Sign Language Recognition using LSTM and Media Pipe

Food adulteration refers to the practice of deliberately adding substances to food to increase its volume, weight, or to improve its appearance, texture, or flavor; it is a significant issue that affects the health and safety of consumers. With the increasing demand for food, the risk of contamination and the intentional addition of harmful substances has increased. There are several existing methods for detecting food adulteration, including chemical analysis, microscopy, sensory analysis, etc. While these methods are helpful, they can be time-consuming, labor-intensive, and may not provide Real-time results. Using the Internet of Things (IoT), Machine Learning (ML) can significantly enhance the ability to identify food adulteration.Within this Framework, we are propose a solution to detect food adulteration using IoT and machine learning. The system comprises IoT sensors and devices to gather data on various parameters such as color, pH, gas content, etc. The collected data is fed into machine learning algorithms for preprocessing, analysis, and testing. Any anomalies or deviations from the standard patterns are flagged for further investigation. ML algorithms can continuously learn from the collected data, enabling them to enhance their accuracy and effectiveness over time. By implementing this system, we aim to create a Real-time, data- driven approach to detecting food adulteration, ensuring food safety and quality for consumers by creating a warning system.

“…Authors [22,23] applied deep learning concepts in their applications. G.M Rao et al [24] used sign gestures in video to provide visual communications with machine learning.…”

Section: Literature Surveymentioning

confidence: 99%

IoT-Powered Intelligent Framework for Detecting Food Adulteration: A Smart Approach

Gundavarapu,

Bhavita,

Sahithi

et al. 2023

A Real-time Automated System for Object Detection and Facial Recognition

Reddy,

Ramesh,

Praveen

et al. 2023

Object detection, facial recognition, and person identification are important tasks in computer vision with numerous real-life applications. The major goal of the proposed model is to identify people and recognize them in the images. In this paper, we propose a real-time automated system that combines power of both EfficientDet model for object detection and the FaceNet model for facial recognition to detect persons in an input image, recognize their faces, and label them with their corresponding names. The experimental study of the model takes place on COCO dataset and a custom dataset of images of students. This solution can be applied to various scenarios beyond education, such as in security and surveillance, healthcare, transportation, retail, and entertainment etc. The importance of the model lies in its ability to efficiently and accurately perform person identification and recognition in real-time scenarios, which can save time and resources and improve overall efficiency.

An Automated System for Indian Currency Classification and Detection using CNN

Reddy,

G.,

et al. 2023

The visibly disabled frequently experience difficulties with daily tasks that a typical person would take for granted, such as handling financial transactions. Since India’s demonetization took effect, accepting money has become a difficult task. Due to the similar dimensions of new cash banknotes and the fact that some old money banknotes are still in use, India now has two banknotes for every category. Due to the current situation, it is extremely difficult to identify banknotes for those who appear to be weak. The sight and brain are gifts to humans. Detecting things with the same qualities is practically impossible for persons who are sight impaired. In keeping with this, we suggest an automated system that would enable those who are visually impaired to recognize currency through a sound notification from a variety of applications. Therefore, in this quest, we help them locate the currency notes. In this study, we apply different convolution neural network (CNN) models to datasets of Indian banknotes in order to extract deep features and recognize different currencies. To train, verify, and test the CNN model, we can produce a fresh dataset of Indian banknotes. The proposed model may be created with TensorFlow, enhanced by choosing the best hyper parameter value, and evaluated against well-established CNN architectures using transfer learning.