Search

Different types of paper and different basis weight of the same paper are selected in order to study the relationship between paper and color reproduction. Comparing with the reference data set, the influence of paper on color reproduction is analyzed from the color difference and color gamut. The results show that the colorimetric value of paper is more closer to the reference data set, the average color difference of patches is more smaller. The color reproduction ability of offset paper is weaker than that of other paper in the experiment. The color reproduction ability of different basis weight of the same paper is also slightly different. Therefore, the type and basis weight of the paper affect the color reproduction. In the process of printing proofs, it is considered that paper has a certain impact on color reproduction.

In this paper a new method is proposed for intelligent sort of battery from waste paper based on Invariant Moments and Fractal Dimension (IMFD). In IMFD, a new distinctive feature that based on the edge contours is extracted to describe the target picture. At first invariant moments technique is used to extract Hus seven moments as the global descriptors from the target image. Then the fractal dimensions are extracted as local invariant descriptors by using Fractal Dimension. At last, a combing descriptor is built according the distinctive feature, which combines the global descriptor and the local descriptor together. The features are highly distinctive, and can be matched with high probability against a large database of features. The practical tests performed in this article show that the proposed method has a significant effect on increasing the stability, the accuracy of classification, and also can effectively against the huge-information during the image processing.

International audience; This paper investigates the classification of photographic paper tex-tures using visual descriptors. Such classification is called fine grain due to the very low inter-class variability. We propose a novel image representation for photographic paper texture categorization, relying on the incorporation of a powerful local descriptor into an efficient higher-order model deviation where texture is represented by com-puting statistics on the occurrences of specific local visual patterns. We perform an evaluation on two different challenging datasets of photographic paper textures and show such advanced methods in-deed outperforms existing descriptors.

In this paper, we achieved the floating 3D image based on integral photography theory to display the image in an oblique viewing angle on portable device. Considering the repeated image overlapping problem in the integral image system, it can be solved by adjusting the receiving angle. In the future, the floating 3D image could integrate with the 3D interactive system to provide more realistic visual experience.

This paper proposed an improved method based on adaptive with threshold wavelet transform denoising, according to image is often affected by noise pollution in the process of acquisition and transmission, compared with the advantages and disadvantages of traditional digital filtering method. It extracts the structure information and details of the image. It can adaptively select wavelet transform of optimal decomposition level and soft threshold to achieve the optimal noise reduction effect. The Simulation results demonstrate that this theory can effectively filter Gaussian noise and Salt and pepper noise, at the same time well protect the image details and achieve better visual effects.

In order to consummate the management of bank paper, a new algorithm which can recognize the areas of paper tape in bundle of paper money is presented. Image segmentation is used to divide the image into several sub-blocks. Specifically, image entropy is computed in each sub-block. Experimental in different algorithms, including color training algorithm and the median filter and edge detection algorithm, demonstrates its real-time, effectiveness and robustness.

Paper, as an important substrate of printed matter, the performance will impact on the color reproduction. Brightness, as a key index of paper performance, affects the apparent color of paper directly. It was investigated that the printed samples with different brightness have been evaluated the influence of paper brightness on color reproduction by the methods of subjective and objective color difference evaluation. Three kinds of paper with different brightness have been selected as substrate of printed samples. The standard test color blocks have been printed to do corresponding objective color difference evaluation to different paper by CIEDE2000 color-difference formulae methods. Meanwhile, the standard test images with difference contents have been printed on three kinds of paper, which was subjected to subjective color difference evaluation for visual evaluation of standard test images in standard observe conditions. The results of subjective and objective color difference evaluation have been combined to analyze the effect of paper brightness to color reproduction, and different visual influence to images of difference content, and could provide certain reference for selecting the brightness performance of paper in color reproduction.

In this paper, we describe the development of a system for evaluating an specific quality characteristic of recycled paper sheets using techniques of image analysis and pattern recognition. We call Bumpiness the phenomenon of interest, which is new in the literature on paper quality. This phenomenon is characterized by the appearance of macroscopic undulations on the paper sheet surface that may emerge shortly or some time after its production. We explore the detection and measurement of this defect by means of computer vision and statistical pattern recognition techniques that may allow early detection at the production site. Our goal is to give an scalar continuous measure of Bumpiness. We propose features computed from Gabor filter banks (GFB) and discrete wavelet transforms (DWT) for the characterization of paper sheet surface Bumpiness in recycled paper images. The starting point is to state the problem as a classification of the paper sheet images into two classes: low and high Bumpiness. In this setting we obtain, with both proposed texture modelling approaches (GFB and DWT), classification accuracies comparable to the agreement between human observers. The best performance is obtained using DWT features. Finally, we propose as the scalar index of Bumpines the fisher discriminant analysis (FDA) function defined on the space of the best features for the classification task. We perform an innovative validation process of this Bumpiness index, based on the ordering of random pairs of images, obtaining a very high agreement with the human observers.

