Computer Vision 2017 exercises

Transfer-Learning with Inception-v3

A virtual assistant device with two features of object recognition and reminder system for an Alzheimer's patient

Community project for developing an app which entails (1) an exhibition recognition AI model and (2) mobile-first website for visually and hearing impared people.

ROS 2 interfaces for Ninshiki object detection package

[ICCV23] Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation

CLI to help create custom classifiers for visual recognition systems

Object Recognition Prototype for Detection of Bell Peppers and Kiwis in Video Data (Deployed on NVIDIA Jetson Nano)

Scene Stitching and Object Recognition

This project implements ResNet50 in keras and applies transfer learning from Imagenet to recognize food. It achieves 77.25% Top1 and 92.90% Top5 testing accuracy after 9 training epochs which takes only 5 hour.

Tag Me was a Machine Learning Contest by IISc Bangalore. Please refer : http://events.csa.iisc.ernet.in/opendays2014/events/MLEvent/index.php

Computer vision pipeline for image processing, image segmentation and classification of 2D puzzle-like tiles.

One-stage and two-stage face detection models

Example of how to get data from SVHN dataset and visualize it.

Identify the virtual object using ray-casting

A collection of 4 CV applications.