Quantized Deep Residual Convolutional Neural Network for Image-Based Dietary Assessment

Abstract

Vegetable intake is an essential element to maintain a healthy body of a human. However, research shows most people do not consume an adequate intake of vegetables per day. An ameliorate dietary assessment for vegetable intake is needed to increase awareness and assist users to improve their vegetable consumption. In this paper, we proposed a novel Quantized Deep Residual Convolutional Neural Network (DRCNN) model to ameliorate the fundamental task of dietary assessment. The proposed deep learning strategy integrating a deep residual architecture and a deep learning model, i.e. convolutional neural network, to apply for image-based dietary assessment. The proposed DRCNN model is then deeply fused with posttraining quantization techniques to quantize the network weights of the proposed DRCNN model into lowbit fixed-point representations. Extensive experiments have been done to evaluate the proposed model. Results show that the proposed Quantized DRCNN model outperformed the state-of-the-arts, which include the conventional CNN models and also the machine learning models. Those experiments also indicate the effectiveness of the proposed Quantized DRCNN model. Finally, we further evaluate our model with crossdataset validation to verify the generalization of the proposed model. The experimental result proves that the proposed Quantized DRCNN model is general enough to predict unseen cases and it works well on a wide range of food images. INDEX TERMS Convolutional neural network, deep learning, deep residual network, image-based dietary assessment, machine learning, quantized model.

Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors

“…To satisfy these requirements, various network compression studies, such as approximate computing, data quantization, and pruning, have been actively conducted [12]- [31]. Pruning methods reduce the number of parameters by removing unnecessary weights, filters, and layers, resulting in a less-complex network.…”

Harnessing LSTM Classifier to Suggest Nutrition Diet for Cancer Patients

“…The efficiency of the proposed E-LSTM is analyzed by comparing with standard LSTM and existing systems DeepFood [7], Smart-Log [16], CSW-WLIFC (Cauchy, Generalized T-Student, and Wavelet kernel based Wu-and-Li Index Fuzzy Clustering) [34], and Quantized DRCNN (Deep Residual CNN) [35] which are developed for analyzing food nutrients and diets. The following terms are used for efficiency analysis, Precision, Recall, and F1 Score Classification Accuracy Training Loss and Validation Loss.…”

“…In this Smart-Log, only the food is predicted and it will not produce any diet plan. In Quantized DRCNN [35], the deep learning model (CNN) is used to identify only the vegetables in the food images and it will not consider the food nutrition values. In the CSW-WLIFC technique, Whale Levenberg Marquardt Neural Network (WLM-NN) classifier is used for the classification.…”

At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives

“…One of the main reasons for health damage is an unhealthy diet. To tackle the automation of dietary assessment, authors in [ 80 ] proposed a food-recognition model with a deep residual convolutional neural network, which determines whether the food photos include enough vegetables. In order to make predictions on a mobile device without connecting to a cloud server, the authors quantized the network weights of the proposed model by using posttraining quantization methods into low-bit fixed-point representations.…”