yogeshpvt / deep-learning-based-food-recognition-and-calorie-estimation-for-indian-food-images Goto Github PK

View Code? Open in Web Editor NEW

Transformer based YOLO v5 model for food image localization for 36 distinct food classes and giving better results than the YOLO v7 model

Python 40.86% Jupyter Notebook 58.39% Shell 0.49% Dockerfile 0.26%

deep-learning-based-food-recognition-and-calorie-estimation-for-indian-food-images's Introduction

Deep Learning Based Food Recognition and Calorie Estimation for popular Indian Foods

Summary of Important research papers to embark into this field of research

Paper Title	DOI	Summary
Deep learning in food category recognition	10.1016/j.inffus.2023.101859	Focuses on deep learning for food category recognition.
DeepFood: Food Image Analysis and Dietary Assessment via Deep Model	10.1109/ACCESS.2020.2973625	Introduces DeepFood, a model for food image analysis and dietary assessment using deep learning.
A review on vision-based analysis for automatic dietary assessment	10.1016/j.tifs.2022.02.017	Offers a comprehensive review of vision-based analysis for automatic dietary assessment.
Analysis of Convolutional Neural Networks on Indian food detection and estimation of calories	10.1016/j.matpr.2022.03.122	Analyzes the use of CNNs for Indian food detection and calorie estimation.
Applying Image-Based Food-Recognition Systems on Dietary Assessment, A Systematic Review	10.1093/advances/nmac078	Systematic review of image-based food recognition systems for dietary assessment.
YOLO*C — Adding context improves YOLO performance	10.1016/j.neucom.2023.126655	How adding context enhances YOLO performance.
Small-object detection based on YOLOv5 in autonomous driving systems	10.1016/j.patrec.2023.03.009	Discusses small-object detection using YOLOv5 in autonomous driving systems.
Vision-based food nutrition estimation via RGB-D fusion network	10.1016/j.foodchem.2023.136309	Presents a method for food nutrition estimation using an RGB-D fusion network.
A Novel Ensemble Weight-Assisted Yolov5-Based Deep Learning Technique for the Localization and Detection of Malaria Parasites	10.3390/electronics11233999	Introduces a novel ensemble weight-assisted YOLOv5-based technique for detecting malaria parasites.
An Image Augmentation Method Based on Limited Samples for Object Tracking Based on Mobile Platform	10.3390/s22051967	Proposes an image augmentation method for object tracking on mobile platforms with limited samples.