crnn

Sequence recognizer

An image-based sequence recognition system using a combination of CNN and RNN algorithms.

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

GitHub

2k stars
78 watching
552 forks
Language: Lua
last commit: over 7 years ago
computer-visionmachine-learningocrsequence-recognitiontorch7

Related projects:

RepositoryDescriptionStars
warrengreen/srcnnSoftware for enhancing satellite images through deep learning techniques76
nv-tlabs/gscnnThis code implements a neural network architecture designed to perform semantic segmentation in computer vision tasks.920
guillaume-chevalier/har-stacked-residual-bidir-lstmsAn implementation of a deep neural network architecture for Human Activity Recognition using stacked residual bidirectional LSTM cells with TensorFlow.319
google/uis-rnnThis library provides an implementation of an algorithm for segmenting and clustering sequential data, learning from examples.1,564
aaronshan/12306-captchaDeep learning-based system to recognize and classify 12306 captcha images281
cszn/bsrganA deep learning-based approach to super-resolution of degraded images.1,222
oyxhust/cnn-lstm-ctc-text-recognitionDevelops CTC-based text recognition models with neural network architectures259
saschagrunert/nnA small neural network implementation of the backpropagation algorithm in Haskell127
taosir/cnn_handwritten_chinese_recognitionA Python-based web application that recognizes handwritten Chinese characters using a Convolutional Neural Network (CNN), allowing users to input text via an online writing board and receive recognition results.511
canjie-luo/moran_v2A deep learning framework for scene text recognition with rectification and attention mechanisms.639
martinkersner/train-crf-rnnTrains a CRF-RNN model for semantic image segmentation using the PASCAL VOC dataset.199
berkeleyautomation/gqcnnDevelops and analyzes convolutional neural networks for grasp quality in robotics316
torrvision/crfasrnnA deep learning-based method for semantic image segmentation using conditional random fields and recurrent neural networks1,342
cszn/srmdDevelops a single convolutional network to handle various image degradations with improved scalability and efficiency427
bruinxiong/modified-crunet-and-residual-attention-network.mxnetAn MXNet implementation of a modified deep neural network architecture for image classification67