Abstract

Now a day, people around the world are becoming more sensitive to their diet. Fruits contribute to an essential part of the diet because they are a major source of energy, vitamins, fiber, plant chemicals and nutrients. Fruits are naturally low in fat, sodium & calories and rich in potassium and fiber, vitamin C. The proposed system gives quickly how much calories present in their diet or fruit intake that can be very useful to maintain health without expert dietitian advice. The system will take the images of fruit and using image processing, segmentation and classification it calculates the calorie content in the fruit. This work proposes an algorithm for fruit recognition and its calorie measurement based on the image features such as shape, color and texture. For shape based feature extraction the geometrical region parameters like area, major axis and minor axis are calculated. For color based segmentation the K-Mean Clustering method is used. The gray level co-occurrence matrix (GLCM) is used to calculate different texture features. The user just takes a picture of the fruit image then to recognize the image to detect the type of fruit portion and classify using support vector machine. After classifying the type of the fruit, the calorie of each fruit with generally for 100g are derived using standard calories table. May Zin Oo | Dr. Mya Thandar Kyu"Fruit Classification and Calories Measurement System" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-5 , August 2018, URL: http://www.ijtsrd.com/papers/ijtsrd18296.pdf http://www.ijtsrd.com/other-scientific-research-area/other/18296/fruit-classification-and-calories-measurement-system/may-zin-oo

Authors and Affiliations