A Survey: Nutrivision A Comprehensive System for Real-Time Food Recognition and Nutritional Analysis

  • Unique Paper ID: 168685
  • Volume: 11
  • Issue: 5
  • PageNo: 1686-1691
  • Abstract:
  • This survey paper provides a detailed examination of recent progressions in food recognition systems, with a particular focus on the application of CNNs (CNNs) and other AI-driven learning techniques. We examine key studies that address various aspects of food classification, including dataset diversity, classification precision, and resource efficiency. The paper highlights the challenges encountered by existing systems, such as sensitivity to surrounding conditions and the trade-off between accuracy and complexity, particularly in mobile platforms. We also explore integrated architectures that combine CNNs alongside RNNs (RNNs) and Long Short-Term Memory (LSTM) architectures to improve effectiveness in dynamic settings. Additionally, emerging technologies such as Augmented Reality (AR) and Mixed Reality (MR) are discussed in the context of enhancing user interaction. By synthesizing these contributions, this survey outlines upcoming exploration paths, including the development of more robust datasets, improved pre-processing techniques, and the integration of contextual data to refine classification accuracy. This paper serves as a valuable resource for researchers and practitioners seeking to understand the current landscape of food recognition technologies and their future uses.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 5
  • PageNo: 1686-1691

A Survey: Nutrivision A Comprehensive System for Real-Time Food Recognition and Nutritional Analysis

Related Articles