No abstract

In this paper, we propose a mobile cooking recipe recommendation system employing object recognition for food ingredients such as vegetables and meats. The proposed system carries out object recognition on food ingredients in a real-time way on an Android-based smartphone, and recommends cooking recipes related to the recognized food ingredients. By only pointing a built-in camera on a mobile device to food ingredients, the user can obtain a recipe list instantly. As an object recognition method, we adopt bagof-features with SURF and color histogram extracted from multiple images as image features and linear SVM with the one-vs-rest strategy as a classifier. We built 30 kinds of food ingredient short video database for experiments. With this database, we achieved the 83.93% recognition rate within the top six candidates. In the experiment, we made user study by comparing mobile recipe recommendation systems with/without ingredient recognition.

The chondroprotective effect of olive leaf extract (OLE) on knee osteoarthritis (OA) was studied with STR/ort mice (n = 5). OLE was administrated with a dosage of 100 mg/kg for 8 weeks and the OA severity score of hind limb knee joints was then measured. The Mankin scores of the knee joints of the non-OA control group, OA control group and OLE-treated group were 3.50, 11.13 and 7.20, respectively. This suggests that oral OLE supplements help prevent cartilage degeneration in STR/ort mice. In vitro, the synthesis of high molecular weight hyaluronan in synovial cells (HIG-82) was increased by OLE stimulation. This suggests that OLE modulates hyaluronan metabolism in synovial cells and improves OA symptoms. Our findings indicate that OLE intake inhibits cartilage destruction by increasing high molecular weight hyaluronan and thus preventing OA progress.

In this paper, we propose a cooking recipe recommendation system which runs on a consumer smartphone as an interactive mobile application. The proposed system employs real-time visual object recognition of food ingredients, and recommends cooking recipes related to the recognized food ingredients. Because of visual recognition, by only pointing a built-in camera on a smartphone to food ingredients, a user can get to know a related cooking recipes instantly. The objective of the proposed system is to assist people who cook to decide a cooking recipe at grocery stores or at a kitchen. In the current implementation, the system can recognize 30 kinds of food ingredient in 0.15 seconds, and it has achieved the 83.93% recognition rate within the top six candidates. By the user study, we confirmed the effectiveness of the proposed system.