CTPN
Text detector
Detects text in images using a neural network architecture
Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)
1k stars
78 watching
538 forks
Language: Jupyter Notebook
last commit: over 3 years ago
Linked from 1 awesome list
ocrtext-detection
Related projects:
Repository | Description | Stars |
---|---|---|
| A tool for detecting and translating text from images. | 180 |
| Develops CTC-based text recognition models with neural network architectures | 259 |
| Improves object detection by generating region proposals with increased adaptivity. | 156 |
| A research project focused on developing algorithms and models to accurately detect and recognize text in images and videos from various scenes. | 368 |
| Recurrent neural network designed to detect code blocks in text. | 12 |
| A Caffe-based implementation of A-Fast-RCNN, a method for object detection using adversarial networks. | 482 |
| An Android implementation of object detection using Yolov7 and the ncnn neural network library | 137 |
| A TensorFlow-based implementation of Faster R-CNN object detection using pre-trained ResNet networks and custom datasets. | 875 |
| An implementation of Mask R-CNN using MXNet and Resnet-50-FPN for object detection and segmentation in images. | 1,755 |
| A neural network framework for wireframe parsing from images | 508 |
| A 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 |
| A Matlab project for vehicle detection and recognition using deep learning techniques. | 202 |
| This project demonstrates how to build and train a convolutional neural network (CNN) to recognize Chinese characters. | 200 |
| An implementation of R-FCN, an object detection algorithm using region-based fully convolutional networks. | 1,048 |
| A tool for fine-tuning deep neural networks to improve object detection and segmentation capabilities by incorporating contextual information. | 27 |