High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps
Recognize your handwritten numbers
https://medium.com/@o.kroeger/recognize-your-handwritten-numbers-3f007cbe46ff#.jllz62xgu
Handwritten Digit Recognition using Convolutional Neural Networks in Python with Keras
MNIST Handwritten Digit Classifier
如何用卷积神经网络CNN识别手写数字集？
LeNet – Convolutional Neural Network in Python
Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention
MLPaint: the Real-Time Handwritten Digit Recognizer
- blog: http://blog.mldb.ai/blog/posts/2016/09/mlpaint/
- github: https://github.com/mldbai/mlpaint
- demo: https://docs.mldb.ai/ipy/notebooks/_demos/_latest/Image%20Processing%20with%20Convolutions.html
Training a Computer to Recognize Your Handwriting
Using TensorFlow to create your own handwriting recognition engine
- blog: https://niektemme.com/2016/02/21/tensorflow-handwriting/
- github: https://github.com/niektemme/tensorflow-mnist-predict/
Building a Deep Handwritten Digits Classifier using Microsoft Cognitive Toolkit
- blog: https://medium.com/@tuzzer/building-a-deep-handwritten-digits-classifier-using-microsoft-cognitive-toolkit-6ae966caec69#.c3h6o7oxf
- github: https://github.com/tuzzer/ai-gym/blob/a97936619cf56b5ed43329c6fa13f7e26b1d46b8/MNIST/minist_softmax_cntk.py
Hand Writing Recognition Using Convolutional Neural Networks
- intro: This CNN-based model for recognition of hand written digits attains a validation accuracy of 99.2% after training for 12 epochs. Its trained on the MNIST dataset on Kaggle.
- github: https://github.com/ayushoriginal/HandWritingRecognition-CNN
Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling
- intro: 0.57 MB, performance is decreased only by 0.91%.
- arxiv: https://arxiv.org/abs/1705.05207
Handwritten digit string recognition by combination of residual network and RNN-CTC