This paper puts across the various approaches and methods that have been proposed in the context of Fuzzy Mathematical Morphology. The underlying principles of Dilation & Erosion, the structuring elements used in various techniques, the unique variations put forth by researchers, new applications in spatial relationships, decision making, segmentation of medical images have been discussed.

Stripes are important features for scrap paper images mosaics. The stripe feature extraction can directly affect the effect of mosaics. A method of stripe feature extraction from scrap paper images is proposed in this paper. In order to obtain the background binary image, the original scrap paper images are firstly carried out by close operation and binarization. Secondly, the single pixel edges are extracted by using edge detection operator. Finally, the crossing points of stripes and the boundary of the background are detected by using the Progressive Probabilistic Hough Transformation. The length, angle and direction features of stripes are also extracted during this process. The experimental results show that the method of stripe feature extraction proposed in this paper is reasonable. By using this method the stripe features can be extracted from scrap paper images quickly and correctly. It provides features for the subsequent image mosaics.

We deal with the 3D reconstruction of deformed paperlike surfaces given a template and a single perspective image, for which the internal camera parameters are known. The general problem is ill-posed. We show that when the surface rulings are parallel the problem is well-posed. Given a procedure to recover the rulings direction, this particular problem is equivalent to the reconstruction of a 2D curve seen from a set of ID camera pairs given a ID template. Paper can be physically modeled by exploiting local properties. This allows us to formulate the reconstruction problem by non linear variational optimization. We provide experimental results which validate our approach on simulated and real data.

Wavelet moment features of image can reflect the image's part and whole characteristics and have strong anti-jamming ability. We use wavelet moments extracted from Paper-cut patterns to get multi-scale features. Combined with the paper-cut images' characteristics, the different mean and standard deviation of eigenvector are used to compute resolution and produce N class model feature selection. Finally, the eigenvectors are sent to nearest neighbor classifier for recognition. Experiments show that this method is effective in distinguishing paper cut-cut patterns with noise contamination or geometric deformation.

Protecting data transmitted over the Internet has become a critical issue driven by the progress in data digitalization and communications networking over the past decade. The content being transmitted can be in the form of images, text and voice. To ensure that transmitted data are secure and cannot be tampered with or noticed by malicious attackers, several approaches have been proposed. Steganography is one general approach among them. The hiding capacity and image quality of stego-images are two major measures with which to evaluate an image hiding scheme. To enhance the hiding capacity of Fridrich et al.'s scheme, an improved image hiding scheme for grayscale images based on wet paper coding is proposed in this paper. The significant difference between Fridrich et al.'s scheme and ours is that we shuffle all the pixels in the host image by adopting toral automorphism, then segment all pixels before using our proposed wet pixel hiding strategies to hide the data. Experimental results show that our proposed scheme embeds a larger-sized secret image while maintaining acceptable image quality of the stego-image better than Fridrich et al.'s scheme does. Moreover, the computational cost of our proposed scheme is significantly less than that of Fridrich et al.'s scheme because inverse matrix and multiplication operations are not required. Therefore, our proposed scheme is suitable for real time applications.

Annotation watermarking (sometimes also called caption or illustration watermarking) denotes a specific application of watermarks, which embeds supplementary information directly in the media, so that additional information is intrinsically linked to media content and does not get separated from the media by non-malicious processing steps such as image cropping or compression. Recently, nested object annotation watermarking (NOAWM) has been introduced as a specialized annotation watermarking domain, whereby hierarchical object information is embedded in photographic images. In earlier work, the Hierarchical Graph Concept (HGC) has been suggested as a first approach to model object relations, which are defined by users during editing processes, into a hierarchical tree structure. The original HGC method uses a code-book decomposition of the annotation tree and a block-luminance algorithm for embedding. In this article, two new approaches for embedding nested object annotations are presented and experimentally compared to the original HGC approach. The first one adopts the code-book scheme of HGC using an alternative embedding based on Wet Paper Codes in blue-channel LSB domain, whereas the second suggests a new method based on the concept of intrinsic signal inheritance by sub-band energy and phase modulation of image luminance blocks. A comparative experimental evaluation based on more than 100 test images is presented in the paper, whereby aspects of transparency and robustness with respect to the most relevant image modifications to annotations, cropping and JPEG compression, are discussed comparatively for the two code-book schemes and the novel inheritance approach.

