Chen Guojin, Ling Yongning, Zhu Miao-fen, Wang Wan-qiang
{"title":"基于人工神经网络的图像自动调焦方法","authors":"Chen Guojin, Ling Yongning, Zhu Miao-fen, Wang Wan-qiang","doi":"10.1109/CIMSA.2010.5611751","DOIUrl":null,"url":null,"abstract":"According to the image feature extraction capacity based on wavelet transformation and the nonlinear, self-adaptive and pattern recognition capacity based on artificial neural networks, the image auto-focusing method based on artificial neural networks is put forward. The wavelet components' statistics obtained by the wavelet transform are taken as the inputs of the 5 layer BP neural network model. The model identifies the image definition applying the steepest descent method of the additional momentum in a variable step to adjust the network weights. The model is first trained by 75 images from a training set, and then is tested by 102 images from a testing set. The results show that it is a very effective identification method which can obtain a higher recognition rate.","PeriodicalId":162890,"journal":{"name":"2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"221 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"The image auto-focusing method based on artificial neural networks\",\"authors\":\"Chen Guojin, Ling Yongning, Zhu Miao-fen, Wang Wan-qiang\",\"doi\":\"10.1109/CIMSA.2010.5611751\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"According to the image feature extraction capacity based on wavelet transformation and the nonlinear, self-adaptive and pattern recognition capacity based on artificial neural networks, the image auto-focusing method based on artificial neural networks is put forward. The wavelet components' statistics obtained by the wavelet transform are taken as the inputs of the 5 layer BP neural network model. The model identifies the image definition applying the steepest descent method of the additional momentum in a variable step to adjust the network weights. The model is first trained by 75 images from a training set, and then is tested by 102 images from a testing set. The results show that it is a very effective identification method which can obtain a higher recognition rate.\",\"PeriodicalId\":162890,\"journal\":{\"name\":\"2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications\",\"volume\":\"221 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-10-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CIMSA.2010.5611751\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIMSA.2010.5611751","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The image auto-focusing method based on artificial neural networks
According to the image feature extraction capacity based on wavelet transformation and the nonlinear, self-adaptive and pattern recognition capacity based on artificial neural networks, the image auto-focusing method based on artificial neural networks is put forward. The wavelet components' statistics obtained by the wavelet transform are taken as the inputs of the 5 layer BP neural network model. The model identifies the image definition applying the steepest descent method of the additional momentum in a variable step to adjust the network weights. The model is first trained by 75 images from a training set, and then is tested by 102 images from a testing set. The results show that it is a very effective identification method which can obtain a higher recognition rate.