017 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM)\",\"volume\":\"70 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"15\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ECMSM.2017.7945888\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ECMSM.2017.7945888","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Cross-spectral image patch similarity using convolutional neural network
The ability to compare image regions (patches) has been the basis of many approaches to core computer vision problems, including object, texture and scene categorization. Hence, developing representations for image patches have been of interest in several works. The current work focuses on learning similarity between cross-spectral image patches with a 2 channel convolutional neural network (CNN) model. The proposed approach is an adaptation of a previous work, trying to obtain similar results than the state of the art but with a low-cost hardware. Hence, obtained results are compared with both classical approaches, showing improvements, and a state of the art CNN based approach.