Most computer graphics researchers would agree that the pixel is the fundamental atomic element of imaging. But what is a pixel? The simple notion of a hardware displayable pixel becomes far more complex when it is examined more closely. Early 2D windowing systems considered a pixel to be a little square. A more enlightened signal processing approach thinks of a pixel as a point sample of a continuous function. Many signal processing problems occur since physical pixels can only have positive values. Hardware pixels are usually given with 8 bits of resolution. But the precise translation of these bit patterns into physical intensities is often not specified. More careful treatment of intensity encoding takes into consideration gamma correction and dithering, as well as the intensity sensitivity of the human eye. Color pixels are generally thought to have Red, Green and Blue components. A closer examination leads to the concept of a pixel as some projection of a full spectral distribution that must take into account the response of the eye and the physics of the display emitters. In addition, some modern displays, like LCD panels, have a predictable geometric offset between the color emitters. This has implications on the proper spatial filtering of an image in addition to any color matching problems. Compositing and blending images leads to the creation of a fourth channel, called alpha, to represent an amount of geometric coverage. The exact meaning of this transparency channel has also been a subject of debate. Furthermore, the traditional single alpha channel is often used to represent colored object transparency. This is another approximation to a more accurate approach that progresses through usage of three alpha channels per pixel to, ultimately, a whole spectral distribution for transmission as well as emission. Finally, there are reasons to specify still more quantities, such as depth information, on a pixel-by-pixel basis. Ultimatly, like the blind men and the elephant, a pixel means different things to different people. In fact, when we consider the proper handling of color, geometry and transparency we realize that an ordinary hardware pixel is simply a bad image compression technique.

The goal of this work is the fully-automated detection of cellulose fibre cross sections in microtomy images. A lack of significant appearance information makes edges the only reliable cue for detection. We present a novel and highly discriminative edge fragment descriptor that represents angular relations between fragment points. We train a Random Forest with a plurality of these descriptors including their respective center votes. In such a way, the Random Forest exploits the knowledge about the object centroid for detection using a generalized Hough voting scheme. In the experiments we found that our method is able to robustly detect fibre cross sections in microtomy images and can therefore serve as initialization for successive fibre segmentation or tracking algorithms.

Smoothly bent paper-like surfaces are developable. They are however difficult to minimally parameterize since the number of meaningful parameters is intrinsically dependent on the actual deformation. Previous generative models are either incomplete, i.e. limited to subsets of developable surfaces, or depend on huge parameter sets. We propose a generative model governed by a quasi-minimal set of intuitive parameters, namely rules and angles. More precisely, a flat mesh is bent along guiding rules, while a number of extra rules controls the level of smoothness. The generated surface is guaranteed to be developable. A fully automatic multi-camera three dimensional reconstruction algorithm, including model-based bundle-adjustment, demonstrates our model on real images.

Image retrieval is generally implemented by image matching or based-regions retrieval, but itpsilas difficult to balance retrieval performance and complexity. Query images may appear with different scales and rotations in different images, so a hierarchical image segmentation is proposed to partition the retrieved images into equal blocks with different sizes at different levels. Then, the similar metrics of these sub-blocks to query image, are evaluated to retrieve those sub-blocks with contents in query images. Meanwhile, information about scales and locations of query objects in retrieved images can also be returned. The hierarchical block image retrieval schemes with geometric invariants, normalized histograms and their combinations are tested by experiments via a database with 500 images, respectively. The retrieval accuracy with geometric invariants as invariant features can achieve 78% for the optimal similar metric threshold. Furthermore, the scheme can also work with different size images.

In this paper “wobulation” is presented. Wobulation is a cost-effective method of increasing the resolution of digital projection systems without changing the spatial light modulator (SLM). Multiple sub-frames of data are generated from each frame of image data. An optical image shifting mechanism displaces the projected image of each sub-frame by a fraction of a pixel. The sub-frames are projected in rapid succession, thereby appearing as if they were projected simultaneously and superimposed. The resulting image has significantly higher resolution than images produced by unwobulated systems having the same number of SLM pixels.

Focus cues specify inappropriate 3d scene parameters in conventional displays because the light comes from a single surface, independent of the depth relations in the portrayed scene. We examine the efficacy of a stereo-display prototype designed to minimize these problems by using multiple image planes to present near-correct focus cues. Each eye's view is the sum of several images presented at different focal distances. Variation in focal distance is provided by either multiple beam splitters or by use of a switchable lens. The stimulus to accommodation is more consistent with the portrayed depth than with conventional displays. Compared to a normal, fixed-distance display, observers show improved stereoscopic performance in different psychophysical tasks including speed of fusing stereoscopic images. The multiple image-planes approach provides a practical solution for some shortcomings of conventional displays.

This paper provides a methodology which bridges the gap between a simple color-difference metric and a full spatio-chromatic vision model to predict color differences. Because luminance and chromatic visual channels differ greatly in their spatial sensitivities, more than a single number is needed for specific applications—e.g., performance of softcopy displays. On the other hand, a full vision model implies dependence on the displayed images as well as on the display device, and may be impractical to implement. The compromise proposed here is to adopt in certain cases two color-difference metrics, one for luminance and the other for chrominance. Because chromatic coordinates are not luminance-independent in uniform color spaces such as CIELAB, the endpoints of the color difference are made isoluminous prior to transformation to a uniform-color space.

A reflection-type integral imaging scheme for displaying three-dimensional images and its modifications are proposed. A concave mirror array instead of a lens array is adopted for the image integration. Its feasibility is demonstrated by basic experiments.

