Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model

Abstract

Fabric defect detection is a necessary and essential step of quality control in the textile manufacturing industry. Traditional fabric inspections are usually performed by manual visual methods, which are low in efficiency and poor in precision for long-term industrial applications. In this paper, we propose an unsupervised learning-based automated approach to detect and localize fabric defects without any manual intervention. This approach is used to reconstruct image patches with a convolutional denoising autoencoder network at multiple Gaussian pyramid levels and to synthesize detection results from the corresponding resolution channels. The reconstruction residual of each image patch is used as the indicator for direct pixel-wise prediction. By segmenting and synthesizing the reconstruction residual map at each resolution level, the final inspection result can be generated. This newly developed method has several prominent advantages for fabric defect detection. First, it can be trained with only a small amount of defect-free samples. This is especially important for situations in which collecting large amounts of defective samples is difficult and impracticable. Second, owing to the multi-modal integration strategy, it is relatively more robust and accurate compared to general inspection methods (the results at each resolution level can be viewed as a modality). Third, according to our results, it can address multiple types of textile fabrics, from simple to more complex. Experimental results demonstrate that the proposed model is robust and yields good overall performance with high precision and acceptable recall rates.

Method-Induced Errors in Fractal Analysis of Lung Microscopic Images Segmented with the Use of HistAENN (Histogram-Based Autoencoder Neural Network)

“…During the first phase, HistAENN works as an autoencoder [8,51,52] with input vectors (histograms) and exactly the same output vectors. A bottleneck in the inner part of an autoencoder (FC10 together with RELU10) forces data clustering.…”

A Fast Fabric Defect Detection Framework for Multi-Layer Convolutional Neural Network Based on Histogram Back-Projection

“…On the other hand, after AlexNet [20] was successful in image recognition tasks, some deep learning methods similar to convolutional neural networks (CNN), have set off a research boom in many computer vision tasks. Mei et al [21] train multiple convolutional denoising autoencoder networks with randomly sampled image blocks from defect-free samples, and finally predict the defects by synthesizing multiple pyramid layers. However, in these visual recognition task, most researchers use a network detection model from coarse to fine.…”

An Intelligent Vision System for Detecting Defects in Micro-Armatures for Smartphones

“…With the rapid expansion of network applications, computer vision technology has been successfully applied to the quality inspection of industrial production [1][2][3][4][5][6], including glass products [1], fabrics [2,3], steel surfaces [4], bearing rollers [5], and casting surfaces [6]. The inspection of these mentioned examples needs a matching algorithm to extract image features based on the actual defect situation.…”

“…First, the sample class was determined based on its background texture information, then the image was divided into 49 blocks to figure out which images contain defective regions. For the defects of steel surfaces, an inspection system with a dual lighting structure was proposed to distinguish uneven defects and color changes by surface noise [4]. In a previous study [5], a multi-task convolutional neural network applied to recognize defects was raised.…”