vison-models

Implementing OCR with a local visual model run by ollama.

An automated tool that uses AI vision models to detect smoking scenes in movies and automatically adds appropriate disclaimers, eliminating manual frame-by-frame editing

Awesome AI Reasearch Work

A Website that uses transfomers based Vision Language Model to Identify and Categorizes dark patterns and Irregualtory practices in Websites.

PDF Compliance Checker AI

A PyTorch image classifier using RegNetY and Albumentations on the Fashion MNIST dataset. Trains with TQDM progress, plots loss curves, and supports clean modular design.

Cup Work is an autonomous AI coworker for your desktop. Give it a goal, and it plans, acts, asks for approval when necessary, observes the result, and keeps working until the task is verified.

Image Similarity Search Engine is recreates Google Lens functionalities using a ResNet model. It allows users to find similar images based on a query image by performing feature extraction and similarity search.

Description: Production-grade RAG pipeline for IT helpdesk — hybrid search, confidence-gated responses, OCR support, and streaming APIs.

Robust Content Based Image Retreival which utilizes Vision transformer, Colors, Metadata and User Feedbacks for the images uploaded and to retreive images from the system as per user query, using combination of Boolean model and VSM.