Indigenous Food Recognition Model Based on Various Convolutional Neural Network Architectures for Gastronomic Tourism Business Analytics

In gastronomic tourism, food is viewed as the central tourist attraction. Specifically, indigenous food is known to represent the expression of local culture and identity. To promote gastronomic tourism, it is critical to have a model for the food business analytics system. This research undertakes an empirical evaluation of recent transfer learning models for deep learning feature extraction for a food recognition model. The VIREO-Food172 Dataset and a newly established Sabah Food Dataset are used to evaluate the food recognition model. Afterwards, the model is implemented into a web application system as an attempt to automate food recognition. In this model, a fully connected layer with 11 and 10 Softmax neurons is used as the classifier for food categories in both datasets. Six pre-trained Convolutional Neural Network (CNN) models are evaluated as the feature extractors to extract essential features from food images. From the evaluation, the research found that the EfficientNet feature extractor-based and CNN classifier achieved the highest classification accuracy of 94.01% on the Sabah Food Dataset and 86.57% on VIREO-Food172 Dataset. EFFNet as a feature representation outperformed Xception in terms of overall performance. However, Xception can be considered despite some accuracy performance drawback if computational speed and memory space usage are more important than performance.

[1]  Thinagaran Perumal,et al.  Multi-resident activity recognition using label combination approach in smart home environment , 2017, 2017 IEEE International Symposium on Consumer Electronics (ISCE).

[2]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[3]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[4]  Kyungha Min,et al.  A Hierarchical deep model for food classification from photographs , 2020 .

[5]  Yuzhen Lu,et al.  Food Image Recognition by Using Convolutional Neural Networks (CNNs) , 2016, ArXiv.

[6]  Farzana Quoquab,et al.  Enhancing the Tourism Operation Success in Sabah Malaysia: a Conceptual Framework , 2018, International Journal of Engineering & Technology.

[7]  Norwati Mustapha,et al.  Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity , 2018, TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES.

[8]  Mantao Wang,et al.  EfficientNet based recognition of maize diseases by leaf image classification , 2020, Journal of Physics: Conference Series.

[9]  N. H. Nasrudin,et al.  A preliminary study on digital image performance to stimulate food taste experience , 2020, Bulletin of Electrical Engineering and Informatics.

[10]  Jamal Ahmad Dargham,et al.  The Effect of Training Data Selection on Face Recognition in Surveillance Application , 2015, DCAI.

[11]  L2MXception: an improved Xception network for classification of peach diseases , 2021, Plant methods.

[12]  Stella Markantonatou,et al.  Deep learning approaches in food recognition , 2020, ArXiv.

[13]  Farashazillah Yahya,et al.  Machine Learning in Dam Water Research: An Overview of Applications and Approaches , 2020, International Journal of Advanced Trends in Computer Science and Engineering.

[14]  Ervin Gubin Moung,et al.  Face Recognition State-of-the-art, Enablers, Challenges and Solutions: A Review , 2020, International Journal of Advanced Trends in Computer Science and Engineering.

[15]  Sigeru Omatu,et al.  Data Fusion for Face Recognition , 2010, DCAI.

[16]  Jamal Ahmad Dargham,et al.  Fusing Facial Features for Face Recognition , 2012, Int. J. Interact. Multim. Artif. Intell..