Neighborhood-preserving cross correlation for automated visual inspection of fine-structured textile fabrics

2011 ◽  
Vol 81 (19) ◽  
pp. 2033-2042 ◽  
Author(s):  
A. S. Tolba
Keyword(s):  
Defect Detection ◽  
Visual Inspection ◽  
Cross Correlation ◽  
Gabor Filter ◽  
Probabilistic Neural Network ◽  
Computational Cost ◽  
Detection Accuracy ◽  
Automated Visual Inspection ◽  
Textile Fabrics ◽  
Discriminant Power

The automated visual inspection of homogeneous flat surface products is a challenging task that needs fast and accurate algorithms for defect detection and classification in real time. Multi-directional and Multi-scale approaches, such as Gabor Filter Banks and Wavelets, have high computational cost in addition to their average performance in defect characterization. This paper presents a novel implementation of a neighborhood-preserving approach for the fast and accurate inspection of fine-structured industrial products using a new neighborhood-preserving cross-correlation feature vector. The fast and noise immune Probabilistic Neural Network (PNN) classifier has been found to be very suitable for defect detection in homogeneous non-patterned surfaces with acceptable slight variations, such as textile fabrics. A defect detection accuracy of 99.87% has been achieved with 99.29% recall/sensitivity and 99.91% specificity. The discriminant power shows how well the PNN classifier discriminates between normal and abnormal surfaces. The experimental results show that the proposed system outperforms the Gabor function-based techniques.

scholarly journals Analysis of texture features for wood defect classification

2020 ◽  
Vol 9 (1) ◽  
pp. 121-128
Author(s):  
Nur Dalila Abdullah ◽  
Ummi Raba'ah Hashim ◽  
Sabrina Ahmad ◽  
Lizawati Salahuddin
Keyword(s):  
Classification Accuracy ◽  
Visual Inspection ◽  
Visual Analysis ◽  
Computational Cost ◽  
Texture Features ◽  
Feature Analysis ◽  
Defect Classification ◽  
Grey Level ◽  
Automated Visual Inspection ◽  
Accuracy Measures

Selecting important features in classifying wood defects remains a challenging issue to the automated visual inspection domain. This study aims to address the extraction and analysis of features based on statistical texture on images of wood defects. A series of procedures including feature extraction using the Grey Level Dependence Matrix (GLDM) and feature analysis were executed in order to investigate the appropriate displacement and quantisation parameters that could significantly classify wood defects. Samples were taken from the KembangSemangkuk (KSK), Meranti and Merbau wood species. Findings from visual analysis and classification accuracy measures suggest that the feature set with the displacement parameter, d=2, and quantisation level, q=128, shows the highest classification accuracy. However, to achieve less computational cost, the feature set with quantisation level, q=32, shows acceptable performance in terms of classification accuracy.

Layerwise Automated Visual Inspection in Laser Powder-Bed Additive Manufacturing

2015 ◽  
Author(s):  
Masoumeh Aminzadeh ◽  
Thomas Kurfess
Keyword(s):  
Additive Manufacturing ◽  
Defect Detection ◽  
Visual Inspection ◽  
Object Segmentation ◽  
Detection System ◽  
Automated Visual Inspection ◽  
Powder Bed ◽  
Geometric Objects ◽  
Powder Fusion

Laser powder-bed fusion (L-PBF) is an additive manufacturing (AM) process that enables fabrication of functional metal parts with near-net-shape geometries. The drawback to L-PBF is its lack of precision as well as the formation of defects due to process randomness and irregularities associated with laser powder fusion. Over the past two decades much research has been conducted to control laser powder fusion in order to provide parts of higher quality. This paper addresses online quality monitoring in AM by in-situ automated visual inspection of each layer which is aimed to geometric objects and defects from high-resolution visual images. A scheme for online defect detection system is presented that consists of three levels of processing: low-level, intermediate-level, and high-level processing. Each level is described and appropriately divided to several stages, when insightful. Techniques that are feasible in each level for successful defect detection and classification are identified and described. Requirements and specifications of the measurement data to achieve desired performance of the online defect detection system are stated. Image processing algorithms are developed for first level of processing and implemented for segmentation of geometric objects. Due to the large variation of intensities within the powder region and fused regions, and also the non-multi-modal nature of the image, the basic segmentation algorithms such as thresholding do not produce appropriate results. In this work, morphological operations are effectively designed and implemented following thresholding to achieve the desired object segmentation. Examples of implementations are given. The paper provides the results of object segmentation which is the initial stage of development of an in-situ automated visual inspection for L-PBF process.

