Farrel Athaillah Putra, Dwi Anggun Cahyati Jamil, Briliantino Abhista Prabandanu, Suhaili Faruq, Firsta Adi Pradana, Riqqah Fadiyah Alya, H. Santoso, Farrikh Al Zami, Filmada Ocky Saputra
{"title":"基于迁移学习卷积神经网络算法的蜡染真伪分类","authors":"Farrel Athaillah Putra, Dwi Anggun Cahyati Jamil, Briliantino Abhista Prabandanu, Suhaili Faruq, Firsta Adi Pradana, Riqqah Fadiyah Alya, H. Santoso, Farrikh Al Zami, Filmada Ocky Saputra","doi":"10.1109/ICIC54025.2021.9632937","DOIUrl":null,"url":null,"abstract":"Batik is one of Indonesia's cultural heritages that UNESCO has recognized as an Intangible Cultural Heritage, so we should be proud and preserve it. However, there are problems in the batik industry related to the labelling of traditional and modern batik products. The prevalence of fraud in printed batik, which is given a price equivalent to written batik, which is much more expensive, and public ignorance of the aesthetic value and authenticity of written batik, can disrupt the traditional batik industry in Indonesia. Based on these problems, the authors innovate to develop a machine learning model that aims to classify the authenticity of batik using the Convolutional Neural Network Algorithm with Transfer Learning Method. The classification process consists of several stages: collecting datasets, preprocessing data, developing CNN models with transfer learning, and compiling and training models. The development of the machine learning model that has been trained produces an accuracy of 96.91%. The author hopes that this research can make it easier for people to distinguish between written and printed batik, minimize the existence of batik price fraud, and increase consumer confidence in batik transactions by ensuring the originality of batik products.","PeriodicalId":189541,"journal":{"name":"2021 Sixth International Conference on Informatics and Computing (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Classification of Batik Authenticity Using Convolutional Neural Network Algorithm with Transfer Learning Method\",\"authors\":\"Farrel Athaillah Putra, Dwi Anggun Cahyati Jamil, Briliantino Abhista Prabandanu, Suhaili Faruq, Firsta Adi Pradana, Riqqah Fadiyah Alya, H. Santoso, Farrikh Al Zami, Filmada Ocky Saputra\",\"doi\":\"10.1109/ICIC54025.2021.9632937\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Batik is one of Indonesia's cultural heritages that UNESCO has recognized as an Intangible Cultural Heritage, so we should be proud and preserve it. However, there are problems in the batik industry related to the labelling of traditional and modern batik products. The prevalence of fraud in printed batik, which is given a price equivalent to written batik, which is much more expensive, and public ignorance of the aesthetic value and authenticity of written batik, can disrupt the traditional batik industry in Indonesia. Based on these problems, the authors innovate to develop a machine learning model that aims to classify the authenticity of batik using the Convolutional Neural Network Algorithm with Transfer Learning Method. The classification process consists of several stages: collecting datasets, preprocessing data, developing CNN models with transfer learning, and compiling and training models. The development of the machine learning model that has been trained produces an accuracy of 96.91%. The author hopes that this research can make it easier for people to distinguish between written and printed batik, minimize the existence of batik price fraud, and increase consumer confidence in batik transactions by ensuring the originality of batik products.\",\"PeriodicalId\":189541,\"journal\":{\"name\":\"2021 Sixth International Conference on Informatics and Computing (ICIC)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 Sixth International Conference on Informatics and Computing (ICIC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIC54025.2021.9632937\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Sixth International Conference on Informatics and Computing (ICIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIC54025.2021.9632937","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Classification of Batik Authenticity Using Convolutional Neural Network Algorithm with Transfer Learning Method
Batik is one of Indonesia's cultural heritages that UNESCO has recognized as an Intangible Cultural Heritage, so we should be proud and preserve it. However, there are problems in the batik industry related to the labelling of traditional and modern batik products. The prevalence of fraud in printed batik, which is given a price equivalent to written batik, which is much more expensive, and public ignorance of the aesthetic value and authenticity of written batik, can disrupt the traditional batik industry in Indonesia. Based on these problems, the authors innovate to develop a machine learning model that aims to classify the authenticity of batik using the Convolutional Neural Network Algorithm with Transfer Learning Method. The classification process consists of several stages: collecting datasets, preprocessing data, developing CNN models with transfer learning, and compiling and training models. The development of the machine learning model that has been trained produces an accuracy of 96.91%. The author hopes that this research can make it easier for people to distinguish between written and printed batik, minimize the existence of batik price fraud, and increase consumer confidence in batik transactions by ensuring the originality of batik products.