Research Article
Image Recognition Method of Educational Scene Based on Machine Learning
@INPROCEEDINGS{10.1007/978-3-031-18123-8_16, author={Yingjian Kang and Lei Ma}, title={Image Recognition Method of Educational Scene Based on Machine Learning}, proceedings={Multimedia Technology and Enhanced Learning. 4th EAI International Conference, ICMTEL 2022, Virtual Event, April 15-16, 2022, Proceedings}, proceedings_a={ICMTEL}, year={2022}, month={10}, keywords={Machine learning Convolutional neural network Educational scene image Image recognition Image enhancement Feature extraction}, doi={10.1007/978-3-031-18123-8_16} }- Yingjian Kang
Lei Ma
Year: 2022
Image Recognition Method of Educational Scene Based on Machine Learning
ICMTEL
Springer
DOI: 10.1007/978-3-031-18123-8_16
Abstract
The traditional image recognition method mainly relies on the similarity expansion calculation of the prominent features of the image to realize the image recognition. This method not only reduces the recognition accuracy of the image, but also makes the recognition efficiency of the image low due to the complex calculation process. In response to the above problems, this research designed an image recognition method for educational scenes based on machine learning. After performing normalization, denoising, and enhancement preprocessing on the educational scene image, the HOG, SIFT, and Haar features in the image are extracted. Then use the convolutional neural network model in machine learning technology to complete the recognition of educational scene images. Experimental results show that the effective recognition rate of this method is higher than 92%, and compared with traditional methods, the recognition efficiency of this method is significantly improved.
