Quick image classification method based on deep learning
A technology of deep learning and classification methods, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problems of long training time, difficult training, low classification accuracy, etc., to speed up the classification speed, speed up the network convergence speed, The effect of ensuring classification accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0033] In order to better illustrate the technical solutions of the present invention, the present invention will be further described through an embodiment with reference to the accompanying drawings.
[0034] Reference figure 1 with figure 2 , A fast image classification method based on deep learning, the method includes four processes: deep convolutional neural network construction, data set preprocessing, network training and image classification testing.
[0035] The pictures in this implementation case are divided into 100 categories, and there are 600 pictures in each category. In each type of pictures, 500 pictures are randomly selected for training, and the remaining 100 pictures are used for testing. The image classification process is as figure 1 As shown, its structural framework is as figure 2 As shown, the operation steps include network construction, training process and testing process.
[0036] The fast image classification method includes the following steps:
...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap