Edge detection method of color textile texture image oriented to textile industry

Abstract

The invention discloses an edge detection method of a color textile texture image oriented to the textile industry. The method comprises the following steps: computing color differences between an upper half and a lower half, and a left half and a right half of a window within a sliding window by taking a pixel point as a center according to a fact that a human visual system is affected by surrounding adjacent pixel points when observing image colors; taking the color differences as partial derivatives in horizontal direction and vertical direction of the pixel point, wherein, the partial derivatives in the horizontal direction and the vertical direction of three color components of the pixel point form a 3*2 matrix D; computing a maximum characteristic value of the matrix D<T>D and a corresponding characteristic vector, and respectively taking the maximum characteristic value and the corresponding characteristic vector as a gradient size and a gradient direction of the pixel point; and computing and thinning an edge graph of the image according to the gradient size and the gradient direction of the pixel point. The method can resist against the interference of texture noise in the color textile image, improve the edge detection accuracy of an art pattern in the image, and provide basic edge information for further pattern editing and design, thus achieving an automatic tracing function oriented to the textile industry.

Description

technical field [0001] The invention relates to an edge detection method of a color textile texture image facing the textile industry. Background technique [0002] Extracting the edges of artistic patterns in textile printing and dyeing fabrics is an essential early step in pattern editing and design in the textile printing and dyeing industry, but due to the use of color halftone technology in the textile printing and dyeing industry to reduce production costs, the number obtained by scanning textile fabric samples There is uniformly distributed texture noise in the image. Traditional image edge detection methods, such as Sobel operator, Canny operator, LoG (Laplacian of Gaussian) operator, and Susan operator, only consider the distance between two adjacent horizontal or vertical pixels when calculating the image gradient. Differences, and the interference of texture noise will cause color differences between two adjacent pixels in a uniform color area, so many false edge...

AI Technical Summary

Problems solved by technology

[0002] Extracting the edges of artistic patterns in textile printing and dyeing fabrics is an essential early step in pattern editing and design in the textile printing and dyeing industry, but due to the use of color halftone technology in the textile printing and dyeing industry to reduce production costs, the number obtained by scanning textile fabric samples There is uniformly distributed texture noise in the image

Traditional image edge detection methods, such as Sobel operator, Canny operator, LoG (Laplacian of Gaussian) operator, and Susan operator, only consider the distance between two adjacent horizontal or vertical pixels when calculating the image gradient. Differences, and the interference of texture noise will cause color differences between two adjacent pixels in a uniform color area, so many false edges will be detected, confused with the real edges in the image, so that the cloth can be automatically extracted by computer The edges of artistic patterns in the medium become very difficult

Moreover, these traditional operators can only act on grayscale images. For color textile texture images, these traditional edge detection operators act on the brightness component of the input image, losing the correlation between the color components in the image.

Images