[1] 陆靖滨,许丽.基于自适应特征提取的数显仪表识别系统[J].现代电子技术,2017,40(24):147-150.(LU J B, XU L. Digital-display instrument recognition system based on adaptive feature extraction[J]. Modern Electronics Technique, 2017, 40(24):147-150.) [2] 董延华,陈中华,宋和烨,等.改进特征匹配算法在银行卡号识别中的应用[J].吉林大学学报(理学版),2018,56(1):126-129.(DONG Y H, CHEN Z H, SONG H Y, et al. Application of improved feature matching algorithm in bank card number recognition[J]. Journal of Jilin University (Science Edition), 2018, 56(1):126-129.) [3] 陈玮,曹志广,李剑平.改进的模板匹配方法在车牌识别中的应用[J].计算机工程与设计,2013,34(5):1808-1811.(CHEN W, CAO Z G, LI J P. Application of improved templates matching method on license plate recognition[J]. Computer Engineering and Design, 2013, 34(5):1808-1811.) [4] 甘胜江,白艳宇,孙连海,等.融合改进K近邻和随机森林的机器学习方法[J].计算机工程与设计,2017,38(8):2251-2255,2275.(GAN S J, BAI Y Y, SUN L H, et al. Machine learning method fusing improved K-nearest neighbor and random forest[J]. Computer Engineering and Design, 2017, 38(8):2251-2255, 2275.) [5] TUBA E, BACANIN N. An algorithm for handwritten digit recognition using projection histograms and SVM classifier[C]//Proceeding of the 23rd Telecommunications Forum Telfor. Piscataway, NJ:IEEE, 2015:464-467. [6] 潘虎,陈斌,李全文.基于二叉树和Adaboost算法的纸币号码识别[J].计算机应用,2011,31(2):396-398.(PAN H, CHEN B, LI Q W. Paper currency number recognition based on binary tree and Adaboost algorithm[J]. Journal of Computer Applications, 2011, 31(2):396-398.) [7] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324. [8] ALANI A. Arabic handwritten digit recognition based on restricted Boltzmann machine and convolutional neural networks[J]. Information, 2017, 8(142):1-13. [9] SINGH S, PAUL A, ARUN M. Parallelization of digit recognition system using deep convolutional neural network on CUDA[C]//Proceeding of the 2017 International Conference on Sensing, Signal Processing and Security. Piscataway, NJ:IEEE, 2017:379-383. [10] SABOUR S, FROSST N, HINTON G E. Dynamic routing between capsules[C]//Proceeding of the 31st Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2017:1-11. [11] JIA Y, SHELHAMER E, DONAHUE J, et al. Caffe:convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York:ACM, 2014:675-678. [12] LECUN Y, CORTES C. The MNIST database of handwritten digits[DB/OL].[2018-03-26]. http://yann.lecun.com/exdb/mnist/. [13] 叶景东,宗寿松,朱美强,等.基于机器视觉的矿用数显电测量仪表检测系统[J].工矿自动化,2016,42(9):13-16.(YE J D, ZONG S S, ZHU M Q, et al. Detection system for coal mine electrical inspection instrument with digital display based on machine vision[J]. Industry and Mine Automation, 2016, 42(9):13-16.) [14] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444. [15] 赵永科.深度学习:21天实战Caffe[M].北京:电子工业出版社,2016:50-76.(ZHAO Y K. Deep Learning 21 Days Real Battle Caffe Tutorials Fast Mastering Framework[M]. Beijing:Publishing House of Electronics Industry, 2016:50-76.) [16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. New York:Curran Associates Inc. 2012:1097-1105. [17] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958. [18] 王文朋,毛文涛,何建樑,等.基于深度迁移学习的烟雾识别方法[J].计算机应用,2017,37(11):3176-3181.(WANG W P, MAO W T, HE J L, et al. Smoke recognition based on deep transfer learning[J]. Journal of Computer Applications, 2017, 37(11):3176-3181.) [19] RASTEGARI M, ORDONEZ V, REDMON J, et al. XNOR-Net:ImageNet classification using binary convolutional neural networks[C]//Proceeding of the 2016 European Conference on Computer Vision, LNCS 9908. Berlin:Springer, 2016:525-542. |