{"title":"Analysis of timing constraint on combined SVM-HMM classifier and SVM classifier","authors":"A. K. Kumawat, Sarika Khandelwal","doi":"10.1109/MITE.2013.6756337","DOIUrl":null,"url":null,"abstract":"In Handwriting Verifier Timing constraint is very crucial part which have used in the SVM Classifier, these have using the more time for the large number of sample and get the less accuracy. When there is used the Combined SVM-HMM so that has taken less time for the analysis the large sample and give better accuracy than SVM. That all time has evaluated with the curvelet transform and make a digital clock pulse in form of 1's and 0's. Which have calculate in the invariant movement with the wavelength from the trained data image and replace them, on the place of selected writing image, than make an metric of binary number and calculate them with the method of invariant curve let, thereafter compare the character on the time of the calculate image binary code and make an metrics on the striate line of SVM-HMM in terms of 1's and 0's.","PeriodicalId":284844,"journal":{"name":"2013 IEEE International Conference in MOOC, Innovation and Technology in Education (MITE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference in MOOC, Innovation and Technology in Education (MITE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MITE.2013.6756337","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In Handwriting Verifier Timing constraint is very crucial part which have used in the SVM Classifier, these have using the more time for the large number of sample and get the less accuracy. When there is used the Combined SVM-HMM so that has taken less time for the analysis the large sample and give better accuracy than SVM. That all time has evaluated with the curvelet transform and make a digital clock pulse in form of 1's and 0's. Which have calculate in the invariant movement with the wavelength from the trained data image and replace them, on the place of selected writing image, than make an metric of binary number and calculate them with the method of invariant curve let, thereafter compare the character on the time of the calculate image binary code and make an metrics on the striate line of SVM-HMM in terms of 1's and 0's.