Supervised defect detection on textile fabrics via optimal Gabor filter

2013 ◽  
Vol 44 (1) ◽  
pp. 40-57 ◽  
Author(s):  
Junfeng Jing ◽  
Panpan Yang ◽  
Pengfei Li ◽  
Xuejuan Kang
Keyword(s):  
Defect Detection ◽  
Gabor Filter ◽  
Textile Fabrics

Automated visual inspection of fabric image using deep learning approach for defect detection

2021 ◽  
Author(s):  
Vyacheslav V. Voronin ◽  
Roman Sizyakin ◽  
Marina Zhdanova ◽  
Evgenii A. Semenishchev ◽  
Dmitry Bezuglov ◽  
...  
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Visual Inspection ◽  
Learning Approach ◽  
Automated Visual Inspection

Image Processing for Fault Detection in Aluminum Castings

2019 ◽  
Author(s):  
Domingo Mery ◽  
Dieter Filbert ◽  
Thomas Jaeger
Keyword(s):  
Image Processing ◽  
Fault Detection ◽  
Digital Image Processing ◽  
Defect Detection ◽  
Digital Image ◽  
Visual Inspection ◽  
Automated Visual Inspection ◽  
X Ray ◽  
Aluminum Castings

In this article, a review of the use of image processing as a tool in the automated visual inspection of aluminum castings is provided. Methodologies and principles are outlined. This discussion includes detained overviews of: digital image processing in x-ray testing and defect detection in castings.

scholarly journals Efficient Binarized Convolutional Layers for Visual Inspection Applications on Resource-Limited FPGAs and ASICs

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1511
Author(s):  
Taylor Simons ◽  
Dah-Jye Lee
Keyword(s):  
Neural Networks ◽  
Visual Inspection ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Quality Inspection ◽  
Agricultural Produce ◽  
Resource Limited ◽  
Inspection Tasks ◽  
Computational Resources ◽  
Small Models

There has been a recent surge in publications related to binarized neural networks (BNNs), which use binary values to represent both the weights and activations in deep neural networks (DNNs). Due to the bitwise nature of BNNs, there have been many efforts to implement BNNs on ASICs and FPGAs. While BNNs are excellent candidates for these kinds of resource-limited systems, most implementations still require very large FPGAs or CPU-FPGA co-processing systems. Our work focuses on reducing the computational cost of BNNs even further, making them more efficient to implement on FPGAs. We target embedded visual inspection tasks, like quality inspection sorting on manufactured parts and agricultural produce sorting. We propose a new binarized convolutional layer, called the neural jet features layer, that learns well-known classic computer vision kernels that are efficient to calculate as a group. We show that on visual inspection tasks, neural jet features perform comparably to standard BNN convolutional layers while using less computational resources. We also show that neural jet features tend to be more stable than BNN convolution layers when training small models.

Improved SSD-assisted algorithm for surface defect detection of electromagnetic luminescence

2021 ◽  
pp. 1748006X2199538
Author(s):  
Zhenying Xu ◽  
Ziqian Wu ◽  
Wei Fan
Keyword(s):  
Defect Detection ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Detection Methods ◽  
Small Scale ◽  
Detection Accuracy ◽  
Single Shot ◽  
Surface Defect Detection ◽  
Feature Pyramid ◽  
Small Feature

Defect detection of electromagnetic luminescence (EL) cells is the core step in the production and preparation of solar cell modules to ensure conversion efficiency and long service life of batteries. However, due to the lack of feature extraction capability for small feature defects, the traditional single shot multibox detector (SSD) algorithm performs not well in EL defect detection with high accuracy. Consequently, an improved SSD algorithm with modification in feature fusion in the framework of deep learning is proposed to improve the recognition rate of EL multi-class defects. A dataset containing images with four different types of defects through rotation, denoising, and binarization is established for the EL. The proposed algorithm can greatly improve the detection accuracy of the small-scale defect with the idea of feature pyramid networks. An experimental study on the detection of the EL defects shows the effectiveness of the proposed algorithm. Moreover, a comparison study shows the proposed method outperforms other traditional detection methods, such as the SIFT, Faster R-CNN, and YOLOv3, in detecting the EL defect.

Sign in / Sign up

Export Citation Format

Share Document