We have developed a new scaling technique, which we call “Advanced Scaling with Preserving Extracted Contour's Transition (ASPECT)”. When an image is expanded, it generally lose uniformity and become blurred. ASPECT change the scaling ratio at the contour of an image so that it can maintain sharpness of the expanded image. Thus the technology can create a crisp expanded image without producing artifacts caused by non-uniformity or overshooting.

It is shown that when two images are registered by cross-correlating one image with a functional of the other image the minimum registration error variance results when the operation performed cofresponds to that of matched filtering.

This paper based on the concept of function interpolation, a functional network interpolation mechanism was analyzed, the equivalent between functional network and kernel functions based SVM, and the equivalent relationship between functional networks with SVM is demonstrated. This result provides us a very useful guideline when we perform theoretical research and applications on design SVM, functional network systems.

RST invarian watermarking scheme is proposed in this paper based on the SIFT feature points and improved pseudo-Zernike moment. Firstly, feature points are detected using SIFT, and some suitable points are selected to form localized feature regions which are scaled to a standard sized. After computing these regions by the improved pseudo-Zernike moments of these regions , the digital watermark are embedded into the host image by quantizing some low-lever moments. Experimental results show this scheme is robust against the rotation, shearing, JPEG compression, noise and filtering attack.

Face verification technology is widely used in the fields of public safety, e-commerce and so on. Due its characteristic of insensitive to the varied illumination, a new method about face verification with illumination invariant is presented in this paper based on gabor wavelet. First, ATICR method is used to do light preprocessing on images. Second, certain gabor wavelet filters, which are selected on the experiment inducing different gagor wavelet filter has not the same effect in verification, are used to extract feature of the image, of which the dimension in succession is reduced by Principal Component Analysis. At last, SVM classifiers are modeled on the data with reduced dimension. The experiment results in IFACE database and NIRFACE database indicate the algorithm named “Selected Paralleled Gabor Method” can achieves higher verification performance and better adaptability to the variable illumination.

The research of 3D shape matching starts to get more attention recently. In this short paper, we present a 3D shape matching framework. First, we give a general definition of similarity value of two objects. Then, an algorithm is proposed consisting of Principal Component Analysis (PCA), voxelization, and iterative coarse-to-fine aligning of two objects using multi-resolution volume representation. This process will align two objects to have the maximum overlap. Then, we can compute the similarity value for shape matching. The experiment results show the effectiveness of our framework.

China is gradually transitioning from the “tunnel construction era” to the “tunnel maintenance era,” and more and more operating tunnels need to be inspected for diseases. With the continuous development of computer vision, the automatic identification of tunnel lining cracks with computers has gradually been applied in engineering. On the basis of summarizing the weaknesses and strengths of previous studies, this paper first uses the improved multiscale Retinex algorithm to filter the collected tunnel crack images and introduces the eight-direction Sobel edge detection operator to extract the edges of the cracks. Perform mathematical morphological operations on the image after edge extraction, and use the principle of the smallest enclosing rectangle to remove the isolated points of the image. Finally, the performance of the algorithm is judged by the objective evaluation index of the image, the accuracy of crack recognition, and the running time of the algorithm. The image filtering algorithm proposed in this paper can better preserve the edges of the image while enhancing the image. The objective evaluation indexes of the image have been improved significantly, and the main body of the crack can be accurately identified. The overall crack recognition accuracy rate can reach 97.5%, which is higher than the existing tunnel lining crack recognition algorithm, and the average calculation time for each image is shorter. This algorithm has high research significance and engineering application value.

Sea ice disasters are already one of the most serious marine disasters in the Bohai Sea region of our country, which have seriously affected the coastal economic development and residents’ lives. Sea ice classification is an important part of sea ice detection. Hyperspectral imagery and multispectral imagery contain rich spectral information and spatial information and provide important data support for sea ice classification. At present, most sea ice classification methods mainly focus on shallow learning based on spectral features, and the good performance of the deep learning method in remote sensing image classification provides a new idea for sea ice classification. However, the level of deep learning is limited due to the influence of input size in sea ice image classification, and the deep features in the image cannot be fully mined, which affects the further improvement of sea ice classification accuracy. Therefore, this paper proposes an image classification method based on multilevel feature fusion using residual network. First, the PCA method is used to extract the first principal component of the original image, and the residual network is used to deepen the number of network layers. The FPN, PAN, and SPP modules increase the mining between layer and layer features and merge the features between different layers to further improve the accuracy of sea ice classification. In order to verify the effectiveness of the method in this paper, sea ice classification experiments were performed on the hyperspectral image of Bohai Bay in 2008 and the multispectral image of Bohai Bay in 2020. The experimental results show that compared with the algorithm with fewer layers of deep learning network, the method proposed in this paper utilizes the idea of residual network to deepen the number of network layers and carries out multilevel feature fusion through FPN, PAN, and SPP modules, which effectively solves the problem of insufficient deep feature extraction and obtains better classification performance.

