Background Texture Research Articles

Digital Camouflage Pattern Design Based on the Biased Random Walk

Digital camouflage is a common countermeasure against military reconnaissance. In the face of high-tech imaging reconnaissance, battlefield detection means tend to be automated and refined. In order to adapt to the concealment requirements under various environmental backgrounds, combined with the camouflage performance of digital camouflage and its feedback mechanism in camouflage pattern design, this paper proposed a digital camouflage pattern design method based on biased random walk. Firstly, the original background is preprocessed, and the background texture’s direction, corner, step length, and pixel intensity difference are statistically analyzed, and the boundary probability between pixel nodes is estimated. Then, a biased random walk is used to outline the camouflage patches. The edge scatter is enriched according to the density of the patches, and the camouflage patches are filled according to the proportion of the main color of the background. Finally, a digital camouflage pattern is obtained. The quantitative analysis results show that the mean heart rate of the digital camouflage pattern based on multiscene design is at least 31.0% higher than that of the original background segmentation texture, and the standard deviation index of equivalent diameter is increased by 14.9% on average. In addition, the results of simulation camouflage image detection in multiple scenes show that the proposed method can effectively deal with camouflage target detection on the basis of fully retaining the original background texture information and has strong camouflage concealment effect in the scene.

Automatic defect detection of texture surface with an efficient texture removal network

Automated defect inspection of texture surface is still a challenging task in the industrial automation field due to the tremendous changes in the appearance of various surface textures. We present a simple but powerful image transformation network to remove textures and highlight defects at full resolution. The simple full convolution network consists only of 3 × 3 regular convolution and several dilated convolution blocks, which makes it compact and able to capture multi-scale features effectively. To further improve the ability of the network to suppress texture and highlight defects, a polynomial loss function combining perceptual loss, structural similarity loss and image gradient loss is proposed. In addition, a semi-automatic annotation method mainly composed of wavelet transform and relative total variation is designed to generate a data set of image pairs containing the original texture image and the desired texture removal image. We conducted experiments on a milled metal surface defect dataset and an open data set containing various textured backgrounds to evaluate the performance of our method. Compared with other convolutional neural network approaches, the results demonstrate the superiority of the proposed method. The method has been applied to the surface defect online detection system of an aluminum ingot milling production line, which effectively improves the surface inspection efficiency and product quality.

Feature pyramid network with self-guided attention refinement module for crack segmentation

Automated pavement crack segmentation is challenging due to the random shape of cracks, complex background textures and the presence of miscellaneous objects. In this paper, we implemented a Self-Guided Attention Refinement module and incorporated it on top of a Feature Pyramid Network (FPN) to model long-range contextual information. The module uses multi-scale features integrated from different layers in the FPN to refine the features at each layer of the FPN using a self-attention mechanism. The module enables the earlier layers and deeper layers of FPN to suppress noise and increase the crack details, respectively. The proposed network obtains an F1 score of 79.43% and 96.19% on the Crack500 and CFD datasets, respectively. Furthermore, the network also generalizes better than other state-of-the-art methods when tested on uncropped Crack500 and field images using the weights trained on CFD. In addition, ablation tests using the Crack500 dataset are conducted. The Self-Guided Attention Refinement module increases the average F1 score and recall by 0.6% and 0.8% while roughly maintaining the average precision. From the ablation test, the inclusion of the Self-Guided Attention Refinement module allows the network to segment finer and more continuous cracks. Then, the module is incorporated on PANet, DeepLab v3+ and U-Net to verify the improvements made to FPN. The results show that the module improves the F1 score, precision and recall compared to the absence of it. Moreover, the Self-Guided Attention Refinement Module is compared with the Self-Adaptive Sparse Transform Module (SASTM). The results show that the Self-Guided Attention Refinement Module provides a more consistent improvement.

