Search

Conventional noise reduction algorithms have been used in image processing for a very long time, but recently, deep learning-based algorithms have been shown to significantly reduce the noise in CT images. In this paper, a comparison of CT noise reduction of a deep learning-based, a conventional, and their combined denoising algorithms is presented. A conventional adaptive 3D bilateral filter and a 2D deep learning-based noise reduction algorithm and a combination of these are compared. For comparison, we used the noise power spectrum and the task transfer function which were measured on original CT images and the effective dose saving factors were also calculated. The noise reduction effect, the noise power spectrum and the task-transfer function are studied using Catphan 600 phantom and 26 clinical cases with more than 100,000 images. We also show that the effect of noise reduction of a 2D deep learning-based algorithm can be further enhanced by using conventional 3D spatial noise reduction algorithms. [ABSTRACT FROM AUTHOR]

• The proposed Anti-Gravity Stem-Seeking (AGSS) root image restoration algorithm can quickly and effectively repair root images. • AGSS root image restoration algorithm has good universality and does not need training data and high-performance hardware platforms. • Drought and waterlogging resistances of maizes can be effectively evaluated by the phenotypic parameters of repaired seed roots. Root phenotype detection is key to cultivating seeds with excellent traits, and requires a complete root image. However, soil occlusion, uneven lighting, and other factors cause broken points and segments in the root image. To solve this problem, an anti-gravity stem-seeking (AGSS) root image restoration algorithm is proposed in this paper to repair root images and extract root phenotype information for different resistant maize seeds. First, the obtained root image was processed using uniform illumination, grayscale, binarization, and morphological filtering to separate it from the background. Subsequently, a root skeleton map was generated using a thinning algorithm for pixel-level image processing, and the Taproot junction G was obtained. Subsequently, root pixel coordinates were obtained by traversing the root skeleton map. All root-segment endpoint coordinates were obtained using the endpoint judgment rule and stored in the endpoint list. The lateral and primary root endpoints were separated based on the lateral root judgment rule, and stored in the side root and primary root endpoint lists, respectively. Subsequently, the primary root endpoints were processed and fitted in the order short to long using arbitrary-two-endpoint spacing until all breakpoints of the primary root were found. The coordinates of the top endpoints of each principal root were obtained. Finally, the top endpoint was connected to point G based on the Bezier curve-fitting method to achieve complete root repair. The proposed AGSS root image restoration algorithm was applied to detect the root systems of maize with different resistances and wheat to evaluate its performance against the standard dataset. The results indicated a detection accuracy of greater than 90% for root taproot length and diameter. It was also found that maize drought resistance was positively correlated with root length and diameter, but negatively with the lateral root number. In contrast, the waterlogging and salt resistance traits of maize were positively correlated with the number of lateral roots. In conclusion, the proposed AGSS root image restoration algorithm can quickly and effectively repair root images, is suitable for different resistance evaluations of maize seeds, and is conducive to the detection of root phenotypes. Compared with deep learning methods, this algorithm displays advantages of fast repair, low hardware platform requirements, and less requirement of training images. The algorithm is highly suitable for deploying in small embedded systems, with broad application prospects. [ABSTRACT FROM AUTHOR]

• In this work, hidden topography under paint were characterized by dynamic speckle image processing. • The choice of an algorithm for dynamic speckled image processing was made with the lighting profile in mind. • The results show that the performance of various intensity normalized speckle algorithms decreases with the number of frames used. The use of qualitative algorithms in images with dynamic speckle allows generating a three-dimensional intensity map, which correlates with the sample activity. Samples in an evaporation state will present temporary mobility related to their volume, which allows characterizing their topography. However, the quality of the topographic characterization depends on the illumination profile and the number of images or frames used. In this paper, a review of various qualitative processing algorithms is carried out in order to evaluate their robustness to the number of frames and their dependence on the beam profile, evaluating the characterization of topography hidden by a layer of paint in process of drying. We use an aluminum structure with perforations of different diameters and depths as a sample. Among the algorithms used, we highlight the results obtained by the normalized DJC method, which characterizes the topography of our sample with a correlation of 0.98 and presents stability to the number of frames used. Thus, with these results we validate the use of dynamic speckle in the characterization of a surface covered with paint. [ABSTRACT FROM AUTHOR]

Though most of the faces are axis-symmetrical objects, few real-world face images are axis-symmetrical images. In the past years, there are many studies on face recognition, but only little attention is paid to this issue and few studies to explore and exploit the axis-symmetrical property of faces for face recognition are conducted. In this paper, we take the axis-symmetrical nature of faces into consideration and design a framework to produce approximately axis-symmetrical virtual dictionary for enhancing the accuracy of face recognition. It is noteworthy that the novel algorithm to produce axis-symmetrically virtual face images is mathematically very tractable and quite easy to implement. Extensive experimental results demonstrate the superiority in face recognition of the virtual face images obtained using our method to the original face images. Moreover, experimental results on different databases also show that the proposed method can achieve satisfactory classification accuracy in comparison with state-of-the-art image preprocessing algorithms. The MATLAB code of the proposed method can be available at http://www.yongxu.org/lunwen.html . [ABSTRACT FROM AUTHOR]