Microscope vision analysis is applied in many fields. The traditional way is to use the human eye to observe and manually focus to obtain the image of the observed object. However, with the observation object becoming more and more subtle, the magnification of the microscope is required to be larger and larger. The method of manual focusing cannot guarantee the best focusing position of the microscope in use. Therefore, in this paper, we are studying the existing autofocusing technology and the autofocusing method of microscope based on image processing, which is different from the traditional manual focusing method. The autofocusing method of microscope based on image processing does not need the information such as the target position and the focal length of optical system, to directly focus the collected image. First of all, in order to solve the problem of large computation and difficult real time of traditional wavelet based image sharpness evaluation algorithm, this paper proposes an improved wavelet based image sharpness evaluation algorithm; secondly, in view of the situation that the window selected by traditional focusing window selection method is fixed, this paper adopts an adaptive focusing window selection method to increase the focusing window. Finally, this paper studies the extremum search strategy. In order to avoid the interference of the local extremum in the focusing curve, this paper proposes an improved hill-climbing algorithm to achieve the accuracy of focusing search. The simulation results show that the improved wavelet transform image definition evaluation algorithm can improve the definition evaluation performance, and the improved mountain climbing algorithm can reduce the impact of local extremum and improve the accuracy of the search algorithm. All in all, it can be concluded that the method based on image processing proposed in this paper has a good focusing effect, which can meet the needs of anti-interference and extreme value search of microscope autofocus.

The Radon transform is a major integral transform in computed tomography and a widely applied technique in computer vision and image analysis which is used to detect linear structures and regular textures. Its application is based on the property of the integrals of the direct problem to accumulate the image brightness along the contours under study. The back-projection operation, one of the main components of tomographic algorithms, results in ridge functions having the directions in which they participated in the direct operator. In the present paper, we examine the ridge functions and their orientation as the features for describing the anisotropy of regular textures. These features are involved in the regular texture model as a sum of ridge functions. Many textures are visually perceived as a superposition of linear structures and are therefore examined using the Radon transform. The paper presents a computational scheme for the singular value decomposition of a regular texture into a sum of informative ridge functions. The results are given of numerical experiments with the textures of industrial fabrics. The algorithm can be used in processing the visual data in computer vision systems, textile industry, robotics, and crystallography.

Sports video is loved by the audience because of its unique charm, so it has high research value and application value to analyze and study the video data of competition. Based on the background of football match, this paper studies the football detection and tracking algorithm in football game video and analyzes the real-time image of real-time mobile devices in sports video augmented reality. Firstly, the image is preprocessed by image graying, image denoising, image binarization, and so on. Secondly, Hough transform is used to locate and detect football, and according to the characteristics of football, Hough transform is improved. Based on the good performance of SIFT algorithm in feature matching, a football tracking algorithm based on SIFT feature matching is proposed, which matches the detected football with the sample football. The simulation results show that the improved Hough transform can effectively detect football and has good antijamming performance. And the designed football tracking algorithm based on SIFT feature matching can accurately track the football trajectory; therefore, the football detection and tracking algorithm designed in this paper is suitable for real-time football monitoring and tracking.

With the advancements of computer technology, image recognition technology has been more and more widely applied and feature extraction is a core problem of image recognition. In study, image recognition classifies the processed image and identifies the category it belongs to. By selecting the feature to be extracted, it measures the necessary parameters and classifies according to the result. For better recognition, it needs to conduct structural analysis and image description of the entire image and enhance image understanding through multi-object structural relationship. The essence of Radon transform is to reconstruct the original N-dimensional image in N-dimensional space according to the N-1 dimensional projection data of N-dimensional image in different directions. The Radon transform of image is to extract the feature in the transform domain and map the image space to the parameter space. This paper study the inverse problem of Radon transform of the upper semicircular curve with compact support and continuous in the support. When the center and radius of a circular curve change in a certain range, the inversion problem is unique when the Radon transform along the upper semicircle curve is known. In order to further improve the robustness and discrimination of the features extracted, given the image translation or proportional scaling and the removal of impact caused by translation and proportion, this paper has proposed an image similarity invariant feature extraction method based on Radon transform, constructed Radon moment invariant and shown the description capacity of shape feature extraction method on shape feature by getting intra-class ratio. The experiment result has shown that the method of this paper has overcome the flaws of cracks, overlapping, fuzziness and fake edges which exist when extracting features alone, it can accurately extract the corners of the digital image and has good robustness to noise. It has effectively improved the accuracy and continuity of complex image feature extraction.