Improved Faster R-CNN Based Surface Defect Detection Algorithm for Plates

Defect recognition plays an important part of panel inspection, and most of the current manual inspection methods are used, but the recognition efficiency and recognition accuracy are low. The Fast-Convolutional Neural Network (Faster R-CNN) algorithm is improved, and a surface defect detection algorithm based on the improved Faster R-CNN is proposed. Firstly, the algorithm improves the bilateral filtering algorithm to smooth the image texture background. Subsequently, a feature pyramid network with a shape-variable convolutional ResNet50 network can be applied to acquire defect semantic feature maps to improve the network's ability to express the features of multiscale defects while solving the difficulty problem of many types of defects and variable shapes. To obtain more accurate defect localization information, the algorithm in this paper uses the Region of Interest Align (ROI Align) algorithm instead of the crude Region of Interest Pooling (ROI Pooling) algorithm. Then, an improved attention region recommendation network is used to improve the focus of the model on plate defects and suppress the features of complex background. Finally, a K-means algorithm is added to cluster the defect data to derive anchor frames that are better adapted to the plate defects. In this paper, a dataset containing 3216 images of surface defects of plate metal is made by acquiring surface defect images from the production site of the plate metal factory, which mainly include various defect types. This dataset is used to train and test the algorithm model of this paper, and the results of detection accuracy and detection speed are compared with those of other algorithms, which prove that the algorithm of this paper can achieve real-time detection of plate defects with high detection accuracy.

CASPPNet: a chained atrous spatial pyramid pooling network for steel defect detection

Automatic machine vision-based defect detection has been successfully applied to many industrial visual inspection applications. However, automatic steel surface defect detection is still a challenging task due to diverse defect categories, low-contrast between defect and complex texture background. To address these challenges, a chained atrous spatial pyramid pooling network (CASPPNet) is proposed for steel surface defect detection. In CASPPNet, chained atrous spatial pyramid pooling is designed to enlarge receptive field and obtain enrich semantic information. An improved global attention feature fusion module is introduced to achieve feature interaction and salience. Moreover, residual boundary refinement block is introduced to get more complete defect boundary. Comparative experimental results verify that our method is superior to the state-of-the-art segmentation methods on public accessible SD-saliency-900 datasets and can meet the requirement of real-time online detection (the detection efficiency is at over 47 FPS on a single GPU).

Adaptive infrared and visible image fusion method by using rolling guidance filter and saliency detection

Infrared and visible images have good complementarity; thus, infrared and visible image fusion methods are extensively used in military, target detection, pattern recognition, and other applications. However, problems such as halo effect, poor background texture, and contrast reduction are encountered in image fusion methods. In addition, when the visible image is disturbed by smoke and high brightness, it will affect the quality of the fused image, making image fusion a challenge. To address these problems, an adaptive image fusion method is proposed in this paper. First, the image decomposition method based on rolling guidance filter and saliency detection (RGFSD) is proposed. Next, the source image is decomposed into three layers by using RGFSD: detail layer, salient layer, and base layer. The detail layer is then fused using the phase congruency strategy. Subsequently, the local entropy and gradient (LEG) method is proposed to simulate the perception of significant information by the human visual system to assign the weights for salient layer fusion. Next, the base layer is fused using the averaging method. Furthermore, an image enhancement method based on rolling guidance filter and contrast-limited adaptive histogram equalization is proposed to enhance the detail and contrast of the fused image. Finally, the proposed method is compared qualitatively and quantitatively with eight fusion methods. The experiment results show that compared with the existing methods, the proposed method can better enhance the contrast and retain details of the source images.

Surface Defect Segmentation and Detection of Printing Roller Based on Improved FT Algorithm

The method based on machine vision is one of the important ways of printing roller defect detection. It has the advantage of intuitively reflecting the surface state of printing roller, but the effect of detecting the position where the surface defect of printing roller is not obvious is not ideal. Aiming at the problems of different printing roller surface defects and large interference of background texture, a printing roller surface defect detection algorithm based on improved frequency tuning significance and threshold segmentation is proposed. Firstly, the nonlocal mean filter method is used to preprocess the image to solve the influence of noise on the image; Then, the saliency map is extracted by converting the lab color space of FT algorithm to HSV color space, normalizing and weighting each eigenvalue respectively; Finally, the salient image is binarized by iterative threshold segmentation to obtain the final defect image. The experimental results show that the accuracy of the algorithm is 97.1%, which is better than other similar algorithms. It can accurately detect the roller image with different size of surface defects and texture background interference, and the comprehensive performance is outstanding.