Recent advances in image classification mostly rely on the use of powerful local features combined with an adapted image representation. Although Convolutional Neural Network (CNN) features learned from ImageNet were shown to be generic and very efficient, they still lack of flexibility to take into account variations in the spatial layout of visual elements. In this paper, we investigate the use of structural representations on top of pretrained CNN features to improve image classification. Images are represented as strings of CNN features. Similarities between such representations are computed using two new edit distance variants adapted to the image classification domain. Our algorithms have been implemented and tested on several challenging datasets, 15Scenes, Caltech101, Pascal VOC 2007 and MIT indoor. The results show that our idea of using structural string representations and distances clearly improves the classification performance over standard approaches based on CNN and SVM with linear kernel, as well as other recognized methods of the literature. [ABSTRACT FROM AUTHOR]

In this paper, we propose an improved keypoint detection algorithm of object-based recognition for non-uniform illumination, called IKDSIFT, which is implemented using the SIFT approach, morphological operations, Top-Hat filtering and various techniques in pre-processing procedures. The number of keypoint rate of data sets was compared. Data sets consist of three hundred 150x150 images and thirty 851x566 images with different uniform and non-uniform illumination. The experimental results show that the number of keypoint detection is reciprocal to peak selection thresholds. The best algorithm is the proposed IKDSIFT, followed by the SIFT. The ASIFT performs the worst. Additionally, the SIFT and ASIFT can detect some peak selection thresholds while the IKDSIFT can detect all ranges of the peak and obtains the best result comparing to other ones. Hence, the proposed algorithm looks promising to be used for recognizing under non-uniform illumination. [ABSTRACT FROM AUTHOR]

Consider a set of images of a single object, or scenery, taken from different viewpoints and time. Panorama image creation is the process of stitching such images into a single coordinate system to generate a wider viewing panoramic image. Image stitching consists of two processes which are image registration and image blending. In image registration, parts of two overlapping or consecutive images are considered to find an appropriate merging position and transformation to combine the images. In image blending, the intensities of pixels along the stitching line are modified so that they flow naturally without any noticeable break. In this paper, we propose a novel method that utilizes the Dynamic Time Warping (DTW) algorithm to match pairs of images for image stitching. We also perform a dimension reduction scheme that significantly reduces the computational complexity of the standard DTW without affecting its performance. The effectiveness of the proposed method is demonstrated in stitching 50 pairs of medical X-ray images and its performance is compared to those of normalized cross correlation (NCC), Minimum Average Correlation Energy (MACE) filters, sum-of-square-differences (SSD) and sum-of-absolute-differences (SAD). For the database used, the dimensionally reduced DTW outperforms the NCC, MACE, SSD and SAD methods in accuracy and average execution time. The method also outperforms two widely used stitching programs available on the internet called Hugin and Autostitch. [ABSTRACT FROM AUTHOR]

Learning-based partial differential equations (PDEs), which combine fundamental differential invariants into a nonlinear regressor, have been successfully applied to several computer vision and image processing problems. However, the gradient descent method (GDM) for solving the linear combination coefficients among differential invariants is time-consuming. Moreover, when the regularization or constraints on the coefficients become more complex, it is troublesome or even impossible to deduce the gradients. In this paper, we propose a new algorithm, called fast alternating time-splitting approach (FATSA), to solve the linear combination coefficients. By minimizing the difference between the expected output and the actual output of PDEs at each time step , FATSA can solve the linear combination coefficients much faster than GDM. More complex regularization or constraints can also be easily incorporated. Extensive experiments demonstrate that our proposed FATSA outperform GDM in both speed and quality. [ABSTRACT FROM AUTHOR]

Recently a delta-density based clustering (DDC) algorithm was proposed to cluster data efficiently by fast searching density peaks. In the DDC method, the density and a new-defined criterion delta-distance are utilized. The examples with anomalously large delta-density values are treated as cluster centers, then the remaining are assigned the same cluster label as their neighbor with higher density. However there are two challenges for the DDC algorithm. First, no rules are available to judge density-delta values as “anomalously large” or not. Second, the decision graph might produce the redundant examples with “anomalous large” density-delta values, as we define as the “decision graph fraud” problem. In this paper, an improved and automatic version of the DDC algorithm, named as 3DC clustering, is proposed to overcome those difficulties. The 3DC algorithm is motivated by the divide-and-conquer strategy and the density-reachable concept in the DBSCAN framework. It can automatically find the correct number of clusters in a recursive way. Experiments on artificial and real world data show that the 3DC clustering algorithm has a comparable performance with the supervised-clustering baselines and outperforms the unsupervised DDCs, which utilize the novelty detection strategies to select the “anomalously large” density-delta examples for cluster centers. [ABSTRACT FROM AUTHOR]

