In this paper, we propose a novel and robust fabric defect detection method based on the low-rank representation (LRR) technique. Due to the repeated texture structure we model a defects-free fabric image as a low-rank structure. In addition, because defects, if exist, change only the texture of fabric locally, we model them with a sparse structure. Based on the above idea, we represent a fabric image into the sum of a low-rank matrix which expresses fabric texture and a sparse matrix which expresses defects. Then, the LRR method is applied to obtain the corresponding decomposition. Especially, in order to make better use of low-rank structure characteristics we propose LRREB (low-rank representation based on eigenvalue decomposition and blocked matrix) method to improve LRR. LRREB is implemented by dividing a image into some corresponding blocked matrices to reduce dimensions and applying eigen-value decomposition (EVD) on blocked matrix instead of singular value decomposition (SVD) on original fabric image, which improves the accuracy and efficiency. No training samples are required in our methods. Experimental results show that the proposed fabric defect detection method is feasible, effective, and simple to be employed.

Textile fabric defect detection based on low-rank representation

Matrix singular value decomposition technique is employed for the detection of defects in fabrics. Firstly, a region of interest (ROI) containing the defect is identified by a proposed adaptive partitioning technique – thus reducing the computational duty of operating over the whole image. The ROI portion of fabric image is then divided into small nonoverlapping subimages to further reduce the computational complexity and the average singular values of the subimages are calculated. To remove the interlaced warp–weft grating structure from ROI, which is the global information in the fabric image, selected singular values associated with positive average singular numbers are rejected and the fabric image is reconstructed to yield the image of the defect. Since the resulting image is saturated with noise and some unconnected parts mainly due to dissimilarity of the subimage of the fabric structure, postprocessing is carried out by binarization and edge detection to yield the edge map of the defect. Validity ...

Detection of defects in fabrics using subimage-based singular value decomposition

摘 要 提出了一种基于概率神经网络 (Probabilistic neural networks, PNN) 和DSmT 推理 (Dezert-Smarandache theory) 的飞机图像目标多特征融合识别算法. 针对提取的多个图像特征量, 利用数据融合的思想对来自图像目标各个特征量提供的 信息进行融合处理. 首先, 对图像进行二值化预处理, 并提取 Hu 矩、归一化转动惯量、仿射不变矩、轮廓离散化参数和奇异 值特征 5 个特征量; 其次, 针对 DSmT 理论中信度赋值构造困难的问题, 利用 PNN 网络, 构造目标识别率矩阵, 通过目标识 别率矩阵对证据源进行信度赋值; 然后, 用 DSmT 组合规则在决策级层进行融合, 从而完成对飞机目标的识别; 最后, 在目标 图像小畸变情形下, 将本文提出的图像多特征信息融合方法和单一特征方法进行了对比测试实验, 结果表明本文方法在同等 条件下正确识别率得到了很大提高, 同时达到实时性要求, 而且具有有效拒判能力和目标图像尺寸不敏感性. 即使在大畸变情 况下, 识别率也能达到 89.3%.

/pdf/an-airplane-image-target0s-multi-feature-fusion-recognition-2tmgec765w.pdf

An Airplane Image Target0s Multi-feature Fusion Recognition Method

The upkeep of systems that are designed to operate over long periods of time requires the precise execution of complex sequences of tasks. Such maintenance activities are expensive and require large investments in training costs. We present an approach that leverages Augmented Reality (AR) to guide the completion of such complex task sequences. This system presents real-time system-status and guidance to operators to complete the task sequences. One of the critical requirements in such a system is the ability to annotate objects and artifacts of the physical world when they are viewed in an AR device. Instead of using computationally intensive approaches based on computer vision, our novel approach relies on a CAD model of the engineered system. In our approach, we transform the gaze point of the user in the virtual world to corresponding coordinates in a 3D CAD model. The high-resolution details of in the 3D CAD model allows us to extract and present appropriate annotations. In the future, this approach can be significantly enhanced by designed intelligent methods to automatically generate the AR content necessary to guide the completion of complex task sequences.

Mapping a Virtual View to the Physical World to Guide the Completion of Complex Task Sequences

This paper presents a method for detecting harmful images using an active shape model (ASM) in social network services (SNS). For this purpose, our method first learns the shape of a woman’s breast lines through principal component analysis and alignment, as well as the distribution of the intensity values of the corresponding control points. This method then finds actual breast lines with a learned shape and the pixel distribution. In this paper, to accurately select the initial positions of the ASM, we attempt to extract its parameter values for the scale, rotation, and translation. To obtain this information, we search for the location of the nipple areas and extract the location of the candidate breast lines by radiating in all directions from each nipple position. We then locate the mean shape of the ASM by finding the scale and rotation values with the extracted breast lines. Subsequently, we repeat the matching process of the ASM until saturation is reached. Finally, we determine objectionable images by calculating the average distance between each control point in a converged shape and a candidate breast line.

ASM-Based Objectionable Image Detection in Social Network Services

Singular value decomposition technique is widely employed in feature analysis due to its strong capability of feature expression. Aiming at detection of fabric defects, this paper gives an approach for the fabric defects extraction in an image based on the theories of singular value decomposition, and proposes the corresponding algorithm. Firstly, singular value decomposition is performed on sub-image of the entire image, size of a rectangle window so that the average of singular values of every sub-image is obtained. Then, according to last step the average of singular values of all of sub-image is calculated. Finally the fabric image is segmented by means of a threshold related to the average of singular values and the defects could be detected. By using singular value decomposition, the complexes of operation are reduced, and noise issues of the image may be overcome. Validity and feasibility of this approach is proved through several experiments of fabric defects detection.

Shuyue Chen

Papers

Research on detection of fabric defects based on singular value decomposition