A. N. M. Sajedul Alam
Data Extraction from PDF files of Resume
a) Implemented on 6 different resumes randomly collected from web
b) Used poppler utils for manipulating PDF files and converting them to other formats
c) Used pdf2image and easyocr for converting pdf to image and for optical character recognition
d) Used spacy for doing advanced natural language processing tasks and pillow's imageDraw module for getting simple 2D graphics for image objects
e) Worked only with resumes written in English Language
All the resumes were webscraped randomly from web. Author will not be liable for any future misuse.