When classifying breeds of dogs, the accuracy of classification significantly affects breed identification and dog research. Using images to classify dog breeds can improve classification efficiency; however, it is increasingly challenging due to the diversities and similarities among dog breeds. Traditional image classification methods primarily rely on extracting simple geometric features, while current convolutional neural networks (CNNs) are capable of learning high-level semantic features. However, the diversity of dog breeds continues to pose a challenge to classification accuracy. To address this, we developed a model that integrates multiple CNNs with a machine learning method, significantly improving the accuracy of dog images classification. We used the Stanford Dog Dataset, combined image features from four CNN models, filtered the features using principal component analysis (PCA) and gray wolf optimization algorithm (GWO), and then classified the features with support vector machine (SVM). The classification accuracy rate reached 95.24% for 120 breeds and 99.34% for 76 selected breeds, respectively, demonstrating a significant improvement over existing methods using the same Stanford Dog Dataset. It is expected that our proposed method will further serve as a fundamental framework for the accurate classification of a wider range of species.
Keywords: Stanford dog dataset; convolutional neural network; dog breed classification; feature selection; multi-network integration; support vector machine.