Use of Image Processing models such as Optical Character Recognition (OCR) to digitalize the process of invoice transactions. Moving towards fully automated invoice processing and extracting data from pdf/jpeg/webcam image into scalable xlsx/csv template. UI deployment using styling scripts.
- Pytesseract
- pdf2image
- OpenCV
- xlsxwriter
- NumPy
- Pandas
- I/O: Loading data in the form of PDF/jpeg/webcam image
- Performing feature extraction using OpenCV's existing algorithms
- Mapping the extracted features into scalable excel templates which are easy to process automatically
The project is a part of ongoing Flipkart Grid 2.0 competition in Software Delevelopment Module