Learning-to-rank techniques have shown promising results in the domain of image ranking recently, where dimensionality reduction is a critical step to overcome the “curse of dimensionality”. However, conventional dimensionality reduction approaches cannot guarantee the satisfying performance because the important ranking information is ignored. This paper presents a novel “Ranking Dimensionality Reduction” scheme specifically designed for learning-to-rank based image ranking, which aims at not only discovering the intrinsic structure of data but also keeping the ordinal information. Within this scheme, a new dimensionality reduction algorithm called Relevance Marginal Fisher Analysis (RMFA) is proposed. RMFA models the proposed pairwise constraints of relevance-link and irrelevance-link into the relevance graph and the irrelevance graph, and applies the graphs to build the objective function with the idea of Marginal Fisher Analysis (MFA). Further, a semi-supervised RMFA algorithm called Semi-RMFA is developed to offer a more general solution for the real-world application. Extensive experiments are carried on two popular, real-world image search reranking datasets. The promising results demonstrate the robustness and effectiveness of the proposed scheme and methods. [ABSTRACT FROM AUTHOR]

The combination of a camera and an Inertial Measurement Unit (IMU) has received much attention for state estimation of Micro Aerial Vehicles (MAVs). In contrast to many map based solutions, this paper focuses on optic flow (OF) based approaches which are much more computationally efficient. The robustness of a popular OF algorithm is improved using a transformed binary image from the intensity image. Aided by the on-board IMU, a homography model is developed in which it is proposed to directly obtain the speed up to an unknown scale factor (the ratio of speed to distance) from the homography matrix without performing Singular Value Decomposition (SVD) afterwards. The RANSAC algorithm is employed for outlier detection. Real images and IMU data recorded from our quadrotor platform show the superiority of the proposed method over traditional approaches that decompose the homography matrix for motion estimation, especially over poorly-textured scenes. Visual outputs are then fused with the inertial measurements using an Extended Kalman Filter (EKF) to estimate metric speed, distance to the scene and also acceleration biases. Flight experiments prove the visual inertial fusion approach is adequate for the closed-loop control of a MAV. [ABSTRACT FROM AUTHOR]

An acceleration technique for multiplicative iterative methods, such as Lucy–Richardson and Image Space Reconstruction Algorithm, is presented. The technique is inspired by the Landweber method in Banach spaces and is based on the application of duality maps, which allow to compute the iterations in the dual space. We show the link between the proposed acceleration and the previously known Meinel acceleration, which consists in the introduction of an exponent in the basic iterative formulas. We prove that the new acceleration technique is more stable than the Meinel acceleration. This implies that, in the restoration process, the former is able to get better accuracy and higher speeding-up than the latter. In addition to the main focus of the paper, we propose a generalization of the Landweber method in Banach space, in order to overcome some drawbacks of this recent strategy when compared with classical (Hilbertian) Landweber method. Numerical results show the behavior and the features of the several techniques considered, highlighting the goodness of our proposals. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new algorithm for power line identification and extraction from high resolution remote sensing images. Theoretically, it is difficult to detect power lines in satellite images due to some characteristics, such as sub-pixel, weak target, discrete and the complicated background. To our knowledge, the problem of extraction of the power lines from satellite images is faced for the first time. An improved Radon transform, Cluster Radon Transform (CRT), was developed to extract linear feature from satellite image. Compared with conventional Radon transform, CRT can efficiently avoid false alarm. After that, a set of rules of power lines was abstracted to distinguish power lines from other linear feature, such as roads. The experimental results show that CRT not only has strong anti-noise capability to random noise, but also has strong anti-noise capability to system noise caused by non- linear feature. Furthermore, CRT also has the strong capability to detect short segment in an image. Finally, synthetic images and true images were used to verify the new approach. The achievement has potential to be applicable not only to the power line extraction, but also to other weak linear target detection. [ABSTRACT FROM AUTHOR]

According to accuracy requirements of aerial camera focusing and characteristics of CCD camera imaging, this paper proposed automatic focusing system of aerial camera based on image processing technology. Firstly, in accordance with self-made resolution target, image sharpness function and optimization of hill climbing algorithm, autocollimation defocusing compensation method was used to achieve correction of the aerial camera defocus caused by temperature and atmospheric pressure. Then the amount of defocus was calculated by introducing the aircraft height data, and defocus adjustment was realized by appropriate device. Finally, the experiment was carried out for simulating and testing of the system, and the results showed that: error of the system for camera defocusing correction is less than half of the camera focal depth, which can meet the requirements of the aerial camera, such as fast, high-precision focusing and so on. [ABSTRACT FROM AUTHOR]

Pedestrian detection is an important image understanding problem with many potential applications. There has been little success in creating an algorithm which exhibits a high detection rate while keeping the false alarm in a relatively low rate. This paper presents a method designed to resolve this problem. The proposed method uses the Kinect or any similar type of sensors which facilitate the extraction of a distinct foreground. Then potential regions, which are candidates for the presence of human(s), are detected by employing the widely used Histogram of Oriented Gradients (HOG) technique, which performs well in terms of good detection rates but suffers from significantly high false alarm rates. Our method applies a sequence of operations to eliminate the false alarms produced by the HOG detector based on investigating the fine details of local shape information. Local shape information can be identified by efficient utilization of the edge points which, in this work, are used to formulate the so called Shape Context (SC) model. The proposed detection framework is divided in four sequential stages, with each stage aiming at refining the detection results of the previous stage. In addition, our approach employs a pre-evaluation stage to pre-screen and restrict further detection results. Extensive experimental results on the dataset created by the authors, involves 673 images collected from 11 different scenes, demonstrate that the proposed method eliminates a large percentage of the false alarms produced by the HOG pedestrian detector. [ABSTRACT FROM AUTHOR]

