Food detection and volume estimation for nutritional analysis
Komal Dilip Nale1*, Dr.S.O. Rajankar2, Prof. V.B. Baru3, Dr. M.B. Mali4
Research Scholar1 Sinhgad College of Engineering, Vadgaon Bk, Pune
Research Guide2 Sinhgad College of Engineering, Vadgaon Bk, Pune
Research Co-Guide3 Sinhgad College of Engineering, Vadgaon Bk, Pune
Head Of Department4 Sinhgad College of Engineering, Vadgaon Bk, Pune
Mail id: komalnale1@gmail.com1*
Abstract
A healthy lifestyle and the prevention of chronic illnesses like diabetes and obesity depend on the precise calculation of dietary nutrition values, including calories, proteins, and carbs. Automated food recognition and volume estimate from photos is a viable solution to the problems with traditional nutritional assessment approaches, which rely on self-reporting and are prone to mistakes. Real-time nutrition estimate smartphone apps have been made possible by recent developments in machine learning (ML) and deep learning (DL). Techniques for food categorization, segmentation, and volume estimation that are used in automated dietary assessment systems are examined in this paper. Traditional machine learning (ML) techniques like support vector machines and k-nearest neighbors were used in early research, but convolutional neural networks (CNNs) and optimization techniques like fuzzy clustering and evolutionary algorithms are used in more recent studies. Additionally, the research emphasizes the difficulties in food segmentation, the use of picture datasets like Food-101, and the incorporation of depth estimate methods for volume measurement. Automated nutritional assessment systems provide increased accuracy and user engagement with the growing usage of AI-driven models, opening the door to better public health nutrition programs. For thorough nutrition estimate, future studies should concentrate on enhancing segmentation methods, diversifying datasets, and combining multi-modal data sources.
Keywords: Food Detection, Nutritional Analysis, Food Volume Estimation, Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks (CNNs)