Magnetic tile crack defect detection based on Contourlet transform and singular value decomposition

ABSTRACT The magnetic tile is a permanent magnet made of ferrite material, which is shaped like a tile and mainly used in permanent magnet motor. The magnetic tile image taken by camera is with dark colour and uneven background brightness and texture, and the contrast between crack defect and background is low. In this paper, a non-destructive testing method based on machine vision technology is proposed for magnetic tile crack defect detection. We propose a new crack defect detection algorithm based on Contourlet transform and singular value decomposition (SVD). The algorithm first adopted Contourlet transform to decompose the original image, and the subband coefficients were decomposed by singular value decomposition, then according to the difference of singular values gradient, the principal singular values which would be set to zero were determined. Finally, the image was reconstructed with the reconstruction coefficients that were modified by inversing SVD, the background texture was eliminated and crack defect was obtained. To verify the effectiveness and superiority of the proposed algorithm, extensive experiments were carried out and compared with the traditional algorithms. Experimental results show that the proposed method can effectively detect crack defect with the accuracy rate of 94.29%, and outperforms traditional methods.

MCW-Net: Single image deraining with multi-level connections and wide regional non-local blocks

A recent line of convolutional neural network-based works has succeeded in capturing rain streaks. However, difficulties in detailed recovery still remain. In this paper, we present a multi-level connection and wide regional non-local block network (MCW-Net) to properly restore the original background textures in rainy images. Unlike existing encoder–decoder-based image deraining models that improve performance with additional branches, MCW-Net improves performance by maximizing information utilization without additional branches through the following two proposed methods. The first method is a multi-level connection that repeatedly connects multi-level features of the encoder network to the decoder network. Multi-level connection encourages the decoding process to use the feature information of all levels. In multi-level connection, channel-wise attention is considered to learn which level of features is important in the decoding process of the current level. The second method is a wide regional non-local block. As rain streaks primarily exhibit a vertical distribution, we divide the grid of the image into horizontally-wide patches and apply a non-local operation to each region to explore the rich rain-free background information. Experimental results on both synthetic and real-world rainy datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art models. Furthermore, the results of the joint deraining and segmentation experiment prove that our model contributes effectively to other vision tasks.

Research on defect detection algorithm of complex texture ceramic tiles based on visual attention mechanism

Aiming at the difficulty of detecting the surface defects of complex texture tiles, a salient target detection method based on the human visual attention mechanism is proposed and used for the detection of tile surface defects. Firstly, the image of ceramic tile surface is pretreated using the single-scale SSR light correction method and bilateral filtering method; Secondly, according to the principle of contrast and high-frequency suppression in the visual attention mechanism, aiming at the "imaging" and "aggregation" characteristics of complex background textures, a detection model based on the visual attention mechanism is established to determine and mark defects.According to the contrast principle and high-frequency suppression principle in visual attention mechanism, feature extraction of ceramic tile surface is carried out. Then, the image color patch weight salient map and image feature fused salient map are obtained, and the two maps are fused according to the image saliency criteria.Finally, the marked ceramic tile defects are determined and marked.Finally the marked ceramic tile defects are obtained. This defect detection algorithm and the other two algorithms are applied to three kinds of randomly selected complex texture ceramic tiles. The experimental results show that compared with other algorithms, our algorithm can achieve a comprehensive detection rate of more than 96% for complex texture ceramic tiles, and can obtain a good effect of ceramic tile defect detection as well.

The effect of textured background and perceived distance on perceived size

The perceived size of an object depends on its spatial context, in addition to its projected image on the retina and perceived distance. However, how these factors interact with each other to affect perceived object size is still not clear. In this study, we manipulated the binocular disparity of images to assess the effect of perceived distance on perceived object size, as well as background element size to assess the effect of context. The perceived target size under different combinations of perceived distance and context was measured with a two-interval forced-choice paradigm, in which one interval contained a standard disk with a textured background while the other contained a comparison disk on a blank background in each trial. The observers were instructed to indicate which interval contained a larger disk. A staircase procedure was used to measure the point of subjective equality for the perceived target size. Our results showed that the perceived target size increased with the perceived distance while decreased with background element size. In addition, context modulated the relationship between the perceived target size and perceived distance. The data can be explained by a computational model that incorporates several size selective channels whose size sensitivity to a stimulus can be modulated by its disparity. The target response of each channel is subjected to the divisive inhibition signal from the size information in the context. The perceived size is determined by the weighted average of the responses of these size channels. This model can explain more than 91% of variability in the averaged data. Thus, while both perceived distance and context can affect the perceived size of an object, they exert the effect through different mechanisms.

