Fusing Local Shallow Features and Global Deep Features to Identify Beaks

SIMPLE SUMMARY: Cephalopods are not only important economic products in fisheries, but also located in the middle pyramid of the marine ecosystem, playing a role of carrying the top and bottom. Cephalopods are the meals of large marine mammals, and their soft tissues are mostly digested in the stomach, and the beaks can be retained as hard tissues of cephalopods, which are structurally stable and resistant to corrosion. Therefore, the biodiversity of cephalopods can be analyzed by studying the beaks. However, there are many difficulties in the identification of beaks, such as the high level of similarity between different species of beaks and the variability arising from the growth process. The local shallow features, namely texture features and morphological features, and the global deep features were used, and the two types of features were fused for identification. This study verifies the complementarity between the two types of features and further contributes to the progress of beak recognition, providing a new approach to analyzing the biodiversity of cephalopods. ABSTRACT: Cephalopods are an essential component of marine ecosystems, which are of great significance for the development of marine resources, ecological balance, and human food supply. At the same time, the preservation of cephalopod resources and the promotion of sustainable utilization also require attention. Many studies on the classification of cephalopods focus on the analysis of their beaks. In this study, we propose a feature fusion-based method for the identification of beaks, which uses the convolutional neural network (CNN) model as its basic architecture and a multi-class support vector machine (SVM) for classification. First, two local shallow features are extracted, namely the histogram of the orientation gradient (HOG) and the local binary pattern (LBP), and classified using SVM. Second, multiple CNN models were used for end-to-end learning to identify the beaks, and model performance was compared. Finally, the global deep features of beaks were extracted from the Resnet50 model, fused with the two local shallow features, and classified using SVM. The experimental results demonstrate that the feature fusion model can effectively fuse multiple features to recognize beaks and improve classification accuracy. Among them, the HOG+Resnet50 method has the highest accuracy in recognizing the upper and lower beaks, with 91.88% and 93.63%, respectively. Therefore, this new approach facilitated identification studies of cephalopod beaks.