Iris recognition is a challenging problem in the noisy environment. Our primary focus is to develop the reliable iris recognition system that can work in a noisy imaging environment and to increase the iris recognition rate on CASIA and MMUiris datasets. This research paper proposes two algorithms, first, a novel method for removing noise from the iris image and second, a texture feature extraction method using a combined approach of Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM). Our proposed approach give highest recognition rate of 96.5% and low error rate and requires less execution time. [ABSTRACT FROM AUTHOR]

Speckle reduction is an important pre-processing stage for ultrasound medical image processing. In this paper, an adaptive fuzzy logic approach for speckle noise reduction in ultrasound images is presented. In the proposed method, adaptiveness is incorporated at two levels. In the first level, applying fuzzy logic on the coefficients of variation computed from the noisy image, image regions are classified. The best suitable filter for the particular image region is adaptively selected by the system yielding appreciable improvement in noise suppression and preservation of image structural details. At the second level, to distinguish between edges and noise, the proposed method uses a weighted averaging filter. The structural similarity measure, which depends on the nature of image and quantity of noise present in the image, is used as the tuning parameter. Thus with two levels of adaptiveness, the proposed method has better edge preservation compared to existing methods. Experimental results of the proposed method for natural images, Field II simulated images and real ultrasound images, show that proposed denoising algorithm has better noise suppression and is able to preserve edges and image structural details compared with existing methods. [ABSTRACT FROM AUTHOR]

Finding correspondences between pair of images of the same scene is a key problem in computer vision. When matching images undergo viewpoint change, partial occlusion, clutters and illumination change, there will be a lot of mismatches due to the limited repeatability and discriminative power of features. In this paper, we propose a robust matching algorithm that can remove false matches and propagate the correct ones to obtain more matches, thus improve the matching accuracy. First, extracts SURF (Speeded Up Robust Features) descriptors from the input two images, which can be used to build the proximity matrix. Then perform SVD (Singular Value Decomposition) on the proximity matrix to obtain the initial matches. Third, refine the initial matches by the unique property of Delaunay triangulation that can produce the maximum cliques of the two Delaunay graph. Finally, recover the lost matches with the constraint of dual graph of Voronoi. Experimental results on Oxford datasets indicate that our algorithm can improve the match performance compared to the RANSAC-based method. [ABSTRACT FROM AUTHOR]

This paper proposed a new method to improve the visibility and contrast of color images. The proposed method is a joint technique scheme of Color Adaptive Histogram Equalization (CAHE) and interpolation method. CAHE is an effective algorithm for image contrast enhancement, and interpolation method enhances the image by increasing the number of pixels without missing any intermediate component of image. Hence, the combination of both may give the good agreement of image visuality and contrast. [ABSTRACT FROM AUTHOR]

This paper presents a novel single image super-resolution (SR) reconstruction method using shifted kernel regression. Assuming that a low-resolution (LR) image is made by the shifted regression-based image degradation model, the proposed SR process shifts pixels in a regularly sampled LR image with a subpixel precision according to local gradient. The optimum displacement of each pixel is estimated using the Gaussian filtered second derivatives. The shifted low-resolution image is finally up-scaled by estimating the regression coefficients of the shifted kernels in the spatially adaptive manner. Experimental results show that the proposed method overcomes the limitation of existing intensity-based SR algorithms. The proposed SR algorithm can successfully restore sharp, clear edges without undesired artifacts such as ringing, inverted gradient, halo effects, etc. Without using an iterative process, the proposed single image SR algorithm can easily be implemented in the form of either pre- or post-processing filters for further enhancing the SR result of existing methods. [ABSTRACT FROM AUTHOR]

Phase-diversity (PD) is the least square adaptive-filter of the imaging system based on wave optics theory. It can use unknown extended object as the observation object to collect two or more images whose wave-front diversities are known and fixed. According to the images, the wave-front of the optical system can be calculated by PD, and simultaneously the estimation of ideal image for the observation object can be obtained. Phase-diverse speckle (PDS) technique extends PD by using a series of short-expose frames as the input. In this paper, we designed PDS experiment on a 1.23 m telescope and successfully got clear restored images of space objects. Under the observation condition that the atmospheric coherent length was not more than 8 cm at 500 nm wavelength in Changchun city, we replaced the deformable mirror with a plane mirror in adaptive optical system and separately used the moon and Polaris as the observation objects. For Polaris, the FWHW reduced from 20.6 to 5.3 (in pixel), which decreased about 74%. The experimental results demonstrate that PDS algorithm can be used on one meter-scale telescope in practical observation. [ABSTRACT FROM AUTHOR]

