TY - JOUR
T1 - Traditional food knowledge of Indonesia
T2 - a new high-quality food dataset and automatic recognition system
AU - Wibisono, Ari
AU - Wisesa, Hanif Arief
AU - Rahmadhani, Zulia Putri
AU - Fahira, Puteri Khatya
AU - Mursanto, Petrus
AU - Jatmiko, Wisnu
N1 - Funding Information:
Indonesia has one of the most diverse cultural heritages in the world. The southeast Asian nation has more than 300 unique ethnic groups. As mentioned previously, the cultural identities of these ethnic groups are related to the traditional foods. Owing to the large number of unique ethnic groups in Indonesia, the number of distinct traditional food is also quite large. Despite the rapid urbanization of the country, the dietary preferences of both rural and urban residents still include traditional foods []. However, the dietary preferences of certain small ethnic groups that have moved to megacities such as Jakarta have shifted towards western food []. Recently, several efforts have been concentrated to ensure food security in Indonesia. Ensuring food security is essential to protect the diversity of traditional foods in Indonesia, as the appropriate food systems must be implemented for each region. However, according to a study conducted by the United Nations World Food Program (UN WFP), several regions in Indonesia are still categorized as “chronically food insecure.” One of the listed causes of this problem is that the food supply and availability threaten the food security in Indonesia []. This fact is also supported by an existing work []. In several regions of Indonesia, food is either under or oversupplied. The UN WFP recommends developing a surveillance system to realize food security and satisfy the nutrition requirements in Indonesia.
Publisher Copyright:
© 2020, The Author(s).
PY - 2020/12/1
Y1 - 2020/12/1
N2 - Traditional food knowledge (TFK) is an essential aspect of human life. In terms of sociocultural aspects, TFK is necessary to protect ancestral culture. In terms of health, traditional foods contain better and more natural ingredients compared to the ingredients of processed foods. Considering this background, in this study, data acquisition and automatic food recognition were performed for traditional food in Indonesia. The food images were captured in a professional mini studio. The food image data were captured under the same light intensity, camera settings, and shooting distance from the camera. The parameters were precisely measured and configured with a light intensity meter, adjustable lighting, and a laser distance measurement device. The data of 1644 traditional food images were successfully obtained in the data acquisition process. These images corresponded to 34 types of traditional foods, and 30–50 images were obtained for each type of food. The size of the raw food image data was 53 GB. The data were divided into sets for training, testing, and validation. An automatic recognition system was developed to classify the traditional food of Indonesia. Training was performed using several types of convolutional neural network (CNN) models such as Densenet121, Resnet50, InceptionV3, and Nasnetmobile. The evaluation results indicated that when using a high quality dataset, the automatic recognition system could realize satisfactory area under the receiver operating characteristics (AUROC) and high accuracy, precision, and recall values of more than 0.95.
AB - Traditional food knowledge (TFK) is an essential aspect of human life. In terms of sociocultural aspects, TFK is necessary to protect ancestral culture. In terms of health, traditional foods contain better and more natural ingredients compared to the ingredients of processed foods. Considering this background, in this study, data acquisition and automatic food recognition were performed for traditional food in Indonesia. The food images were captured in a professional mini studio. The food image data were captured under the same light intensity, camera settings, and shooting distance from the camera. The parameters were precisely measured and configured with a light intensity meter, adjustable lighting, and a laser distance measurement device. The data of 1644 traditional food images were successfully obtained in the data acquisition process. These images corresponded to 34 types of traditional foods, and 30–50 images were obtained for each type of food. The size of the raw food image data was 53 GB. The data were divided into sets for training, testing, and validation. An automatic recognition system was developed to classify the traditional food of Indonesia. Training was performed using several types of convolutional neural network (CNN) models such as Densenet121, Resnet50, InceptionV3, and Nasnetmobile. The evaluation results indicated that when using a high quality dataset, the automatic recognition system could realize satisfactory area under the receiver operating characteristics (AUROC) and high accuracy, precision, and recall values of more than 0.95.
KW - Convolutional neural network
KW - Food recognition
KW - High-quality dataset
KW - Traditional food knowledge
UR - http://www.scopus.com/inward/record.url?scp=85089970391&partnerID=8YFLogxK
U2 - 10.1186/s40537-020-00342-5
DO - 10.1186/s40537-020-00342-5
M3 - Article
AN - SCOPUS:85089970391
SN - 2196-1115
VL - 7
JO - Journal of Big Data
JF - Journal of Big Data
IS - 1
M1 - 69
ER -