MR brain segmentation based on DE-ResUnet combining texture features and background knowledge

The segmentation of the brain Magnetic Resonance (MR) images plays an essential role in neuroimaging research and clinical settings. Currently, deep learning combined with prior knowledge and attention mechanism is intensively implemented to solve the brain tissue segmentation task because of its superior performance. However, there are still two problems: firstly, some prior knowledge is difficult to obtain; secondly, incorrect attention is easy to produce in self-attention mechanism. To address these two issues, a novel dual encoder residual U-Net based on texture features and background knowledge, namely DE-ResUnet, is proposed in this work. In DE-ResUnet, the dual encoders for T1-weighted image and texture features are combined to learn hidden additional information. The introduction of channel attention mechanism (CAM) into two encoder and decoder paths facilitates the model to extract more useful informative features. Moreover, we design a strengthen module to refine the coarse segmentation, which can focus on brain tissue regions guided by background knowledge. We evaluate our proposed method on BrainWeb, OASIS-1 and CANDI datasets. The experimental results show that the proposed DE-ResUnet network achieves the accurate segmentation superior to that of several state-of-the-art methods. We also evaluate DE-ResUnet on the BraTS 2020 dataset and achieve good segmentation results. These experiments demonstrate that DE-ResUnet can not only segment normal brain MR images accurately, but also locate the area of the lesion in abnormal images. Our code is freely available at https://github.com/LiangWUSDU/DE-ResUnet.

Real-world indoor mobility with simulated prosthetic vision: The benefits and feasibility of contour-based scene simplification at different phosphene resolutions.

Neuroprosthetic implants are a promising technology for restoring some form of vision in people with visual impairments via electrical neurostimulation in the visual pathway. Although an artificially generated prosthetic percept is relatively limited compared with normal vision, it may provide some elementary perception of the surroundings, re-enabling daily living functionality. For mobility in particular, various studies have investigated the benefits of visual neuroprosthetics in a simulated prosthetic vision paradigm with varying outcomes. The previous literature suggests that scene simplification via image processing, and particularly contour extraction, may potentially improve the mobility performance in a virtual environment. In the current simulation study with sighted participants, we explore both the theoretically attainable benefits of strict scene simplification in an indoor environment by controlling the environmental complexity, as well as the practically achieved improvement with a deep learning-based surface boundary detection implementation compared with traditional edge detection. A simulated electrode resolution of 26 × 26 was found to provide sufficient information for mobility in a simple environment. Our results suggest that, for a lower number of implanted electrodes, the removal of background textures and within-surface gradients may be beneficial in theory. However, the deep learning-based implementation for surface boundary detection did not improve mobility performance in the current study. Furthermore, our findings indicate that, for a greater number of electrodes, the removal of within-surface gradients and background textures may deteriorate, rather than improve, mobility. Therefore, finding a balanced amount of scene simplification requires a careful tradeoff between informativity and interpretability that may depend on the number of implanted electrodes.

Automatic Defect Identification Method for Magnetic Particle Inspection of Bearing Rings Based on Visual Characteristics and High-Level Features

Fluorescent magnetic particle inspection (MPI) is a conventional non-destructive testing process for railway bearing rings that still needs to be completed manually. Due to the complexity of bearing ring surfaces in inspection, automatic detection for bearing rings based on image processing is difficult to apply. Therefore, we proposed a bearing ring defect identification method based on visual characteristics and high-level features. Inspired by the mechanism of human visual perception, defects can be identified from the complex background conveniently by human eyes. According to the linear structure characteristics and greyscale distribution characteristics of cracks in the acquired images, we introduce the centerline extraction and Gaussian similarity measure to reduce background noise and obtain the crack candidate regions. Then, an improved MobileNetV3 is used to extract high-level features of the candidate regions and determine whether they are defective, which uses a new attention module, Coordinate Attention (CA), to substitute the Squeeze-and-Excitation (SE) attention to improve the performance. The experimental results show that the detection accuracy rate of the proposed method is 96.5%. Compared with traditional methods, the proposed method can efficiently extract crack defects in a complex textured background and shows high-quality performance in recall and precision.

