Food-image recognition plays a pivotal role in intelligent nutrition management, and lightweight recognition methods based on deep learning are crucial for enabling mobile deployment. This capability empowers individuals to effectively manage their daily diet and nutrition using devices such as smartphones. In this study, we propose an Efficient Hybrid Food Recognition Net (EHFR–Net), a novel neural network that integrates Convolutional Neural Networks (CNN) and Vision Transformer (ViT). We find that in the context of food-image recognition tasks, while ViT demonstrates superiority in extracting global information, its approach of disregarding the initial spatial information hampers its efficacy. Therefore, we designed a ViT method termed Location-Preserving Vision Transformer (LP–ViT), which retains positional information during the global information extraction process. To ensure the lightweight nature of the model, we employ an inverted residual block on the CNN side to extract local features. Global and local features are seamlessly integrated by directly summing and concatenating the outputs from the convolutional and ViT structures, resulting in the creation of a unified Hybrid Block (HBlock) in a coherent manner. Moreover, we optimize the hierarchical layout of EHFR–Net to accommodate the unique characteristics of HBlock, effectively reducing the model size. Our extensive experiments on three well-known food image-recognition datasets demonstrate the superiority of our approach. For instance, on the ETHZ Food–101 dataset, our method achieves an outstanding recognition accuracy of 90.7%, which is 3.5% higher than the state-of-the-art ViT-based lightweight network MobileViTv2 (87.2%), which has an equivalent number of parameters and calculations.

Consumer behaviors and habits in food choices impact their physical health and have implications for climate change and global warming. Efficient food image recognition can assist individuals in making more environmentally friendly and healthier dietary choices using end devices, such as smartphones. Simultaneously, it can enhance the efficiency of server-side training, thereby reducing carbon emissions. We propose a lightweight deep neural network named Global Shuffle Net (GSNet) that can efficiently recognize food images. In GSNet, we develop a novel convolution method called global shuffle convolution, which captures the dependence between long-range pixels. Merging global shuffle convolution with classic local convolution yields a framework that works as the backbone of GSNet. Through GSNet's ability to capture the dependence between long-range pixels at the start of the network, by restricting the number of layers in the middle and rear, the parameters and floating operation operations (FLOPs) can be minimized without compromising the performance, thus permitting a lightweight goal to be achieved. Experimental results on four popular food recognition datasets demonstrate that our approach achieves state-of-the-art performance with higher accuracy and fewer FLOPs and parameters. For example, in comparison to the current state-of-the-art model of MobileViTv2, GSNet achieved 87.9% accuracy of the top-1 level on the Eidgenössische Technische Hochschule Zürich (ETHZ) Food-101 dataset with 28% reduction in the parameters, 37% reduction in the FLOPs, but a 0.7% more accuracy.

Food image recognition has recently been given considerable attention in the multimedia field in light of its possible implications on health. The characteristics of the dispersed distribution of ingredients in food images put forward higher requirements on the long-range information extraction ability of neural networks, leading to more complex and deeper models. Nevertheless, the lightweight version of food image recognition is essential for improved implementation on end devices and sustained server-side expansion. To address this issue, we present Aggregation Feature Net (AFNet), a lightweight network that is capable of effectively capturing both global and local features from food images. In AFNet, we develop a novel convolution based on a residual model by encoding global features through row-wise and column-wise information integration. Merging aggregation block with classic local convolution yields a framework that works as the backbone of the network. Based on the efficient use of parameters by the aggregation block, we constructed a lightweight food image recognition network with fewer layers and a smaller scale, assisted by a new type of activation function. Experimental results on four popular food recognition datasets demonstrate that our approach achieves state-of-the-art performance with higher accuracy and fewer FLOPs and parameters. For example, in comparison to the current state-of-the-art model of MobileViTv2, AFNet achieved 88.4% accuracy of the top-1 level on the ETHZ Food-101 dataset, with similar parameters and FLOPs but 1.4% more accuracy. The source code will be provided in supplementary materials.