Image details provide important image information for image analysis. So, it would be very useful to well enhance image while effectively maintaining image details. To achieve this purpose, a detail maintained image enhancement algorithm based on the extracted image features by using morphological alternating filters is proposed in this paper. First, feature extraction based on two types of alternating filters and the threshold constrained strategy is given and discussed. The extracted image features contain the useful image details, which is very useful for the detail maintained image enhancement. Second, the multi-scale extension of the procedure of feature extraction is proposed to extract the multi-scale image features. Third, the final extracted bright and dark image features are calculated based on the extracted multi-scale features. Finally, the final extracted bright and dark image features are imported into the original images through contrast adjustment, which achieves the detail maintained image enhancement. Experimental results on different types of images verified the effective performance of the proposed algorithm for image enhancement. [ABSTRACT FROM AUTHOR]

Multi-frame image super-resolution (SR) aims to utilize information from a set of low resolution (LR) images to compose a high-resolution (HR) one. As it is desirable or essential in many real applications, recent years have witnessed the growing interest in the problem of multi-frame SR reconstruction. In this paper, we propose a novel multi-frame image super-resolution algorithm built on the regularization framework. The objective functional to be minimized for the regularization framework consists of a fidelity term and a regularization term. A new fidelity term is formed by combining L 1 norm and L 2 norm according to defined Residual Weight Parameters (RWP) and Channel Weight Parameters (CWP). A new regularization term which adopts Regional Adaptive Weight Coefficients (RAWC) is proposed to keep edge and flat regions, which are implicitly described in LR images, sharp and smooth, respectively. Thorough experimental results show the new algorithm using both fidelity and regularization terms for SR reconstruction is effective than other methods. [ABSTRACT FROM AUTHOR]

Camera calibration is a basic and crucial problem in computer vision and photogrammetry. The traditional calibration approach based on 2D planar target fails to give reliable and accurate results due to the inaccurate localization of feature points in some calibration images. An accurate and robust estimation method for camera parameters based on RANdom SAmple Consensus (RANSAC) algorithm is proposed to exclude the unreliable images in this study. First, the distance between circular point and image of the absolute conic is defined, and the recommended threshold value is given by computer simulation. Second, RANSAC has been utilized to pick out a subset of calibrating images automatically, and linear algebraic approximation is performed to estimate the intrinsic parameters and external parameters. Finally, all the camera parameters including lens distortion parameters are refined by the non-linear searching algorithm. Numerical simulation and practical experiment in this paper demonstrate the accuracy and robustness of the proposed method. The experimental results show that the proposed method is more robust and efficient in improving the calibration accuracy than the traditional methods. [ABSTRACT FROM AUTHOR]

The paper presents a ECGs classification system that uses powerful algorithms image processing and artificial intelligence. The descriptor haar-like is based on the concept of the integral image to accelerate the calculation of haar features and the classifier multilayer perceptron type. The training and testing of the proposed system were performed on two basic types: a learning base containing labeled data (normal ECG and ECG sick) and another base unlabeled data. The experimental results have shown that the system combines between the respective advantages of haar-like descriptor and artificial neuron networks in terms of robustness and speed. [ABSTRACT FROM AUTHOR]

This paper proposes a reaction-diffusion algorithm designed for image encoding, pooling and decoding with a FitzHugh-Nagumo model. The model simulates biological nonlinear response on external stimuli applied to nerve axon. A system of discretely coupled elements governed by the FitzHugh-Nagumo model has the nature of organizing stationary pulses, depending on their initial conditions and coupling strength. The proposed algorithm utilizes the system, and encodes a gray level image into a halftone image with the nature organizing stationary pulses (image encoding); the encoded halftone image is pooled in the system without external stimuli (image pooling). In the image encoding, we need to add Gaussian noise to the gray level image for randomly distributing pulses, which represent gray levels in a local area. By providing the encoded halftone image for the initial condition of the same reaction-diffusion algorithm, we obtain a gray level image approximating to the original one (image decoding). [ABSTRACT FROM AUTHOR]

In this paper, we present a scalable three dimensional hybrid parallel Delaunay image-to-mesh conversion algorithm (PDR.PODM) for distributed shared memory architectures. PDR.PODM is able to explore parallelism early in the mesh generation process because of the aggressive speculative approach employed by the Parallel Optimistic Delaunay Mesh generation algorithm (PODM). In addition, it decreases the communication overhead and improves data locality by making use of a data partitioning scheme offered by the Parallel Delaunay Refinement algorithm (PDR). PDR.PODM utilizes an octree structure to decompose the initial mesh and to distribute the bad elements to different octree leaves (subregions). A set of independent subregions are selected and refined in parallel without any synchronization among them. In each subregion, a group of threads is assigned to insert or delete multiple points based on the refinement rules offered by PODM. We tested PDR.PODM on Blacklight, a distributed shared memory (DSM) machine in the Pittsburgh Supercomputing Center, and observed a weak scaling speedup of 163.8 and above for up to 256 cores as opposed to PODM whose weak scaling speedup is only 44.7 on 256 cores. The end result is that we can generate 18 million elements per second as opposed to 14 million per second in our earlier work. To the best of our knowledge, PDR.PODM exhibits the best scalability among parallel guaranteed quality Delaunay mesh generation algorithms running on DSM supercomputers. [ABSTRACT FROM AUTHOR]

