Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zihaomu/opencv_digit_text_recognition_demo
live digits recognition based on opencv dnn and lenet.
https://github.com/zihaomu/opencv_digit_text_recognition_demo
Last synced: 18 days ago
JSON representation
live digits recognition based on opencv dnn and lenet.
- Host: GitHub
- URL: https://github.com/zihaomu/opencv_digit_text_recognition_demo
- Owner: zihaomu
- License: bsd-3-clause
- Created: 2020-03-21T08:59:18.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2020-06-27T06:31:32.000Z (over 4 years ago)
- Last Synced: 2024-12-16T05:44:07.875Z (22 days ago)
- Language: C++
- Homepage:
- Size: 42 MB
- Stars: 2
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Digit&Text detection and recognition
[![License](https://img.shields.io/badge/license-BSD-blue.svg)](LICENSE)### My environment
1. hardware
`cpu: i5-8300H 8-core + 16G RAM + 1050 GPU`
2. software
`Ubuntu 18 + Opencv 4.3`### Digit detection and recognition
Very easy demo, based on opencv dnn c++. Digital detector uses connected components. Since the pre-processing process is simple, the model is sensitive to light changes. It can achieve about 13FPS on my laptop.
There are many things can be done to improve its performance, like using good image preprocessing or deep-learning-based digit detector.
hardware:
`cpu: i5-8300H 8-core + 16G RAM`
model:lenet.caffemodel
lenet.prototxt
DEMO:
![image](./demo/demo.gif)### Text detection and recognition