Infrared and visible image fusion based on QNSCT and Guided Filter

Image fusion is the process of fusing multiple images of the same scene to obtain a more informative image for human eye perception. In this paper, a new fusion framework based on Quaternion Non-Subsampled Contourlet Transform (QNSCT) and Guided Filter detail enhancement is designed to address the problems of inconspicuous infrared targets and poor background texture in Infrared and visible image fusion. The proposed method uses the quaternion wavelet transform for the first time instead of the traditional Non-Subsampled Pyramid Filter Bank structure in the Non-Subsampled Contourlet Transform (NSCT). The flexible multi-resolution of quaternion wavelet and the multi-directionality of NSCT are fully utilized to refine the multi-scale decomposition scheme. On the other hand, the coefficient matrix obtained from the proposed QNSCT algorithm is fused using a weight refinement algorithm based on the guided filter. The fusion scheme is divided into four steps. First, the Infrared and visible images are decomposed into multi-directional and multiscale coefficient matrices using QNSCT. The experimental results show that the proposed algorithm not only extracts important visual information from the source image, but also preserves the texture information in the scene better. Meanwhile, the scheme outperforms state-of-the-art methods in both subjective and objective evaluations.

AYOLOv3-Tiny: An improved convolutional neural network architecture for real-time defect detection of PAD light guide plates

Light guide plates (LGPs) are the main component of the backlight unit of liquid crystal display (LCD) devices, and defective LGPs directly affect the display effect of LCDs. In view of the features of portable Android device (PAD) LGP images, such as complex texture background, low contrast, different defect sizes and various defect types and their optical properties, light-spot distribution, defect formation principle and imaging characteristics, this paper proposes an AYOLOv3-Tiny network for the defect detection of LGPs. First, by combining overlapping pooling and the spatial attention mechanism, the overlapping pooling spatial attention module (OSM) is constructed to replace the traditional convolution operation of the YOLOv3-Tiny backbone network. Overlapping pooling can improve the accuracy and prevent overfitting, and the spatial attention mechanism can help the network better extract defect features. Second, a dilated convolution module (DCM) is constructed in the detection branch. The module can expand the receptive field of the convolution kernel and improve the detection ability of large defects by integrating the dilated convolution into the residual network structure. Third, a large number of experiments based on the self-built dataset PAD LGP SDD are carried out. The experimental results show that the mean average precision (mAP) and F1-score of the LGP defect detection system can reach 99.50% and 99.61% respectively, and the detection speed can reach 144 fps. Finally, by testing on the PAD LGP images with defects, it is verified that the proposed network meets the application requirements of high precision and real-time online detection of PAD LGP images.

FR-DETR: End-to-End Flowchart Recognition With Precision and Robustness

As flowchart images become diverse and complex, existing flowchart recognition methods no longer achieve satisfactory recognition accuracy, particularly for images that contain rarely used symbols and texture backgrounds. Existing deep-learning-based object detectors and line segment detectors are promising in recognizing symbols and connecting edges separately. However, using two separate detectors for symbol and edge detection will inevitably cause unnecessary training and inference costs. Moreover, the insufficient volume and diversity of available dataset further limit the overall recognition accuracy. To address these issues, this paper proposes an end-to-end multi-task network FR-DETR (Flowchart Recognition DETection TRansformer) and a new dataset for precise and robust flowchart recognition. FR-DETR comprises a CNN backbone and a shared multi-scale Transformer structure with two prediction heads for symbol detection and edge detection respectively. The multi-scale Transformer encodes and decodes feature maps with different resolutions to jointly detect symbols and edges in a coarse-to-fine refinement process. The coarse stage uses features with low resolution and suggests candidate regions that contain potential targets for the fine stage to produce accurate predictions using features with high resolution. At each stage, every task detects targets using shared features and its respective prediction head. A new dataset is constructed to provide more symbol types and complex backgrounds for network training and evaluation. It contains more than 1000 machine-generated flowchart images, 25K+ symbol instances with nine categories, and 20K+ line segments. The experiments show that FR-DETR achieves an overall precision and recall of 94.0% and 93.1% on the proposed dataset, and 98.7% and 98.1% on the CLEF-IP dataset, respectively, which all outperform the prior methods.

