{"title":"Quality Detection of Export Purple Sweet Potatoes Using Yolov4-Tiny","authors":"S. Lestari, Aviv Yuniar Rahman, Istiadi","doi":"10.1109/ISITIA59021.2023.10221110","DOIUrl":null,"url":null,"abstract":"Purple sweet potato is used as a food staple, especially for Indonesian people. The production process for sweet potato has been produced and exported to various countries for market development. One of the businesses that processes sweet potatoes is UBI Jalar UKM in Sukun District, Malang City. Sweet Potato UKM is an agricultural group engaged in the planting of sweet potatoes. Many sweet potatoes sent to the factory were rejected. The process of selecting sweet potatoes for export still uses a manual system by selecting them directly without considering quality. Therefore it is necessary to detect the quality of superior sweet potatoes using the yolov4-tiny method. Many sweet potatoes submitted by SMEs are rejected by factories/industry because export standards do not comply. Therefore, the selection process manually can be detrimental to the SMEs themselves. So it is necessary to detect the quality of purple sweet potato using the yolov4-tiny method to reduce losses to SMEs. The results on the detection of sweet potatoes using yolov4-tiny prove that the method detects sweet potatoes according to each grade. Furthermore, the system for detecting the quality of sweet potatoes employs yolov4-tiny technology to ensure that they meet industry standards for export. The sweet potatoes are classified into five grades with an impressive 99.15% mAP score.","PeriodicalId":116682,"journal":{"name":"2023 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Seminar on Intelligent Technology and Its Applications (ISITIA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISITIA59021.2023.10221110","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Purple sweet potato is used as a food staple, especially for Indonesian people. The production process for sweet potato has been produced and exported to various countries for market development. One of the businesses that processes sweet potatoes is UBI Jalar UKM in Sukun District, Malang City. Sweet Potato UKM is an agricultural group engaged in the planting of sweet potatoes. Many sweet potatoes sent to the factory were rejected. The process of selecting sweet potatoes for export still uses a manual system by selecting them directly without considering quality. Therefore it is necessary to detect the quality of superior sweet potatoes using the yolov4-tiny method. Many sweet potatoes submitted by SMEs are rejected by factories/industry because export standards do not comply. Therefore, the selection process manually can be detrimental to the SMEs themselves. So it is necessary to detect the quality of purple sweet potato using the yolov4-tiny method to reduce losses to SMEs. The results on the detection of sweet potatoes using yolov4-tiny prove that the method detects sweet potatoes according to each grade. Furthermore, the system for detecting the quality of sweet potatoes employs yolov4-tiny technology to ensure that they meet industry standards for export. The sweet potatoes are classified into five grades with an impressive 99.15% mAP score.