In this paper, a novel superpixel based multi-focus image fusion algorithm for raw images of single-sensor color imaging devices which incorporates the Bayer pattern is proposed. The proposed algorithm is more efficient than traditional fusion schemes since the raw Bayer pattern images are fused before color demosaicing. With the proposed fusion algorithm, the interpolation errors introduced by the repeated demosaicing operation on multi-source images can also be greatly reduced. In detail, a clarity measurement of Bayer pattern image is defined to judge the focus-level of raw Bayer pattern images, and the fusion operator is performed on superpixels which provide powerful grouping cues of local image feature. By comparing the clarities of superpixels, a weight map is constructed and the guided filter is utilized to refine the weight map. The raw images are merged with refined weight map to get the fused Bayer pattern image, which is restored by the demosaicing algorithm to get the full resolution color image. Experimental results demonstrate that the proposed algorithm can obtain better fused results with more natural appearance and fewer artifacts than the traditional algorithms. [ABSTRACT FROM AUTHOR]

This paper presents an intelligent, automatically controlled camera based on visual feedback. The camera housing contains actuators that change the orientation of the camera – enabling a full rotation around the vertical axis (pan) and 90° around the horizontal axis (tilt). A system for acquisition, processing image analysis and a camera driver are implemented in the FPGA Xilinx Spartan-6 device. An original, innovative reconfigurable system architecture has been developed. The FPGA device is connected directly to the eight independently operated SRAM memory banks. A prototype device has been constructed with a real-time tracking algorithm, enabling an automatically control of the position of the camera. The device has been tested indoors and outdoors. The camera is able to keep a tracked object close to the center of its field of view. The power consumption of the control system is 2 W. A reconfigurable part reaches the computing performance of 3200 MOPS. [ABSTRACT FROM AUTHOR]

Ant-tree is a clustering algorithm inspired by biological ants. This paper defines a variant of such algorithm to perform colour quantization. Some of the features of the basic Ant-tree have been adapted to obtain a quicker algorithm and to perform the main steps of colour quantization on a big input set. The centroid of every cluster defines a colour of the palette and once the complete colour palette is established, the algorithm represents each pixel of the original image by the colour associated to its cluster. Computational results show that the error obtained for the quantized images is smaller than the error generated by some other well-known quantization methods. [ABSTRACT FROM AUTHOR]

Object tracking via depth image sequences can output 3D motion trajectories, and is effective in solving many traditional problems such as illumination changes and projective distortion. However, the influence of complex scene in depth-based tracking has received little attention. Depth tracker is susceptible to many kinds of disturbances, such as nearby objects, moving distracters and noise, and these properties need to be considered in the design of a robust tracking algorithm. In this paper we investigated the depth image-based object tracking problem by a typical application: hand tracking. Firstly the properties of depth image and the disturbances are discussed. Secondly two different depth trackers are proposed to handle different scenarios: one is based on depth frame differencing, and the other one is based on the mean shift algorithm which is modified to utilize depth information. Finally, a robust fused tracker is proposed based on the two different trackers. This approach was tested on two groups of depth image sequences recorded by a Kinect device, and the experimental results show that the fused tracker is competent for accurate 3D hand tracking even under very complex scene. [ABSTRACT FROM AUTHOR]

This paper proposes two exposure based recursive histogram equalization methods for image enhancement. The proposed methods are very effective for images acquired in low light condition like underwater sequences or night vision images. The first method is recursive exposure based sub-image histogram equalization (R-ESIHE) that recursively performs ESIHE [20] method till the exposure residue among successive iteration is less than a predefined threshold. The second method is named as recursively separated exposure based sub image histogram equalization (RS-ESIHE) that performs the separation of image histogram recursively; separate each new histogram further based on their respective exposure thresholds and equalize each sub histogram individually. The experimental results show that low exposure image enhancement problem was not addressed by earlier HE based methods, has been efficiently handled by these new methods. The performance evaluation of new methods is done in terms of image information content as well as visual quality inspection. The proposed methods outperforms earlier HE based contrast enhancement algorithms specifically for low light images. [ABSTRACT FROM AUTHOR]

For center deviation of space circular mark in the perspective projection transformation process, a novel method is proposed in this paper to locate the real projection center precisely based on the theory of analytic geometry and spatial perspective. First, we analyze the spatial circle error of perspective projection transforms generated and gives relevant basic principles. Then the detailed implementation of the algorithm and the specific steps are presented. Finally through the experiments verify the effectiveness of the method. Simulation and experimental results indicate that this method can achieve the actual projection point precise positioning of the space circular target. The algorithm does not require additional complex constraints and has good robustness; therefore it has a wide range of practical engineering application value. [ABSTRACT FROM AUTHOR]

