Automatic Helmet Detection using Machine Learning

This project presents and proposes a mechanism for the automatic detection of bike riders without helmets using surveillance videos. Deep learning algorithms were employed to identify bike riders and analyze visual features to detect helmet usage. A violation reporting system was also introduced to enhance the reliability of the solution.

Food Detection and Recognition Using Convolutional Neural Network

Associated with APJ Abdul Kalam Technological University

Food is an important part of everyday life, and this is clearly reflected in digital spaces, as illustrated by the abundance of food photography on social networks, dedicated photo-sharing sites, and mobile applications. Automatic recognition of dishes would help users effortlessly organize their extensive photo collections and make online photo repositories more accessible.

Nowadays, the number of foreigners visiting our country is increasing. One of the main focuses of these travelers is exploring the local cuisine while enjoying the mesmerizing beauty and culture of our country. It is essential for people to have access to vital information about unfamiliar food they consume.

As a solution to this problem, we propose a food detection and information system using Machine Learning. In this study, we apply a Convolutional Neural Network (CNN) to the tasks of detecting and recognizing food images. Deep learning has recently been shown to be a highly effective technique for image recognition, and CNNs represent a state-of-the-art approach to deep learning.

We utilize CNNs to detect and recognize food images. Given the wide diversity of food types, recognizing food items through image analysis can be highly challenging. To address this, the CNN is trained with an Indian food dataset to accurately recognize food items and provide essential information. This system offers the advantages of understanding the food we eat and mitigating any potential instances of being misled about the food.