Unlock instant, AI-driven research and patent intelligence for your innovation.

Texture classifying method based on moment and fractal

A texture classification and fractal technology, applied in the field of image processing, can solve the problems of no objective rules, errors in classification results, etc., and achieve the effect of good robustness and high classification accuracy

Inactive Publication Date: 2006-05-24
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the fractal characteristics of natural images only exist in a limited range, and there are no objective rules for the selection of this range, there may be large errors in the classification results.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Texture classifying method based on moment and fractal
  • Texture classifying method based on moment and fractal
  • Texture classifying method based on moment and fractal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solution of the present invention will be further described in detail below in conjunction with specific embodiments.

[0028] The test images used in the embodiment of the present invention are natural texture images selected from the Brodatz texture image set. figure 1 Shown are six 512×512 pixel natural images: D9 (grass), D15 (grass), D19 (wool), D29 (beach sand), D68 (wood texture), and D84 (raffia fiber) . The whole process is realized as follows:

[0029] 1. Randomly select 40 image blocks of the same size on each image, and then calculate its second-order moment for each image block to form a feature image. Treat the grayscale image as a double variable function f(x, y), calculate its second-order moment (p+q≤2) for each pixel in the image, and calculate it in a smaller window around each pixel. For a given pixel and a finite rectangular window moment, the discrete calculation corresponds to the neighborhood operation of the pixel, which can be ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The method includes steps: selecting image block from original image, calculating its second moment so as to generate characteristic image; estimating fractal dimension of original image block and moment characteristic image; formed characteristic vectors from fractal dimension of original image and six pieces of moment characteristic image are as input to the support vector machine to carry out classification. Comparing with prior art, the invention uses combination of two kinds of characteristics instead of moment characteristic and fractal characteristic utilized solely in current technique. Thus, invention possesses features of high precision of classification and good robustness.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a texture classification method based on moments and fractals. Background technique [0002] The (p+q) moment of the bivariate function f(x, y) about the origin (0, 0) is defined as: [0003] m pq = ∫ - ∞ ∞ ∫ - ∞ ∞ f ( x , y ) x p y q dxdy [0004] If the grayscale image is used as a double-variable function f(x, y), the second-order moment is calculated for each pixel in the image. Since different textures have different moment distributions, a common method is to introduce a nonlinear converte...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/40
Inventor 曹桂涛施鹏飞
Owner SHANGHAI JIAO TONG UNIV