Edge Detecting Method for Microscopic Image of Cotton Fiber Cross-Section Using RCF Deep Neural Network

Abstract

Currently, analyzing the microscopic image of cotton fiber cross-section is the most accurate and effective way to measure its grade of maturity and then evaluate the quality of cotton samples. However, existing methods cannot extract the edge of the cross-section intact, which will affect the measurement accuracy of maturity grade. In this paper, a new edge detection algorithm that is based on the RCF convolutional neural network (CNN) is proposed. For the microscopic image dataset of the cotton fiber cross-section constructed in this paper, the original RCF was firstly used to extract the edge of the cotton fiber cross-section in the image. After analyzing the output images of RCF in each convolution stage, the following two conclusions are drawn: (1) the shallow layers contain a lot of important edge information of the cotton fiber cross-section; (2) because the size of the cotton fiber cross-section in the image is relatively small and the receptive field of the convolutional layer gradually increases with the deepening of the number of layers, the edge information detected by the deeper layers becomes increasingly coarse. In view of the above two points, the following improvements are proposed in this paper: (1) modify the network supervision model and loss calculation structure; (2) the dilated convolution in the deeper layers is removed; therefore, the receptive field in the deeper layers is reduced to adapt to the detection of small objects. The experimental results show that the proposed method can effectively improve the accuracy of edge extraction of cotton fiber cross-section.

A weakly supervised learning pipeline for profiled fibre inspection

“…There are two main paradigms for fibre detection: traditional image processing-based methods and deep learning-based methods. Traditional image processing-based methods [17] segmented fibres by its spatial statistical features and could be classified into four types, threshold algorithms [4,18], morphological algorithms [8], region-based algorithms [19,20], and edge detection-based algorithms [21,22]. Most of these methods are proposed to deal with fibre overlapping, adhesion and breakage which are the main challenges for fibre detection.…”

Local Scale-Guided Hierarchical Region Merging and Further Over- and Under-Segmentation Processing for Hybrid Remote Sensing Image Segmentation

“…The function of image segmentation is to divide a remote sensing image into spatially heterogeneous and spectrally homogeneous regions [20,21]. Most existent segmentation methods only consider the boundary information, such as the edge-based method [22][23][24][25], or the spatial information, such as the region-based method [26][27][28][29][30][31][32][33][34]. The edge-based method determines the edge for an image by tracking the pixel values that are discontinuous at different boundary regions [24], but it always tends towards over-segmentation.…”

“…Most existent segmentation methods only consider the boundary information, such as the edge-based method [22][23][24][25], or the spatial information, such as the region-based method [26][27][28][29][30][31][32][33][34]. The edge-based method determines the edge for an image by tracking the pixel values that are discontinuous at different boundary regions [24], but it always tends towards over-segmentation. The region-based method aggregates or merges similar pixels by calculating the similarity between adjacent pixels restricted by some criterion [33], but it is likely to produce an under-segmented result, and is time-consuming with too much iteration calculation.…”

An image processing and machine learning solution to automate Egyptian cotton lint grading

“…18 Each node connects to another and has an associated weight and bias, which stores the learning from the training data. More recently deep learning, which is an ANN with multiple hidden layers that automate feature extraction, has been used to measure cotton maturity, 31 extract Chinese cotton characteristics, 13 and identify foreign fibers in cotton lint. 14 While deep learning can produce highly accurate models, they require a larger volume of training data than traditional ANN models to learn from, which can limit deep learning use.…”

“…Previous studies have evaluated alternative cotton lint measuring systems to replace or supplement manual inspection and HVI measurement systems, which include the following: the colorimeter; 18,19 computer scanner; 20,21 charge-coupled device (CCD) camera; 12–14,22–26 single-lens reflex camera; 27 thermal camera; 28 infrared spectrometry; 29,30 microscope; 31 X-ray scanner; 32 and optical spectrometry. 16,20 A CCD is a digital camera widely used in digital photography and astronomy.…”