An Automatic Image Annotation Method Based on Attribute Discrimination
An automatic image and image technology, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as automatic image labeling
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.
[0037] The present invention provides an automatic image labeling method based on attribute discrimination, such as figure 1 As shown, aiming at the unsatisfactory overall labeling effect due to unbalanced datasets, an image labeling method based on attribute discrimination is proposed, using the semantic concept of each keyword to construct a locally balanced dataset, and based on this dataset, a A semantic propagation algorithm (Semantic Propagation, SP) that effectively improves the accuracy of low-frequency tag labeling. Finally, combined with the Stacked Auto-Encoder (SAE) model, different annotation processes are selected by discriminating the high and low frequency attributes of the image, which improves the overall image annotation effect. Specific steps are as follows:
[0038] S1: According to each keyword, the training set is...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


