Food Detection and Recognition Using Convolutional Neural Network

Abstract

In this paper, we apply a convolutional neural network (CNN) to the tasks of detecting and recognizing food images. Because of the wide diversity of types of food, image recognition of food items is generally very difficult. However, deep learning has been shown recently to be a very powerful image recognition technique, and CNN is a state-of-the-art approach to deep learning. We applied CNN to the tasks of food detection and recognition through parameter optimization. We constructed a dataset of the most frequent food items in a publicly available food-logging system, and used it to evaluate recognition performance. CNN showed significantly higher accuracy than did traditional support-vectormachine-based methods with handcrafted features. In addition, we found that the convolution kernels show that color dominates the feature extraction process. For food image detection, CNN also showed significantly higher accuracy than a conventional method did.

Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model

“…It has been applied in food classification and resulted in a high accuracy. Kagaya et al [8] applied CNN in food/non-food classification and achieved significant results with a high accuracy of 93.8%. Then, in the work [9], the accuracy of food detection was increased to 99.1%, using a subset of their image dataset.…”

“…Their proposed a new method based on Random Forest outperforms state-of-the-art methods on food recognition. In [8], Kagaya et al also trained CNN for food recognition and the experimental results showed that the CNN outperformed all the other baseline classical approaches by achieving an average accuracy of 73.7% for 10 classes. Kawano et al [19] used CNN as a feature extractor and achieved state-of-the-art best accuracy of 72.3% on the UEC-FOOD-100 [20] dataset, which contains 100 classes of Japanese food.…”

A Comparative Study of Indian Food Image Classification Using K-Nearest-Neighbour and Support-Vector-Machines

“…Marc Bola˜nos and Petia Radeva in [1], proposed a food activation map on the input image for generating bounding boxes proposals and recognize each of the food types. Hokuto Kagaya, Kiyoharu Aizawa and Makoto Ogawa in [16], proposed the tasks of food detection and recognition through parameter optimization and how to construct a dataset of the most frequent food items in a publicly available food-logging system, and used it to evaluate recognition performance. Niki Martinel, Gian Luca Foresti, and Christian Michelon in [17] this paper introduces a new deep scheme that is designed to handle the food structure and also explains about the recent success of residual deep network, introduce a slice convolution block to capture the vertical food layers.…”

Smartphone-Based Food Weight and Calorie Estimation Method for Effective Food Journaling

“…Other studies utilized features extraction techniques such as scale invariant feature transform (SIFT) [28] for food image classification. Kagaya et al proposed a food detection and recognition system using a deep-learning approach called convolutional neural network (CNN) [29]. However in most cases, the accuracy of the classifiers proposed in these study are questionable and/or require further improvements to perform as expected.…”