Essay On Food Recognition

I. INTRODUCTION

Now a days taking pictures of the food we eat, especially when it is bought readily made has become a habit. This habit could be put to good use if only the images we snap could be used in a beneficial way. One way to do this would be to use the images and try and process the nutritional and the calorific value of the food and give this information to the consumer of the food as a way of ensuring a healthy diet requirements are met by the food on the platter. This could be used for disease prevention and diet control. However most of these services unfortunately require manual selection of the food items from the hierarchical menus that was pre-fed to the system, which makes it time- consuming and inefficient.

We propose a system to perform food recognition using mobile. The main aim of the system is to estimate the nutrition and calorific content of the food by automatically recognizing the food without the need of any intervention from

In this paper, we propose an automatic food image recognition system for 85 food categories by fusing various kinds of image features including bag-of-features (BoF), color histogram, Gabor features and gradient histogram with Multiple Kernel Learning (MKL). In addition, we implemented a prototype system to recognize food images taken by cellular phone cameras. In the experiment, we have achieved the 62.52% classification rate for 85 food categories. Thus the food recognition system is based on the number of categories and employed image features. By integrating seventeen kinds of image features with Multiple Kernel Learning, they obtained the 62.52% classification rate for 85-food-category classification evaluated by five-fold