The quantity of information in images can be evaluated by means of the Shannon entropy. When dealing with natural images with a large scale of gray levels, as well as with images containing textures or suffering some degradation such as noise or blurring, this measure tends to saturate. That is, it reaches high values due to a large amount of irrelevant information, making it useless for measuring significant information. In this paper we present a new information measure, the clustered entropy. This information measure, based on clustering local histograms, has a zero value for quasi-homogeneous regions and reaches high values for regions containing edges. The clustered entropy is used in this paper as an edge detector, by centering a sliding window on every pixel of an image, and calculating the clustered entropy of the corresponding histogram. A search for local maxima throughout the resulting matrix of entropies provides the final image of edges. The mathematical properties of clustered entropy are studied, a comparison between the clustered and the normal entropy is done, and some comparative experiments of edge detection are shown in this paper.

Insufficient and poor lightning conditions affect the quality of videos and images captured by the camcorders. The low quality images decrease the performances of computer vision systems in smart traffic, video surveillance, and other imaging systems applications. In this paper, combined gray level transformation technique is proposed to enhance the less quality of illuminated images. This technique is composed of log transformation, power law transformation and adaptive histogram equalization process to improve the low light illumination image estimated using HIS color model. Finally, the enhanced illumination image is blended with original reflectance image to get enhanced color image. This paper shows that the proposed algorithm on various weakly illuminated images is enhanced better and has taken reduced computation time than previous image processing techniques.

Exoskeleton robot is a typical application to assist the motion of lower limbs. To make the lower extremity exoskeleton more flexible, it is necessary to identify various motion intentions of the lower limbs of the human body. Although more sEMG sensors can be used to identify more lower limb motion intention, with the increase in the number of sensors, more and more data need to be processed. In the process of human motion, the collected sEMG signal is easy to be interfered with noise. To improve the practicality of the lower extremity exoskeleton robot, this paper proposed a wavelet packet transform- (WPT-) based sliding window difference average filtering feature extract algorithm and the unscented Kalman neural network (UKFNN) recognition algorithm. We established an sEMG energy feature model, using a sliding window difference average filtering method to suppress noise interference and extracted stable feature values and using UKF filtering to optimize the neural network weights to improve the adaptability and accuracy of the recognition model. In this paper, we collected the sEMG signals of three muscles to identify six lower limb motion intentions. The average accuracy of 94.83% is proposed in this paper. Experiments show that the algorithm improves the accuracy and anti-interference of motion intention recognition of lower limb sEMG signals. The algorithm is superior to the backpropagation neural network (BPNN) recognition algorithm in the lower limb motion intention recognition and proves the effectiveness, novelty, and reliability of the method in this paper.

Fatigue driving is one of the main factors which affect the safety of drivers and passengers in mountain freeway. To improve the driving safety, the application of fatigue driving detection system is a crucial measure. Accuracy, speed and robustness are key performances of fatigue detection system. However, most researches pay attention to one of them, instead of taking care of them all. It has limitation in practical application. This paper proposes a novel three-layered framework, named Real-time and Robust Detection System. Specifically, the framework includes three modules, called facial feature extraction, eyes regions extraction and fatigue detection. In the facial feature extraction module, the paper designs a deep cascaded convolutional neural network to detect the face and locate eye key points. Then, a face tracking sub-module is constructed to increase the speed of the algorithm, and a face validation submodule is applied to improve the stability of detection. Furthermore, to ensure the orderly operation of each sub-module, we designed a recognition loop based on the finite state machine. It can extract facial feature of the driver. In the second module, eyes regions of the driver were captured according to the geometric feature of face and eyes. In the fatigue detection module, the ellipse fitting method is applied to obtain the shape of driver's pupils. According to the relationship between the long and short axes of the ellipse, eyes state (opening or closed) can be decided. Lastly, the PERCLOS, which is defined by calculating the number of closed eyes in a period, is used to determine whether fatigue driving or not. The experimental results show that the comprehensive accuracy of fatigue detection is 95.87%. The average algorithm rate is 32.29 ms/f in an image of 640×480 pixels. The research results can serve the design of a new generation of driver fatigue detection system to mountain freeway.

This paper introduces anenhanced MSM(Mutual Subspace Method) methodology for gait recognition, to provide robustness to variations in walking speed. Theenhanced MSM (eMSM)methodology expands and adapts the MSM, commonly used for face recognition, which is a static/physiological biometric, to gait recognition, which is a dynamic/behavioral biometrics. To address the loss of accuracy during calculation of the covariance matrix in the PCA step of MSM, we use a 2D PCA-based mutual subspace. Furhtermore, to enhance the discrimination capability, we rotate images over a number of angles, which enables us to extract richer gait features to then be fused by a boosting method. The eMSM methodology is evaluated on existing data sets which provide variable walking speed, i.e. CASIA-C and OU-ISIR gait databases, and it is shown to outperform state-of-the art methods. While the enhancement to MSM discussed in this paper uses combinations of 2D-PCA, rotation, boosting, other combinations of operations may also be advantageous.

