Large Scale Learning for Food Image Classification

Abstract

Since health care on foods is drawing people's attention recently, in this paper we propose a computer vision based food recognition system could be used to estimate food for diabetes patients. This study proposes a methodology for automatic food recognition, based on the Bag of Features (BoF) model. We present an approach to find out the group and location of objects in images. The system computes dense local features using scale invariant features. It performs very fast classification of each pixel in an image. For the design and valuation of the proposed system, a image dataset with nearly 5010 food images was created and organized into 11 classes. This system has achieved the accuracy of 78%.of objects in images. The system computes dense local features using scale invariant features. It performs very fast classification of each pixel in an image. For the design and valuation of the proposed system, a image dataset with nearly 5010 food images was created and organized into 11 classes. This system has achieved the accuracy of 78%. DOI: 10.17762/ijritcc2321-8169.150317