Recognition of fabric density with quadratic local extremum

Abstract

PurposeThe purpose of this paper is to propose a new recognition algorithm on quadratic local extremum for fabric density recognition.Design/methodology/approachThe density wave is established to correctly detect density by searching local extremes. The gray wave of each line in fabric image is extracted first. The derivation of gray wave is calculated, extreme waves including all true extreme values and false extreme values are obtained. And then the second derivative of extreme waves are calculated and the result makes local correction. The density wave, which can represent position and quantity of yarn and interstice, is established. According to the resolution and size parameters of image, the function of density with density wave statistics is given.FindingsThe experiment and analysis proved that the method proposed can detect fabric density simply and successfully with less calculation and no image preprocessing.Research limitations/implicationsThe algorithm provides practical guidelines for fabric density detection and provides a new thought for fabric characteristic identification. Future work could be focused on the development of methods for the automatic algorithm with color fabrics.Originality/valueThe algorithm based on quadratic local extremum presented in this paper is a new method to successfully detect fabric density and can be applied to the recognition for other categories of clothing fabrics and images.