Image type labeling method based on phrase bag model
A technology that includes models and phrases, applied in character and pattern recognition, instruments, computer components, etc., to achieve the effects of eliminating sensitivity, improving discrimination, and high performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach
[0036] The specific embodiment of the present invention is described as follows:
[0037] Step S1: For any image I i , using wavelet-based local feature point detectors to obtain all local feature points P in the image i ={p ij}, j=1, 2, ..., N i , where N i for image I i The number of all local feature points in , in the experiments of the present invention N i It is set to 1000, that is, 1000 local feature points are detected in each image;
[0038] Step S2: For the local feature point p obtained in step S1 ij ,Using local features to describe the sub-scale invariant feature transform (SIFT), describe the texture features of the local area around it, and form a local feature point p ij The vector description f ij , we call f ij is the feature point p ij Corresponding visual words, in the experiment of the present invention, the vector f obtained by SIFT descriptor ij is a 128-dimensional vector;
[0039] Step S3: For the local feature point p obtained in step S1 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 