作者: Jija Das Gupta , Soumitra Samanta
DOI: 10.1109/ICAPR.2017.8593025
关键词: Handwriting recognition 、 Feature (machine learning) 、 Word recognition 、 Identification (information) 、 Cashier's check 、 Computer science 、 Test set 、 Convolutional neural network 、 Database 、 Word (computer architecture)
摘要: This paper present a new handwritten English word database namely, ISIHWD for off-line recognition and writer identification. It is collection of 62 legal amount words used in Indian bank cheque written by 105 different writers. The consist 31124 split into training set 24924 test 6200 to provide common platform independent recognition. evaluated deep convolution neural network based feature with SVM classifier text dependent identification on single word. Average accuracy are achieved as 95.35% 85.70% respectively.