"基于CNN与SVM的人脸识别模型研究：特征融合与分类效果分析"

The research paper "A Face Recognition Model Based on CNN and SVM" proposes a novel approach to face recognition by combining the strengths of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) algorithms. In this model, a CNN is constructed and trained to extract feature maps from different depths of the network. These features are then fused together using a weighted fusion technique before being input into an SVM multi-classifier for final classification. The experimental results presented in the research paper demonstrate that the fusion of features significantly enhances the accuracy of the face recognition model, especially when dealing with small sample datasets, face occlusion, and illumination changes. This approach leverages the capabilities of both CNN and SVM, which are known for their effectiveness in image recognition and classification tasks. Overall, the proposed model showcases the power of feature fusion in improving the performance of face recognition systems, making it a promising solution for real-world applications. The integration of CNN and SVM not only enhances accuracy but also demonstrates the potential for further advancements in the field of biometric identification technology. Through this research, the authors provide valuable insights into the fusion of deep learning and machine learning techniques for face recognition, paving the way for more robust and reliable systems in the future. This study published in "Modern Information Technology" (2020, No. 19) contributes to the growing body of knowledge in the field of information technology and serves as a reference for researchers and practitioners in the domain of biometric security.