In order to improve the accuracy of sports combination training action recognition, a sports combination training action recognition model based on SMO algorithm optimization model and artificial intelligence is proposed. In this paper, by expanding the standard action data, the standard database of score comparison is established, and the system architecture and the key acquisition module design based on 3D data are given. In this paper, the background subtraction method is used to process the sports video image to obtain the sports action contour and realize the sports action segmentation and feature extraction, and the artificial intelligence neural network is used to train the feature vector to establish the sports action recognition classifier. This paper mainly uses a three-stream CNN artificial intelligence deep learning framework based on convolutional neural network and uses a soft Vlad representation algorithm based on data decoding to learn the action features. Through the data enhancement of the existing action database, it uses support vector machine to achieve high-precision action classification. The test results show that the model improves the recognition rate of sports action and reduces the error recognition rate, which can meet the online recognition requirements of sports action.

To realize real-time detection of the operating environment of bridge cranes, this paper presents a three-dimensional mapping method using a binocular camera and laser ranging sensor. First, the left and right images are obtained by using the binocular camera, and the block matching is used for stereo correspondence to obtain the disparity image. Then, according to the reprojection matrix and the disparity image, the depth value of each pixel is obtained, and the depth image can be transformed into a three-dimensional point cloud of the current frame. Relying on the camera position data obtained by the laser ranging sensor, the three-dimensional point cloud generated from different positions is registered to obtain the three-dimensional point cloud of the craneʼs global operating environment. Finally, an octree map is used to represent the operating environment. To simulate the construction process of the operating environment of the bridge crane, an experimental platform was built, and experiments were carried out using the method proposed in this paper. The experimental results verified the feasibility of the method proposed in this paper.

This paper represents the recognition of group activity in public areas, considering personal actions and interactions between people from the field of computer vision. Modeling the interaction relationships between multiple people is essential for recognizing group activity in the video scene. In artificial intelligence applications, identifying group activities based on human interaction is often a challenging task. This paper proposed a model that formulates a group action context (GAC) descriptor. The descriptor was developed by integrating the focal person action descriptor and interaction joint context descriptor of nearby people in the video frame. The model used an efficient optimization principle based on machine learning to learn the discriminative interaction context relations between multiple persons. The proposed novel group action context descriptor is classified by support vector machine (SVM) to recognize group activity. The proposed technique effectiveness is evaluated for group activity recognition by performing experiments on a publicly available collective activity dataset. The proposed approach infers a group action class when multiple persons are together in the video sequence, especially when the interaction between people is confusing. The overall group action recognition model is interrelated with a baseline model to estimate the performance of interaction context information. The experimental result of the proposed group activity recognition model is comparable and outperforms the previous methods.

This paper is a preliminary study that aims to build the character of color image object through the Gaussian copula model. The development of the Gaussian copula model is carried out with the distribution of Cumulative Distribution Function (CDF) of the pixels as input. In contrast to other studies that use image pixel values. The random variables used are the CDF value at the point of differentiation determined by the Kulback-Leibler Divergence (KLD). The case discussed in this paper is the image modeling of red apples and green apples. The model is built on each Red, Green, and Blue (RGB) image with three distinguishing points. The result obtained is a Gaussian copula model with different parameters for red apples and green apples. The character of joint distribution is also different. The joint distribution value of green apples is greater than that of red apples in R and G images. The difference in the models obtained shows that the character of this image is different. Future research will use the acquired models to identify new images, whether they are recognized as red and green apples or not. Further development in the field of healthy vision. This model can be used to identify fruit images in an application.

In this paper, we deal with the descriptor combination problem in image classification tasks. This problem refers to the definition of an appropriate combination of image content descriptors that characterize different visual properties, such as color, shape and texture. In this paper, we propose to model the descriptor combination as a swarm-based optimization problem, which finds out the set of parameters that maximizes the classification accuracy of the Optimum-Path Forest (OPF) classifier. In our model, a descriptor is seen as a pair composed of a feature extraction algorithm and a suitable distance function. Our strategy here is to combine distance scores defined by different descriptors, as well as to employ them to weight OPF edges, which connect samples in the feature space. An extensive evaluation of several swarm-based optimization techniques was performed. Experimental results have demonstrated the robustness of the proposed combination approach.

The communication recognition of mobile phone core is a test of the development of machine vision. The size of mobile phone core is very small, so it is difficult to identify small defects. Based on the in-depth study of the algorithm, combined with the actual needs of core identification, this paper improves the algorithm and proposes an intelligent algorithm suitable for core identification. In addition, according to the actual needs of core wire recognition, this paper makes an intelligent analysis of the core wire recognition process. In addition, this paper improves the traditional communication image recognition algorithm and analyzes the data of the recognition algorithm according to the shape and image characteristics of the mobile phone core. Finally, after constructing the functional structure of the system model constructed in this paper, the system model is verified and analyzed, and on this basis, the performance of the improved core recognition algorithm proposed in this paper is verified and analyzed. From the results of online monitoring and recognition, the statistical accuracy of mobile phone core video recognition is about 90%, which has higher accuracy in mobile phone core image recognition than traditional recognition algorithms. The core line recognition algorithm based on deep learning and machine vision is effective and has a good practical effect.

