R. Guzmán Cabrera, Deborah Martínez, M. TORRES CISNEROS, D. MAY ARRIOJA, Mary Carmen PEÑA GOMAR
{"title":"使用机器学习的汽车自动识别","authors":"R. Guzmán Cabrera, Deborah Martínez, M. TORRES CISNEROS, D. MAY ARRIOJA, Mary Carmen PEÑA GOMAR","doi":"10.6036/10673","DOIUrl":null,"url":null,"abstract":"In this work, we perform the automatic classification of 1,000 images of five different models of automobiles. To obtain the highest precision, we have used two different classification scenarios, three algorithms, and five metrics. Also, we assume that the results can be improved by extracting the image characteristics using descriptors and using them as input. Then, we used two descriptors: a histogram of oriented gradient and a convolutional neural network ResNet-50. Our results show that the descriptors improve the classification results and obtain the highest value for the accuracy metric of 88.01 % using the ResNet-50 as a descriptor, the Training and Test Set as a scenario, and Vector Support Machine as the classification algorithm.\n\nKeywords: Convolutional Neural Networks, Gradient Oriented Histogram, Machine Learning, Fine Grain Classification, Car Images.","PeriodicalId":50565,"journal":{"name":"Dyna-Colombia","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AUTOMATIC RECOGNITION OF AUTOMOBILES USING MACHINE LEARNING\",\"authors\":\"R. Guzmán Cabrera, Deborah Martínez, M. TORRES CISNEROS, D. MAY ARRIOJA, Mary Carmen PEÑA GOMAR\",\"doi\":\"10.6036/10673\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, we perform the automatic classification of 1,000 images of five different models of automobiles. To obtain the highest precision, we have used two different classification scenarios, three algorithms, and five metrics. Also, we assume that the results can be improved by extracting the image characteristics using descriptors and using them as input. Then, we used two descriptors: a histogram of oriented gradient and a convolutional neural network ResNet-50. Our results show that the descriptors improve the classification results and obtain the highest value for the accuracy metric of 88.01 % using the ResNet-50 as a descriptor, the Training and Test Set as a scenario, and Vector Support Machine as the classification algorithm.\\n\\nKeywords: Convolutional Neural Networks, Gradient Oriented Histogram, Machine Learning, Fine Grain Classification, Car Images.\",\"PeriodicalId\":50565,\"journal\":{\"name\":\"Dyna-Colombia\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Dyna-Colombia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.6036/10673\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Dyna-Colombia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.6036/10673","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}
AUTOMATIC RECOGNITION OF AUTOMOBILES USING MACHINE LEARNING
In this work, we perform the automatic classification of 1,000 images of five different models of automobiles. To obtain the highest precision, we have used two different classification scenarios, three algorithms, and five metrics. Also, we assume that the results can be improved by extracting the image characteristics using descriptors and using them as input. Then, we used two descriptors: a histogram of oriented gradient and a convolutional neural network ResNet-50. Our results show that the descriptors improve the classification results and obtain the highest value for the accuracy metric of 88.01 % using the ResNet-50 as a descriptor, the Training and Test Set as a scenario, and Vector Support Machine as the classification algorithm.
Keywords: Convolutional Neural Networks, Gradient Oriented Histogram, Machine Learning, Fine Grain Classification, Car Images.
期刊介绍:
The DYNA journal, consistent with the aim of disseminating research in engineering, covers all disciplines within the large area of Engineering and Technology (OECD), through research articles, case studies and review articles resulting from work of national and international researchers.