The detection and recognition of food pictures has become an emerging application field of computer vision. However, due to the small differences between the categories of food pictures and the large differences withi...The detection and recognition of food pictures has become an emerging application field of computer vision. However, due to the small differences between the categories of food pictures and the large differences within the categories, there are problems such as missed inspections and false inspections in the detection and recognition process. Aiming at the existing problems, an <span>improved YOLOv3 model of Asian food detection method is proposed.</span> Firstly, increase the top-down fusion path to form a circular fusion, making full use of shallow and deep features. Secondly, introduce the convolution residual <span>module to replace the ordinary convolution layer to increase the gradient</span> cor<span>relation and non-linearity of the network. Thirdly, introduce the CBAM</span> (Con<span>volutional Block Attention Module) attention mechanism to improve the</span> network’s ability to extract effective features. Finally, CIOU (Complete-IoU) loss is used to improve the convergence efficiency of the model. Experimental results show that the proposed improved model achieves better detection results on the Asian food UECFOOD100 data set.展开更多
文摘The detection and recognition of food pictures has become an emerging application field of computer vision. However, due to the small differences between the categories of food pictures and the large differences within the categories, there are problems such as missed inspections and false inspections in the detection and recognition process. Aiming at the existing problems, an <span>improved YOLOv3 model of Asian food detection method is proposed.</span> Firstly, increase the top-down fusion path to form a circular fusion, making full use of shallow and deep features. Secondly, introduce the convolution residual <span>module to replace the ordinary convolution layer to increase the gradient</span> cor<span>relation and non-linearity of the network. Thirdly, introduce the CBAM</span> (Con<span>volutional Block Attention Module) attention mechanism to improve the</span> network’s ability to extract effective features. Finally, CIOU (Complete-IoU) loss is used to improve the convergence efficiency of the model. Experimental results show that the proposed improved model achieves better detection results on the Asian food UECFOOD100 data set.
