Texture classifying method based on phase coincidence
A texture classification and consistent technology, applied in the field of image processing, can solve problems affecting classification results, image texture effects, etc., and achieve good robustness and high classification accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0015] The technical solution of the present invention will be further described in detail below in conjunction with specific embodiments.
[0016] The experimental images used in the embodiments of the present invention are natural images of the Brodatz natural texture set. Whole invention realization process is as follows:
[0017] 1. First select an image block of an appropriate size from the original image. The image blocks of four images: D19 (wool fabric), D29 (beach sand), D68 (wood texture) and D84 (raffia fiber) are as follows figure 1 .(a), (b), (c) and (d) (for the sake of image clarity, take an image block of 128×128 pixels as an example). In the classification experiment, image blocks of 256×256, 128×128, 64×64, 32×32 pixels and 16×16 pixels were selected as experimental images.
[0018] 2. Compute the initial phase-consistent image. The original image block I(x, y) is convolved with the 2Dlog-Gabor filter bank through the following transfer function:
[0019...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 