Automatic Recognition of Books Based on Machine Learning

The content-based image recognition is a research focus in the field of computer vision. Machine learning especially deep learning has a great potential in the field of image recognition. This paper adopts the support vector machine algorithm and deep learning method convolutional neural network to recognize books in the digital image library and compares their performance. Experiments show that both methods used in this paper realize a fast and efficient image classification and help improve the intelligence of books retrieval.