Alaa Abdalhaleem, Berat Kurar Barakat, Jihad El-Sana
{"title":"案例研究:使用暹罗神经网络进行精细写作风格分类","authors":"Alaa Abdalhaleem, Berat Kurar Barakat, Jihad El-Sana","doi":"10.1109/ASAR.2018.8480212","DOIUrl":null,"url":null,"abstract":"This paper presents an automatic system for dividing a manuscript into similar parts, according to their similarity in writing style. This system is based on Siamese neural network, which consists of two identical sub-networks joined at their outputs. In the training the two sub-networks extract features from two patches, while the joining neuron measures the distance between the two feature vectors. Patches from the same page are considered as identical and patches from different books are considered as different. Based on that, the Siamese network computes the distances between patches of the same book.","PeriodicalId":165564,"journal":{"name":"2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR)","volume":"116 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Case Study: Fine Writing Style Classification Using Siamese Neural Network\",\"authors\":\"Alaa Abdalhaleem, Berat Kurar Barakat, Jihad El-Sana\",\"doi\":\"10.1109/ASAR.2018.8480212\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents an automatic system for dividing a manuscript into similar parts, according to their similarity in writing style. This system is based on Siamese neural network, which consists of two identical sub-networks joined at their outputs. In the training the two sub-networks extract features from two patches, while the joining neuron measures the distance between the two feature vectors. Patches from the same page are considered as identical and patches from different books are considered as different. Based on that, the Siamese network computes the distances between patches of the same book.\",\"PeriodicalId\":165564,\"journal\":{\"name\":\"2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR)\",\"volume\":\"116 1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASAR.2018.8480212\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASAR.2018.8480212","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Case Study: Fine Writing Style Classification Using Siamese Neural Network
This paper presents an automatic system for dividing a manuscript into similar parts, according to their similarity in writing style. This system is based on Siamese neural network, which consists of two identical sub-networks joined at their outputs. In the training the two sub-networks extract features from two patches, while the joining neuron measures the distance between the two feature vectors. Patches from the same page are considered as identical and patches from different books are considered as different. Based on that, the Siamese network computes the distances between patches of the same book.