Abstract: Yarn evenness is a key factor in its performance and in the properties of the material produced from the yarn. The presence of defects in a yarn will result in the deterioration in the quality and usability of the yarn. While many methods are available to ascertain the yarn evenness many of them are tedious and dependent on the operator for its results, while others, though less subjective and of high speed, are prohibitively expensive. A machine vision method which uses a cost-effective image capture device and image processing algorithms to process the captured images, generate a diameter variation plot and analyse the same to count the number of thick and thin places in the yarn. The yarn images are continuously captured via an image acquisition system in real time. Software is continuous measure the yarn diameter, then coefficient of variation (CV value) of the diameter is calculated to characterize the yarn diameter irregularity. Deep learning ANN algorithm of Artificial intelligence technique helped to exact identify the edge of yarn for diameter measurement.
Keywords: diameter variation plot, evenness testing, image processing, thick places, thin places, yarn diameter, yarn evenness, deep learning, ANN.
Title: JUTE YARN DIAMETER IRREGULARITY ANALYSIS BASED ON DEEP LEARNING
Author: Sujai Das, M. Bhowmick, T.K. Kundu
International Journal of Engineering Research and Reviews
ISSN 2348-697X (Online)
Research Publish Journals
