Food Recognition and Nutrients Identification for making Healthy Food Choices

Image Processing

Food Recognition System(FRS) plays an important role in today's modern day life. To lead a healthy life system to measure the amount of nutrients contained in food consumed by humans is important to reduce obesity. High calorie intake in the human body has proved harmful leading to several diseases. To identify food items accurately in such systems, image processing is used. Image processing techniques like image segmentation, feature extraction and classification are used for food recognition and nutrients identification. In the proposed work, image segmentation is done using color and shape segmentation which segments the food portion from the background. In the next step, the key features are extracted from segmented portion using Scale-invariant Feature Transform(SIFT). SIFT is used for texture feature extraction. For classification, Artificial Neural Network(ANN) is used which recognizes the food. After recognition, the nutrient fact table is prepared and based on the amount of fat contained in the food identification whether the food is healthy or not is done. Proposed system gives better accuracy in classification using ANN.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.