Handwritten Digit Recognition Using Deep CNN
Issam Bendib, Abdeljalil Gattal, Guedri Marouane · 2020
This study demonstrates how the deep Convolutional Neural Network (CNN) can be effectively employed to enhance the performance of isolated digit recognition systems. The global and local features are extracted automatically by CNN from the normalized image. Classification is carried out using Convolutional Neural Network while the experimental study is conducted on the standard CVL single digit database. A series of evaluations using different configurations of CNNs realized high recognition rates which are compared with the state-of-the-art methods on this subject.