Rachit R Jindal's Projects
A Deep Learning object detection based web app that removes the background of the images using a Neural Network model. Created on Flask and deployed on Herkou, this app uses a DeepLabV3 Xception model for object detection and image processing techniques to remove the background.
ML (Machine Learning)/NLP project for extraction of Names, Aadhar ID, PAN numbers. It uses Pytesseract OCR for extracting text from images, and uses Hugging Face NER model for Name extraction and regex library for extracting PAN and Aadhaar ID numbers.
Novel Coronavirus 2019 time series data on cases
An interesting deep learning python image classification project for Face Recognition Attendance System using Haar Cascade Classifier. The python libraries include cv2, pillow, os, pickle, etc.
A complete collection of Haar-Cascade files. Every Haar-Cascades here!
This project scrap the job data from Indeed using beautifulsoup library in Python and stores the data in a pandas data frame which can further be converted into any suitable form of file be it csv, xlxs, json etc.
Creating a repository with major algorithms in different languages
A prototype MIS (Management Information System) app deployed using Heroku with full fledged login and encrypted password system developed using Python (Flask)
A short project for gathering the metadata of images and storing the data in a csv file
An interesting python project involving the use of a cv2 module for detecting the motion by using the difference in the frame technique.
Recommendation engines are now a one of the most common Machine Learning project that can be seen now-a-days. In fact, some biggest brands are build around one, like Netflix, Amazon, Google, etc. Thirty-five percent of purchases on Amazon come from product recommendations.
The main objective is to devise an efficient and computationally optimum approach by improving the existing classification model in the field of the Medical World more precisely Dermatology Department for improved diagnosis followed by better medical assistance. Skin diseases are a common problem affecting a lot of people, and lack of proper assistance can lead to chronic problems like acne, vascular lesions, Eczema, etc. With evolving computational performance and algorithms, classification of the disease can be automated and deployed with the live stream using Computer Vision techniques. This project aims toward the classification of 7-types of common pigmented skin lesions using a Neural Network architecture comprising of CNN, Dropout, MaxPooling, and Dense layers and precisely tuned hyper-parameters like Learning Rate, Early stopping, Loss function, etc.
Stackoverflow tag predictor
Product Recommendation Engine Recommendation engines are now a one of the most common Machine Learning project that can be seen now-a-days. In fact, some biggest brands are build around one, like Netflix, Amazon, Google, etc. Thirty-five percent of purchases on Amazon come from product recommendations.
QA (Question-Answering) are machine or deep learning models that can answer questions given some context, and sometimes without any context based on the data already fed into the model. They can extract answer phrases from paragraphs and can even paraphrase the answer generatively.
Reinforcement Learning examples implementation and explanation
An simple yet interesting deep learning forecasting model project for predicting stock prices in real-time. It uses LSTM for pattern learning and better accuracy.
Interesting C++ project using concepts like recursion and backtracking for solving complex puzzle like sudoku.