I would like to extract information from identification cards and forms using Python and OpenCV. The idea is to input an image (jpg, png, etc.), automatically identify the zones/regions where the wanted text is located in the image (ROI), then extract it using OCR and output the results in JSON format. The problem is that the input images are not alway the same size or orientation, so the solution should be scale invariant and can handle rotation. I am looking for a code which I can later easily modify to fit different templates.
Hi !
I have read your project description .I have 2 year experience of Machine Learning .Deep Learning, Computer Vision and Natural Language Processing (NLP). I have worked on the following projects :
- Face Recognition
- Price Predictions
- Stock market Prediction
- Image classifications
- Spam filtering
- Voice Recognition
- Object Detection
- Object Clasification using CNN
- Object Detection using R-CNN, FAST R-CNN,FASTER R-CNN
Tool i use :-
- Python
- opencv
- R
- Matlab
- Numpy/ pandas/matplotlib
- scikit learn
- tensorflow
- keras
- yolo api
- pytorch
Assalam alekum. So its all about text detection and than fetch it as a JSON using OCR , than glad to let you know that i can help you out in this project to be completed.
I had recently made a script to recognize text from the image and than my algorithm was saving that found text into the dataset.
So in your case , i will output the text in Json format , so you use it in your required way.
Lets have detailed talk on this. I promise you will like to work with me.
As i don't focus on money , i focus on sharing the skills.
Thank you.
I work at Infosys ltd. as a python developer. I have worked on various python libraries. I think I would be easily able to complete the requirement.
please consider me for your project
Iam new to this environment, but I have the confidence to solve this using Python and opencv. Since this will be my first project. i will put all my efforts to get it done.
Relevant Skills and Experience
Python opencv
Hello There,
Kindly send me your images. I have code ready for extraction of text from any type of images.
I have worked on bad quality of images too and which also gives clarity.
Hope we will be working together.