Activity Recognition in examination hall to predict unfair means.

Project Title

Activity Recognition in examination hall to predict unfair means.

Project Area of Specialization Artificial IntelligenceProject Summary

In Our project we will be using image processing technique to classify and categorize a person’s activity and on the basis of it forecast whether the person is involved or is going to be involved in unfair or unjust activities in an examination hall.

Human Activity Recognition (HAR) aims to identify the actions carried out by a person given a set of observations of him/herself and the surrounding environment. Recognition can be accomplished by exploiting the information retrieved from various sources such as using environmental or body sensors, video surveillance and also image processing.

           Automatically recognizing human’s physical activities (a.k.a. human activity recognition or HAR) has emerged as a key problem to ubiquitous computing, human-computer interaction and human behaviour analysis.

           Our project is very helpful in achieving true merit. Many organizations, educational institutes and government sectors can ensure and provide capable and truly deserving employees/workforce for their respective institutes.

Project Objectives

Our project is to help improve merit system nationwide. To almost remove unfair activities happening in examination system we are developing this system to detect those cheaters due to which quality of education and merit system gets affected. Our main objectives are,

• to provide an easy way to predict use of unfair means during examination.
• Unusual activities recognition can help to identify suspicious individuals.
• It will help also to learn about deep learning models and their applications

Project Implementation Method

As in our project we will be using pose detection to classify it either as fair or unfair means therefore, we will be considering the following cases:

• Case I

By edge detection we will be sharpening the edges which will help us detect the pose better.

• Case II

We will also consider angle to detect the suspicious turning or bending of a person.

• Case III

Time will also be monitored e.g for how long has a person been in a certain position.

• Case IV

Number of times an activity is occurring will also be recorded.

For our project development we will follow the following steps:

1. We will first collect our Dataset consisting of images to be classified.
2. Preprocessing of data.
3. Apply image processing and relevant techniques to separate the valid and invalid images.
4. Split dataset into Training and Testing data.
5. Applying appropriate Classifying Model for Prediction.
6. Last step is to present our output to the user.

Benefits of the Project

We are going to implement Suspicious Human activity Recognition Surveillance System, which will be useful in detecting and recognizing cheating activities in the examination hall. Human supervisors are error prone, and their efficiency is affected by fatigue, sickness and any other factor. We studied several algorithms of face, hand, eyes, nose detection and recognition for tracking Human in Videos and Other Crowded Scenes. We also study several algorithms of feature extraction, Feature Matching, and Human Activity Recognition to build a fast and also a robust system to detect and recognise cheating activities in the hall

Technical Details of Final Deliverable

Image processing plays a vital role in our project as we are going to classify on the basis of images provided. Edge Detection is the technique we will be using to further identify and filter the relevant data needed.

1. Collecting Dataset

Our dataset will be based on images gathered to be tested.

1. Image Processing

We are going to use python for image processing and classification of images as it provides different techniques for it as well as it can also efficiently provide and implement AI (artificial intelligence) concepts. It should be 2

1. Displaying in Application

In the end for the purpose of proper user interface we are going to connect our processing with an application which will display output to the user.

Final Deliverable of the Project Software SystemCore Industry ITOther Industries IT Core Technology Artificial Intelligence(AI)Other Technologies Artificial Intelligence(AI)Sustainable Development Goals Quality Education, Reduced InequalityRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	70000
Camera	Equipment	2	15000	30000
Mobile	Equipment	2	20000	40000