Based on the scanning mechanism of a 3D laser scanner, a step edge detection method for 3D point clouds was proposed in this paper. A point cloud was first converted into a two-dimensional range image. Topological relations between each point can be determined clearly through the range image. The edges in the two-dimensional range image were extracted by the Canny operator and the edge points in three-dimensional points were obtained according to the mapping algorithm. An experiment was conducted by using a LMS-Z620 3D laser scanner of RIGEL. The experiment results further verify that the new method yields a good effect of edge detection. [ABSTRACT FROM AUTHOR]

In this paper we are presenting some new approaches to the biological model of neural network, which is strictly based on Hodgkin–Huxley types of models. The first aspect was to introduce stochasticity into a model of dendritic structure of neuron already proposed in Hodgkin and Huxley (1952) by using Markov kinetic schemes (Destexhe et al., 1994). Second thing was to bring into this model a training algorithm which is based on the descent gradient method. Subsequently the trained neural network is supposed to solve a problem of noise removal from a given image. This study is supposed to underline potential of biologically realistic models of neural network, which – with a bit of invention – can be used like conventional artificial neural networks. [ABSTRACT FROM AUTHOR]

Detecting the linear features in an image is a key technology for different applications. In this paper, a simple and effective algorithm based on the hit-or-miss transform is proposed. To detect linear features with different directions, multi-structuring elements corresponding to different directions are constructed. To detect linear features with different widths, a multi-scale extension of the constructed multi-structuring elements is used. Then, the grey-level hit-or-miss transform that utilizes the constructed multi-scales of multi-structuring elements could effectively extract all of the possible linear features without thresholding. Therefore, after refining the extracted linear feature regions using three simple steps, the final linear features could be effectively detected. Experimental results on different images from different applications show that the proposed algorithm performs well for detecting linear features with different widths, different grey distributions and noises. [ABSTRACT FROM AUTHOR]

An improved image magnification algorithm for gray and color images is presented in this paper to meet the challenge of preserving high-frequency components of an image, including both image edges and texture structures. In the proposed algorithm, a new edge detection method that uses the well-known Otsu automatic optimum thresholding is proposed to distinguish strong edge pixels. The parameters of the original directional cubic convolution interpolation algorithm, which were selected based on training, were eliminated. As a result, our algorithm achieves more accurate edge detection, better interpolation results, and less computational complexity. Simulation results demonstrate that the improved algorithm can reconstruct the magnified image, preserve edges and textures simultaneously, and reduce common interpolation artifacts. Furthermore, it generates higher visual quality of the magnified images and achieves higher peak signal-to-noise ratio, structural similarity, and feature similarity compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper we use and extend a parallel optoelectronic processor for image preprocessing and implement software tools for testing and evaluating the presented algorithms. After briefly introducing the processor and showing how images can be stored in it, we adapt a number of local image preprocessing algorithms for smoothing, edge detection, and corner detection, such that they can be executed on the processor in parallel. These algorithms are performed on all pixels of the input image in parallel and, as a result, in steps independent of its dimensions. We also develop a compiler and a simulator for evaluating and verifying the correctness of our implementations. [ABSTRACT FROM AUTHOR]

In this paper an innovative algorithm to reproduce non-uniform, photorealistic, gray-scale images on large surfaces, using an ordinary industrial spray-painting robot is proposed. The algorithm splits the process into a set of iterative steps with decreasing spray-gun stroke diameters. Thus, it can efficiently build up the image starting with large strokes to paint the larger details of the image. Then, with increasingly smaller strokes, it can paint the rest of the smaller details. The target image is segmented and a tool-path is computed. A set of critical points in the image is then chosen to avoid oversaturation and used to implement an algorithm to calculate spray-gun operational speed at each path point. Eventually, such conditions lead to a linear system which is solved using an ordinary least squares method. Depending on the image to reproduce, this methodology promises to be far more efficient than painting processes where the image is built entirely at the smallest detail level. For this reason, it would be particularly suitable for large building façade decoration, for example. [ABSTRACT FROM AUTHOR]

Continuous monitoring driver's head dynamics during driving under varying lighting conditions is important yet a challenging problem. Head monitoring becomes even more difficult, when it is done on real-time. Over the past few years, there is growing research interest from research labs, Industry and academic Institutions to develop algorithms for the Advance Driver Assistance System (ADAS).In this paper we present a continuous head monitoring mechanism to detect any drowsiness of driver while driving to avoid the risk of road accidents. [ABSTRACT FROM AUTHOR]

Image segmentation has been an important technique in the field of image processing. Fine-level manual annotations are very limited and difficult for a large collection of imbalanced images, where each image contains quite different small objects. However, we find that these imbalanced images have similar decision graphs obtained by a lightweight and simple clustering algorithm Density Peaks (DPeaks). Hence, in this paper, we propose a weakly supervised image segmentation algorithm. It trains a decision curve from decision graphs of a few sample imbalanced images by SVM and Support Vector Regression (SVR), which is effective for identifying the sparse region of an imbalanced image. Besides, RangeTree is applied to accelerate RDP for large images due to the high complexity of DPeaks Clustering. Experiments prove that the proposed algorithm works well on imbalanced image data sets, not only it can recognize main things, but also has the ability to identify some relatively small objects. [ABSTRACT FROM AUTHOR]

