Abstract: In recent times, advancements in deep learning and computer vision have paved the way for innovative solutions in food detection and nutritional analysis. This paper presents a pioneering framework for detecting food items using ensemble learning techniques, leveraging cutting-edge object detection models like YOLOv7 and YOLOv8. The proposed system aims to precisely identify and categorize various food items in images, catering to diverse user needs such as nutrition research, dietary monitoring, and culinary exploration. The framework initiates by pre-processing food images and inputting them into multiple pre-trained YOLOv7 and YOLOv8 models to extract features and generate decision scores for each detected food item. These decision scores are then combined using a fusion technique, such as the Gompertz function, to amalgamate the strengths of each model and enhance prediction accuracy. To assess the system's performance, experiments are conducted using a comprehensive food image dataset encompassing a wide variety of cuisines and dishes. Performance metrics including accuracy, precision, recall, and F1-score are measured to evaluate the effectiveness of the ensemble approach in accurately detecting and categorizing food items. The proposed framework offers a sturdy and efficient solution for food detection tasks, serving diverse user classes including nutrition researchers, health-conscious individuals, restaurant owners, and culinary enthusiasts. By harnessing ensemble learning techniques and state-of-the-art object detection models, the system aims to empower users with precise and reliable food detection capabilities, facilitating applications such as dietary monitoring, nutrition analysis, and food recognition systems across various domains.
Keywords: YOLOv7 , YOLOv8, Ensemble learning, nutrition monitoring system.
Cite:
Krishnaraj S, Prashanth D, Prasiddhi Nayak, Sathwik Rao K, Jyothi V Prasad," WELLWISE: ADVANCED NUTRITION MONITORING SYSTEM", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133127.
|
DOI:
10.17148/IJARCCE.2024.133127