Deep Adversarial Data Augmentation for Fabric Defect Classification With Scarce Defect Data

Fabric defect classification is a crucial and challenging task for fabric production quality guarantee. In recent years, many deep neural network-based methods have been proposed and shown promising performance on this task. However, it would be laborious and time-consuming to collect enough defect images to satisfy high-quality training because that defects are too rare in factories. In this paper, we propose a deep adversarial data augmentation method named DefectTransfer to address the defect data scarcity issue. Since the defect may happen anywhere on the background texture with any size, we consider the position and size of a defect should not be fully linked to the background texture in the network training. Based on this assumption, we design a cut-paste approach to augment the defect images by cutting out defects and pasting them on defect-free images. The defects are randomly transformed with scaling, rotating, and moving before the paste operation. To make the network training more efficient, we further propose an adversarial transformation algorithm that adjusts the pasted defects targeting the weakness of the classification network. The high diversity of the adversarial synthetic defect images forces the network to learn more discriminative category features. Experimental results show that our method can achieve comparable performance with recent fabric defect classification methods with only 1% fabric defect data on the ZJU-Leaper dataset. DefectTransfer also largely surpasses traditional augmentation methods even without manually annotated masks.

Analysis of Chinese Painting Color Teaching Based on Intelligent Image Color Processing Technology in the Network as a Green Environment.

This work was conducted to study the Chinese painting color teaching analysis of intelligent image color processing technology under the network environment. First, the paper preprocesses the obtained color mural images, realizes the automatic recognition and marking of the images with different defect degrees and color fading, and uses denoising and texture background elimination to remove unnecessary background information. Then, according to the characteristic that the repair order of boundary points in the Criminisi algorithm is determined by the size of priority weight, the data items and confidence items are added. Finally, the design uses image processing technology and the loss formula to identify the connecting edge of the color area to be taught, establish the color extraction area, calculate the bit weight of the best color, find out the color extraction position, and synthesize different colors according to the original painting color superposition method. The partial differential equation is used to set the teaching code of color teaching system to realize the teaching of Chinese painting color. The experimental results show that compared with the original teaching system, the designed color teaching system has a stronger ability to recognize the edge of Chinese painting color teaching, and the quality of Chinese painting after teaching is higher. It can be seen that the color teaching system can be applied to the color teaching of Chinese painting.

Anomaly Composition and Decomposition Network for Accurate Visual Inspection of Texture Defects

Texture defect inspection remains challenging due to the extreme variations in various textures and defects. Current unsupervised learning-based texture defect inspection methods cannot simultaneously inspect a wide variety of texture defects because they lack an explicit mechanism to encourage the model to create large anomaly scores for defects. In this study, we propose a novel anomaly composition and decomposition network (ACDN) for accurate inspection of various texture defects. In the proposed ACDN, a Gaussian-sampling-based anomaly composition (GSAC) method is proposed to perform the anomaly composition procedure, which composites a large number of defective images for training. Then, a novel anomaly decomposition network (ADN) is proposed to perform the anomaly decomposition procedure, which decomposes the defective images into texture background images and anomaly images by forcing the intrinsic texture features of abnormal images to share a common distribution with those of defect-free images. Through the GSAC and ADN, ACDN learns not only to accurately reconstruct texture background images to cause large reconstruction errors for defect regions but also accurately segment defects. In the testing phase, a defective image is decomposed into a texture background image and an anomaly image through the trained ADN. The residual image between the defective image and the texture background image is then fused with the anomaly image to obtain the defect inspection result. Extensive experimental results on mainstream texture defect datasets demonstrate that ACDN achieves state-of-the-art texture defect inspection accuracy.