cnn_lstm_ctc_ocr is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named cnn_lstm_ctc_ocr among their alternatives. The relationship is not symmetric — how cnn_lstm_ctc_ocr rates them is a separate judgement, made when cnn_lstm_ctc_ocr is analysed in its own right.
calls cnn_lstm_ctc_ocr “When you want a simpler independent CNN+CTC TensorFlow OCR trainer instead of the seed's project-management framework; note GPL-3.0 license.”
[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
calls cnn_lstm_ctc_ocr “TensorFlow CNN+LSTM+CTC with GPL license, choose for a maintained TensorFlow baseline.”
主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构
calls cnn_lstm_ctc_ocr “TensorFlow CNN+LSTM CTC OCR model for training/custom text recognition; more limited than a full engine.”
Tesseract Open Source OCR Engine (main repository)
calls cnn_lstm_ctc_ocr “Choose when you want a minimal, self-contained TensorFlow OCR implementation for training on custom data as a research reference.”
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.