To improve the interpretability or perception of information in images for human viewers is the main goal of image enhancement. Aiming at the problem that image edges are difficult to determine due to artefacts, plaques, and vascular branches in cardiovascular ultrasound, an edge ultrasound imaging detection algorithm based on spatial-frequency-domain image enhancement is proposed to improve the clarity of ultrasound images. Firstly, this paper uses the space-frequency-domain enhancement algorithm to enhance the image. This algorithm overcomes the problem of low contrast of conventional algorithms. The enhanced data matrix is used as the cost matrix, and then, the heuristic image search method is used to search the image of the cost matrix. The results show that the use of spatial-frequency-domain image ultrasound imaging algorithm can improve the contrast and sharpness of ultrasound images of cardiovascular disease, which can make the middle edge of the image clearer, the detection accuracy rate is increased to 92.76%, and the ultrasound of cardiovascular disease is improved. The edge of the image gets accuracy. The paper confirms that the ultrasound imaging algorithm based on spatial-frequency-domain image enhancement is worthy of application in clinical ultrasound image processing. The performance of the proposed technique is 32.54%, 75.30%, 21.19%, 21.26%, and 11.10% better than the existing technique in terms of edge energy, detail energy, sharpness, contrast, and information entropy, respectively.

Pixel-wise image quality assessment (IQA) algorithms, such as mean square error (MSE), mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) correlate well with perceptual quality when dealing with images sharing the same distortion type but not well when processing images in different distortion types, which is inconsistent with human visual system (HVS). Although a large number of metrics based on image error has been proposed, there are still difficulties and limitations. To solve this problem, a full reference image quality assessment (FR-IQA) method based on MAE is proposed in this paper. The metric divides the image error (difference between distorted image and reference image) map into smooth region and texture-edge region, calculates their mean values respectively, and then gives them different weights considering the masking effect. The key innovation of this paper is to propose a distortion significance measurement, which is a visual quality coefficient that can effectively indicate the influence of different distortion types on perceptual quality and unify them with HVS. The segmented image error maps are weighted by the distortion significance coefficient. The experimental results on four largest benchmark databases show that the most of the distortions are successfully evaluated and the results are consistent with HVS.

In this paper, we consider a problem-solving technique of the texture changing of an object in a photograph. The task in hand is relevant in the field of intelligent image processing and has a number of practical applications. The solutions to this problem have been proposed in a number of works devoted to the neural network style transfer approach, but they have a number of limitations. Examples of the limitations are as follows: the texture transfer selectivity absence (the image is changed entirely), the target texture distortion with the heterogeneity of the original one, the initial illumination distortion of the object, and the absence of the photographic realism of the resulting image. To solve the problems mentioned above, in this paper we propose a sequential image processing with the use of several neural networks types: segmental, stylizing and generative-adversarial (GAN) ones. The reliable transfer problem of an object illumination is proposed to be solved by the joint work of GAN and methods that do not use the neural network approach. In the context of this paper we developed an algorithm that allows solving the texture transferring task with completely or partially elimination of the listed problems of classical methods. Its high quality of work is shown with the maintaining productivity acceptable for common use. Demonstration of the algorithm is performed on the task of a virtual furniture dust covers fitting (sofas, armchairs). In addition to the algorithm itself, this work includes an enumeration of some heuristics and limitations stated during its implementation and application.

This paper proposes methods for super resolving single noisy low resolution images. Even if single image super resolution has been a topic of research for last few decades, super resolution of noisy low resolution images is still a challenging problem. Most of the state of the art super resolution algorithms will fail to perform if significant amount of noise is present in the observed image. In this paper, we propose a denoised patch dictionary based single image super resolution algorithm. To enhance the robustness to noise performance, this method is further modified by using a wavelet based fusion algorithm which combines the result of proposed method with direct super resolved image, and super resolved image after denoising to preserve the finer details of the super resolved image. The proposed methods are applied on the commonly used test images. The results validate that the proposed methods show improvement over the existing techniques.

This paper proposes two data hiding methods in color halftone images based on new conjugate property. Firstly, implementing and extending previous methods, and analyzing the performance of various methods. Secondly, this paper proposes new conjugate property and applies this property to hide a secret pattern in color halftone images, and two novel methods called data hiding by new color conjugate error diffusion (NCCED) and data hiding by new color conjugate dot diffusion (NCCDD) can be proposed. Using new conjugate property fewer components need to be toggled, as a result the correct decoding rate (CDR) of the revealed pattern will be increased, and the visual effect of halftone images can be improved. Finally, this paper proposes average distortion per pixel (ADPP) to measure toggling distortion in different methods accurately. Experimental results show that NCCED and NCCDD not only have higher CDR than the previous methods, but also provide better visual effect of halftone images.