I'm an individual freelancer with hands-on skills in Python related operations.
Skills in Python:
# Data extraction from PDF or image using Tesseract/EasyOCR/DocTR/PaddleOCR, opencv, pymupdf etc. Extracted data can be parsed to json, csv, excel etc. Flask app can be developed for OCR GUI.
# Advanced OCR operation, such as- Table extraction, layout detection, invoice/receipt data extraction in json format using hugging face pretrained model.
# OCR GUI development with python Tkinter library which facilitates a dedicated interface for OCR (Specific region based extraction or automatic screen data extraction), openai/gemini or other AI based API integration, Whatsapp API integration for message receiving via Twilio or Meta API.
# Hugging face pretrained model (such as-LayoutLMv3-FUNSD/CORD/DocLayNet) integrated with the Tesseract for extraction of specific key-value pair data correction. Also extracted data can be saved to JSON or CSV format.
# Advanced data analysis, EDA & visualization with Plotly / Dash / folium (map) visual.
Additional:
# I also have skills in Large Language Models (LLM) and Flask / Streamlit web app for OCR operation and additional automation related tasks.