Target Feature Recognition Based on Wavelet Transform and CNN-SVM

This paper proposes an image feature extraction method based on wavelet transform and CNN-SVM hybrid model. The image signal is filtered and edge-detected by wavelet transform, which is used as the input quantity of the image for hybrid model recognition and analysis, which improves the quality of the input image data. The CNN and SVM are improved in image feature extraction. The CNN-SVM hybrid model is used to extract the features in the image, which greatly improves the recognition classification efficiency. The effectiveness of the method is proved by simulation experiments.