saurabh ghosh's repositories
AlgoCasts-JS
DSA in JavaScript ✅
applied-ml
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
co-learning-lounge
Welcome to the one point community-driven encyclopedia for anything in technology.
cracking-the-data-science-interview
A Collection of Cheatsheets, Books, Questions, and Portfolio For DS/ML Interview Prep
DeckLinkCapture
Video capture program for Blackmagic Design's devices
deep-learning-with-python-notebooks
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
form-segmentation
Let's explore how we can extract text from forms
HackerrankPractice
170+ solutions to Hackerrank.com practice problems using Python 3, С++ and Oracle SQL
meshrcnn
code for Mesh R-CNN, an academic publication, presented at ICCV 2019
notes
Notes On Using Data Science & Artificial Intelligence To Fight For Something That Matters.
OCR-Identity-Cards
To extract details from Indian National Identification Cards such as PAN (completed) & Aadhar, Passport, Driving License (WIP) in a structured format
OCR-Invoice
a console application that would run on Windows server to scan user’s Bill and Receipts, which are either captured by camera or in form of an electronic file like pdf etc. 1. All the invoices/receipts will be uploaded on server in a folder 2. The uploaded invoices/receipts will be scanned by OCR app and extract following information from the file and put them in database table - Vendor/Party Name - Invoice date - Tax amount - Total amount - Line items(Item Name, Item Qty, Item rate, Item Tax & Item Amount) 3. The processing of OCR should be done with 90% of accuracy 4. Application designed be able to handle the noise & quality of the uploaded invoice images.
PAN_OCR
Building OCR using YOLO and Tesseract
practical-statistics-for-data-scientists
Code repository for O'Reilly book
pytorch3d
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
saurabh.github.io
Demo Example page
signature_extractor
A super lightweight image procesing algorithm for extraction of overlapped handwritten signatures on scanned documents using OpenCV and scikit-image.
SincNet
SincNet is a neural architecture for efficiently processing raw audio samples.
Zero-to-Hero-in-NLP
This repository contains A-Z techniques for Natural Language Processing to get started in NLP.