Regenerated mixed fine aggregate classification and identification method based on color co-occurrence matrix

• Main Authors: BAI YANPING, LI JIANJUN, ZHANG SHUAI, LIU ZHENXIANG, JIAO YUQIAN
• Format: Patent
• Language: Chinese; English
• Published: 09.07.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a regenerated mixed fine aggregate mixing ratio classification method based on a color co-occurrence matrix, and relates to the field of construction waste resourceful treatment. The method specifically comprises the following steps: processing a regenerated mixed fine aggregate image into a square image, converting the image obtained after processing into an HSV space, and extracting three color components H, S and V to obtain a pseudo grayscale image; randomly dividing the pseudo grayscale image into a training set and a test set; respectively extracting characteristic parameters of second moment, contrast, correlation, inverse different moment, mean sum, entropy, sum variance and difference variance from H, S and V of each image to obtain a feature matrix of each image; inputting the feature matrix into a BP neural network and an SVM for identification, obtaining classification precision, and optimizing a classification result by using a genetic algorithm, a particle swarm algorithm