In this paper, we propose a two-step method to recognize multiple-food images by detecting candidate regions with several methods and classifying them with various kinds of features. In the first step, we detect several candidate regions by fusing outputs of several region detectors including Felzenszwalb's deformable part model (DPM) [1], a circle detector and the JSEG region segmentation. In the second step, we apply a feature-fusion-based food recognition method for bounding boxes of the candidate regions with various kinds of visual features including bag-of-features of SIFT and CSIFT with spatial pyramid (SP-BoF), histogram of oriented gradient (HoG), and Gabor texture features. In the experiments, we estimated ten food candidates for multiple-food images in the descending order of the confidence scores. As results, we have achieved the 55.8% classification rate, which improved the baseline result in case of using only DPM by 14.3 points, for a multiple-food image data set. This demonstrates that the proposed two-step method is effective for recognition of multiple-food images.

In this paper, we examined the effectiveness of deep convolutional neural network (DCNN) for food photo recognition task. Food recognition is a kind of fine-grained visual recognition which is relatively harder problem than conventional image recognition. To tackle this problem, we sought the best combination of DCNN-related techniques such as pre-training with the large-scale ImageNet data, fine-tuning and activation features extracted from the pre-trained DCNN. From the experiments, we concluded the fine-tuned DCNN which was pre-trained with 2000 categories in the ImageNet including 1000 food-related categories was the best method, which achieved 78.77% as the top-1 accuracy for UEC-FOOD100 and 67.57% for UEC-FOOD256, both of which were the best results so far. In addition, we applied the food classifier employing the best combination of the DCNN techniques to Twitter photo data. We have achieved the great improvements on food photo mining in terms of both the number of food photos and accuracy. In addition to its high classification accuracy, we found that DCNN was very suitable for large-scale image data, since it takes only 0.03 seconds to classify one food photo with GPU.

We propose a mobile food recognition system the poses of which are estimating calorie and nutritious of foods and recording a user's eating habits. Since all the processes on image recognition performed on a smart-phone, the system does not need to send images to a server and runs on an ordinary smartphone in a real-time way. To recognize food items, a user draws bounding boxes by touching the screen first, and then the system starts food item recognition within the indicated bounding boxes. To recognize them more accurately, we segment each food item region by GrubCut, extract a color histogram and SURF-based bag-of-features, and finally classify it into one of the fifty food categories with linear SVM and fast 2 kernel. In addition, the system estimates the direction of food regions where the higher SVM output score is expected to be obtained, show it as an arrow on the screen in order to ask a user to move a smartphone camera. This recognition process is performed repeatedly about once a second. We implemented this system as an Android smartphone application so as to use multiple CPU cores effectively for real-time recognition. In the experiments, we have achieved the 81.55% classification rate for the top 5 category candidates when the ground-truth bounding boxes are given. In addition, we obtained positive evaluation by user study compared to the food recording system without object recognition.