A Novel Image Classification Method with CNN-XGBoost Model

作者:Ren, Xudie; Guo, Haonan; Li, Shenghong*; Wang, Shilin; Li, Jianhua
来源:16th International Workshop on Digital Forensics and Watermarking (IWDW), 2017-08-23 To 2017-08-25.
DOI:10.1007/978-3-319-64185-0_28

摘要

Image classification problem is one of most important research directions in image processing and has become the focus of research in many years due to its diversity and complexity of image information. In view of the existing image classification models' failure to fully utilize the information of images, this paper proposes a novel image classification method of combining the Convolutional Neural Network (CNN) and eXtreme Gradient Boosting (XGBoost), which are two outstanding classifiers. The presented CNNXG-Boost model provides more precise output by integrating CNN as a trainable feature extractor to automatically obtain features from input and XGBoost as a recognizer in the top level of the network to produce results. Experiments are implemented on the well-known MNIST and CIFAR-10 databases. The results prove that the new method performs better compared with other methods on the same databases, which verify the effectiveness of the proposed method in image classification problem.