Project for detection of Alzheimer(a brain disease) using snaps of brain MRI scans with deep learning.

Expect to have a decent enough image classifier but there's a lot to be taken into account rather than only images so if you can incorporate that too it'll be more accurate.

Gather data from online available databases like oasisbrains

Saransh goswami

* Developed a CNN based model using Pytorch that classifies the input CT scan images as Covid infected or as healthy ( not infected ). * Input images are filtered using a GRU Layer for better accuracy. * The accuracy obtained from the proposed CR Net model is 79% which is slightly lesser than that of some of the pre - trained standard models. * The prediction time of proposed model is lesser than that of pre - trained standard models. * The model is lighter and is suitable to use on the web.

NA

Source 1

https://archive.physionet.org/physiobank/database/

Rohit Yadav

1. Applied image processing techniques on CT scan images of lungs to make them apt for training the model. 2. Built a GRU + CNN based model which classifies CT scan images into Covid positive and Covid negative. 3. Obtained an accuracy of 79.375% on COVID_CT dataset containing 746 images. Wrote a report in the format of research paper summarising results.

NA

Source 1 Source 2 Source 3

https://karpathy.github.io/2015/05/21/rnn-effectiveness/

Saurav C Pandey

The project implements Harris corner detection, Canny edge detection and histogram equalisation for enhancement of images.

Clear demarcation of gate and obstacles (Will be trying to implement sea through algorithm if time permits)

Source 1

NA

Shrishti Sharma

Detecting drowsiness of a driver from the facial expressions captured by a camera on the steering wheel, and thereby sounding an alarm

NA

Source 1

NA

Dinesh Easwaravaka

Hand gesture extraction using background elimination followed by recognition through convolutional neural networks.

NA

Source 1 Source 2

NA

Nishant Kumar

A CNN is made to detect if the person in live videostream is wearing a mask or not. Imp Libraries used : Keras, OpenCV

NA

Search GitHub for face mask detection project

Ashrita Agarwal

1. Built a Human Emotion Detector which takes input from live video feed and detects the faces present at each instant and predicts emotions i.e. happiness, fear, sadness, disgust, anger, surprise and neutral. 2. Used the Kaggle FER-2013 dataset. 3. Built and trained a CNN model for emotion detection.

It detects the faces present at each instant and predicts emotions i.e. happiness, fear, sadness, disgust, anger, surprise and neutral.

Source 1

https://github.com/ashuKS29/Human-Emotion-Detector

Ashutosh Kumar Singh

Used pre-trained coco-data set of 80 classes, to detect and further created warning on detection of anomalies. Deep Neural Network module of Open CV and YOLO_v3 algorithm were used for the detection part. The project is designed for the CCTV frame. Whenever there are anomalies get detected in the frame it will save the information's of anomalies with the timestamp and also creates warning by giving the alarm. Most of the time the CCTVs are used at post-event time to check the footage. This project will help in equipping the CCTV as a pre-event tool by creating alarm for suspected objects. Application of this project is vast for invigilation as well as security purposes at various places like exam hall, Jewelry shops, border area etc. Exposure: Learned Python, Open cv, Yolo_v3 object detection algorithm, Convolution Neural Network. Achievement: Got recognition from HOD of Department of Electrical Engineering and awarded by A grade in the exploratory project.

Successfully tested 80 classes of objects on web cam.

Source 1 Source 2

If you want, you can complete all these courses. But if you have less time, complete only the 4th course, i.e., "Convolution Neural Networks." This will help you understand the fundamentals of this project and give a short and theoretical aspect of the project.

Sanjul Kumar Sharma

Built a CNN model that predicts the emotion of the face and deploys it in Android

NA

Source 1

NA

Mobasshir Ali

Using GANs for open-set person re-identification

NA

Source 1

NA

Dhvani Shah

The task is to implement an automatic number plate recognizer in an unconstrained condition that considers occlusion, poor quality of images, and other spatial variations in image data.

Text obtained from images of Number plates

Source 1

NA

Pushker Naresh

Ive attached my github account link , I've done tons of projects so would be hard to put all in form , please see them

.

Source 1 Source 2 Source 3 Source 4

.

Ayush Agarwal