GLCM and PSNR Analysis of Woven Fabric Images Made from Natural Dyes Due to Sunlight Exposure

Abstract

Listen

Translate article

Traditional woven fabrics generally use natural dyes that come from the local area. Natural dyes are often considered low quality if exposed to sunlight. This study aims to analyze the effect of sunlight on the image of woven fabrics made from natural dyes. The natural dyes used come from noni (Morinda citrofolia L), which produces a red color; Tarum (Indigofera tinctoria L), which produces a blue-black color; and corn starch juice, which produces a white color. A thread made of cotton is dipped and cooked to produce the desired color. The analysis is done by comparing the value of GLCM (Grey Lever Co-Coruent Matrix) features, changes in the value of Mean Square Error (MSE), and Peak Signal Noise Ratio (PSNR) with the original image. The original image is taken before the woven fabric is dried in the sun. The changing image is taken after the woven fabric is dried in the sun with variations in drying times. The drying time of woven fabric is 1 hour. Sun drying starts from 09:00 to 14:00. The distance between the original and sun-dried images is 30 cm. The original image and the sun-dried image went through cropping and resizing the image to be the same size. The grayscale image type is used for the GLCM, MSE, and PSNR comparison process. The image size used is 128x128 for woven fabric images with three kinds of colors (white, red, and blue) and 256x256 pixels for images with white color. The results showed that the quality of the images produced at drying hours of 09.00-10.00 to 14.00-15.00 tended to be low, with a significant difference between the original image and the changed image. The lowest point of quality lies in the drying time of 12.00-13.00 and 13.00-14.00. For the GLCM features, the sun-dried image at 14.00-15.00 has a homogeneity value close to the original value. For contrast features, the image dried at 10.00-11.00 has a contrast value that is close to the original image contrast value. This shows the smaller the difference in pixel intensity in the image.