Accès libre

Research progress of computer vision tasks based on deep learning and SAE network

À propos de cet article

Citez

In recent years, artificial intelligence has gradually become the core driving force of a new round of scientific and technological revolution and industrial transformation, and is exerting a profound impact on all aspects of human life. With the rapid development of Internet big data and high-performance parallel computing, relevant research in computer vision has made significant progress in the past few years, becoming one of the important application branches in the field of artificial intelligence. The exercise of image classification forming part of computer vision tasks involves a large amount of computation, and training based on traditional deep learning (DL) classification models typically involves slow training and low accuracy in many parameters. Thus, in order to solve these problems, an image classification model based on DL and SAE network was proposed. Firstly, the main research of computer vision task-image classification is introduced in detail. Then, the combination framework of deep neural network and SAE network is built. At the same time, the deep neural network was used to carry out convolution operation of the parameters learned by SAE and extract each feature of the image with neurons, so as to improve the training accuracy of the deep neural network. Finally, the traditional deep neural network and SAE network were used for comparative experiment and analysis. Experimental results show that the proposed method has a certain degree of improvement in image classification accuracy compared with traditional deep neural network and SAE network, and the accuracy reaches 97.13%.

eISSN:
2444-8656
Langue:
Anglais
Périodicité:
Volume Open
Sujets de la revue:
Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics