kazmiekr / Gaspumpocr
Python and OpenCV scripts to detect digits on a Gas Pump
Stars: ✭ 116
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Gaspumpocr
Spacextract
Extraction and analysis of telemetry from rocket launch webcasts (from SpaceX and RocketLab)
Stars: ✭ 131 (+12.93%)
Mutual labels: opencv, ocr
Scene Text Recognition
Scene text detection and recognition based on Extremal Region(ER)
Stars: ✭ 146 (+25.86%)
Mutual labels: opencv, ocr
Stb Tester
Automated Testing for Set-Top Boxes and Smart TVs
Stars: ✭ 148 (+27.59%)
Mutual labels: opencv, ocr
Scanner
二维码/条码识别、身份证识别、银行卡识别、车牌识别、图片文字识别、黄图识别、驾驶证(驾照)识别
Stars: ✭ 547 (+371.55%)
Mutual labels: opencv, ocr
Ocrtable
Recognize tables and text from scanned images that contain tables. 从包含表格的扫描图片中识别表格和文字
Stars: ✭ 155 (+33.62%)
Mutual labels: opencv, ocr
Cpp Image Analysis
DataCore bot image analysis component
Stars: ✭ 125 (+7.76%)
Mutual labels: opencv, ocr
Simple Ocr Opencv
A simple python OCR engine using opencv
Stars: ✭ 453 (+290.52%)
Mutual labels: opencv, ocr
Handwriting Ocr
OCR software for recognition of handwritten text
Stars: ✭ 411 (+254.31%)
Mutual labels: opencv, ocr
Prlib
Pre-Recognition Library - library with algorithms for improving OCR quality.
Stars: ✭ 18 (-84.48%)
Mutual labels: opencv, ocr
Idmatch
Match faces on id cards with OCR capabilities.
Stars: ✭ 52 (-55.17%)
Mutual labels: opencv, ocr
Tabulo
Table Detection and Extraction Using Deep Learning ( It is built in Python, using Luminoth, TensorFlow<2.0 and Sonnet.)
Stars: ✭ 110 (-5.17%)
Mutual labels: ocr
Text recognition toolbox
text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.
Stars: ✭ 114 (-1.72%)
Mutual labels: ocr
Ios Rubik Solver
An iOS app that detects a 3x3 Rubik's cube, recognizes the color of all cubies, solves it and provides a 3D visualisation of the solving process.
Stars: ✭ 111 (-4.31%)
Mutual labels: opencv
Pythonml
Artificial neural network classes and tools in Python and TensorFlow.
Stars: ✭ 114 (-1.72%)
Mutual labels: ocr
Aadhaar Card Ocr
Extract text information from Aadhaar Card using tesseract-ocr 😎
Stars: ✭ 112 (-3.45%)
Mutual labels: ocr
Gas Pump OCR
Project for attempting to scan pictures of gas pumps and detect the digits in the cost and fuel amount displays. Operating under the assumption that most pumps use a 7 segment digit display.
Dependencies
- Python
- OpenCV
- NumPy
Global Setup
-
brew install python
- Using python 2.7.13 -
brew install opencv3
- Using >= OpenCV 3.2.0 - Install the OpenCV package into the python site packages following the instructions from the above command output
Virtual Env
-
pip install virtualenv
- Install virtualenv if you haven't -
virtualenv GasPumpOCR_Env
- Create virtual env -
source GasPumpOCR_Env/bin/activate
- Activate virtual env -
pip install -r requirements.txt
- Install dependencies - Write/run the code
-
deactivate
- When you are done and want the global python env
virtualenvwrapper
virtualenvwrapper is a nice set of wrappers around virtualenv that make it easier to use
Install and configure virtualenvwrapper
pip install virtualenvwrapper
export WORKON_HOME=$HOME/.virtualenvs
source /usr/local/bin/virtualenvwrapper.sh
Create new env
mkvirtualenv GasPumpOCR_Env
Work on a virtual env
workon GasPumpOCR_Env
Install dependencies
pip install -r requirements.txt
Deactivate
deactivate
Running
- playground.py [file_name] - Used to try out different image manipulation variables, can hardcode an image or pass one in via the command line
-
train_model.py - Used to take a folder organization of confirmed digits and generate a
knn
training file - test_processing.py - Used to run the trained algorithm on a folder of test images to test accuracy, can also be setup to test all the configurations to determine optimal values
- generate_distorted_images.py - Used to take an image or a folder and run a set of image manipulations to create addtional sample images
Screenshot
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].