{"title":"基于卷积神经网络的珍稀动物图像识别","authors":"Xinyu Hao, Guangsong Yang, Qiubo Ye, Donghai Lin","doi":"10.1109/CISP-BMEI48845.2019.8965748","DOIUrl":null,"url":null,"abstract":"In recent years, due to human destruction, the number of endangered species on the earth is increasing at an alarming rate, and it is urgent to protect the rare species. This paper we propose a new method for rare animal image recognition based on the basic model of Convolutional Neural Networks (CNNs), by which to autonomously extract the image features in the training set and construct an image recognition system to identify rare animals. The method avoids the cumbersome process of manual preprocessing for the target image, and can directly input the original image for recognition, which is more feasible than the traditional image recognition algorithm.","PeriodicalId":257666,"journal":{"name":"2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Rare Animal Image Recognition Based on Convolutional Neural Networks\",\"authors\":\"Xinyu Hao, Guangsong Yang, Qiubo Ye, Donghai Lin\",\"doi\":\"10.1109/CISP-BMEI48845.2019.8965748\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, due to human destruction, the number of endangered species on the earth is increasing at an alarming rate, and it is urgent to protect the rare species. This paper we propose a new method for rare animal image recognition based on the basic model of Convolutional Neural Networks (CNNs), by which to autonomously extract the image features in the training set and construct an image recognition system to identify rare animals. The method avoids the cumbersome process of manual preprocessing for the target image, and can directly input the original image for recognition, which is more feasible than the traditional image recognition algorithm.\",\"PeriodicalId\":257666,\"journal\":{\"name\":\"2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)\",\"volume\":\"56 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 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CISP-BMEI48845.2019.8965748\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CISP-BMEI48845.2019.8965748","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Rare Animal Image Recognition Based on Convolutional Neural Networks
In recent years, due to human destruction, the number of endangered species on the earth is increasing at an alarming rate, and it is urgent to protect the rare species. This paper we propose a new method for rare animal image recognition based on the basic model of Convolutional Neural Networks (CNNs), by which to autonomously extract the image features in the training set and construct an image recognition system to identify rare animals. The method avoids the cumbersome process of manual preprocessing for the target image, and can directly input the original image for recognition, which is more feasible than the traditional image recognition algorithm.