A hybrid deep CNN model for fast class-incremental food classification / Aymen Taher Ahmed al-Ashwal

Aymen Taher , Ahmed al-Ashwal (2019) A hybrid deep CNN model for fast class-incremental food classification / Aymen Taher Ahmed al-Ashwal. Masters thesis, University of Malaya.

	PDF (The Candidate's Agreement) Restricted to Repository staff only Download (216Kb)
Preview	PDF (Thesis M.A) Download (822Kb) | Preview

Abstract

A hybrid deep CNN model for fast class-incremental food classification / Aymen Taher Ahmed al-AshwaFood recognition can help in identifying calories, which is particularly helpful in reducing risks that are related to inaccurate food consumption. Recent works used deep learning classifiers for food recognition, which does not have enough intelligence to update the increasing number of food classes. It requires retraining the model for new classes or using transfer learning. Retraining the model takes an estimated time of 20 to 45 hours depending on the accuracy achieved by that specific model. Inspired by the recent success and high performance of Densely Connected Convolutional Networks (DenseNet), in this study, a hybrid deep Convolutional Neural Network (CNN) model was introduced. This model has an optimized DenseNet network for features extraction and Adaptive Ball COver for Classification (ABACOC) as an incremental learning classifier. The method employs the intelligence of deep CNN (DenseNet Model) to extract the features after training the model on a wide range of food categories and images. Features are then enhanced by using Tree-based feature selection to reduce the size of each feature and, therefore, enhance classification performance. Lastly, the incremental learning algorithm ABACOC is used to classify each feature of food classes. The main contribution of this study is a classification model that can predict new classes and incrementally over time improve the accuracy of different food classes. By evaluating the model on food dataset FOOD101, extracting of features take 80.23 seconds and classifying and training of incremental algorithm take 1253.36 seconds with 77.72% test accuracy. Moreover, adding new classes or new food images features has no significant consequence on the model knowledge. On the contrary, new samples for existing classes improve their overall accuracy. Such results are not close to the state-ofart in food classification. However, further research should be done to accomplish higher results with incremental learning.

Actions (For repository staff only : Login required)