Background: This paper presents an automatic method for assessing temperature distribution on the patient's back using thermal imaging. It discusses the advantages and disadvantages of thermal imaging and presents an algorithm for image analysis and processing that runs automatically and reproducibly. Method: The proposed new method of image analysis relates to automatic and reproducible analysis of temperature distribution on the patient's back. It includes the following steps: (1) detection of the external contours of the human body, (2) identification and recognition of the position of the arms, hips and shoulders, (3) application of a mesh having a fixed number of fields (which automatically adapts to the size of the patient's back), (4) analysis of the paraspinal muscles. These steps are preceded by image pre-processing. Results: Based on a thermal image, this new fully automated algorithm enables to: (1) evaluate temperature distribution in the paraspinal area; (2) pre-assess the degree of lateral spinal curvature in screening, and (3) evaluate anomalies (deviations from the norm) in temperature distribution. The algorithm was practically implemented in Matlab Image Processing Toolbox. [ABSTRACT FROM AUTHOR]

Mastitis is an infectious disease associated with the increased number of somatic cells in cow’s milk, and it is one of the most relevant cause of economic losses in dairy farming industries. In this paper, we propose a method capable of determine, with 99.7% accuracy, the number of these cells in microscope slide images. This level of accuracy is achieved by changing the image original RGB format to Lab color space and applying k -means clustering algorithm to remove debris and other background features. A new gray level thresholding is proposed, and the remaining bound cells are separated in the final segmentation step applying Watershed transform. Many microscope slide images with debris, contrast, and hue variation were used to validate the experimental results. Comparison between the proposed method and manual counting indicates that this new approach is a robust and promising solution to be incorporated in a future automated somatic cell counting system using optical microscopy. [ABSTRACT FROM AUTHOR]

A systematic approach to I / Q mismatch calibration in image-reject receivers is presented in this paper. A new error detection algorithm is proposed, which automatically calibrates for phase and gain mismatches limiting the performance of image-reject receivers. A dual-loop feedback is employed which looks for the minimum phase/gain error using a 2-dimensional analog-based search algorithm and then finds the minimum value for the error. An experimental CMOS prototype RF front-end for cognitive radio applications operating at 400–800 MHz is proposed and simulated in the 0.18 μm CMOS technology, achieving an image rejection ratio (IRR) better than 55-dB in post-layout simulation. The comprehensive mathematical model of this analog algorithm is thoroughly studied in the appendix and the convergence is verified theoretically. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method to address the registration of images with affine transformation. Firstly, the Maximally Stable Extremal Region (MSER) detection method is performed on the reference image and the image to be registered, respectively. And the coarse affine transformation matrix between the two images is estimated by the matched MSER pairs. Two circular regions containing roughly the same image content are also obtained by fitting and normalizing the centroids of the matched MSERs from the two images. Secondly, a scale invariant and approximate affine transformation invariant feature point detection algorithm based on the Gabor filter decomposition and phase congruency is performed on the two coarsely aligned regions, and two feature point sets are achieved, respectively. Finally, the affine transformation matrix between the two feature point sets is obtained by using a probabilistic point set registration algorithm, and the final affine transformation matrix between the reference image and the image to be registered is achieved according to the coarse affine transformation matrix and the affine transformation matrix between the two feature point sets. Several sets of experiments demonstrate that our proposed method performs competitively with the classical scale-invariant feature transform (SIFT) method for images with scale changes, and performs better than the traditional MSER and Affine-SIFT (ASIFT) methods for images with affine distortions. Moreover, the proposed method shows higher computation efficiency and robustness to illumination change than some existing area-based or feature-based methods do. [ABSTRACT FROM AUTHOR]

The paper presents a fast, reliable and efficient method for improving hyperspectral image classification aided by segmentation. The Multinomial Logistic Regression(MLR) algorithm can be extended to a semi-supervised learning of the posterior class distribution using unlabeled samples actively selected from the dataset. Classification results obtained from regression model is improved by performing a maximum a posteriori segmentation as it considers the spatial information of the hyperspectral image. The addition of the spatial processing step prior to the above mentioned classification scheme improves the overall accuracy of the process. The accuracies obtained before and after applying the preprocessing are compared. [ABSTRACT FROM AUTHOR]

Establishing correct correspondences between two faces with different viewpoints has played an important role in 3D face reconstruction and other computer-vision applications. Usually, face images are considered to lack sufficient distinctive features to establish a large number of correspondences on uncalibrated images. In this paper, we investigate pore-scale facial features, which are formed from pores, fine wrinkles, and hair. These features have many characteristics that make them suitable for matching facial images under different variations. Using both biological observation and computer-vision consideration, a new framework is devised for pore-scale facial-feature extraction and matching. The matching difficulty under various skin appearances of different subjects and imaging distortion is also analyzed. For further improving the matching performance and tackling distortions such as varying illuminations and unfocused blurring, a pore-to-pore correspondences dataset is established for training a more distinctive and compact descriptor. Experiments are conducted on a face database containing 105 subjects, and the results prove that the pore-scale features are highly distinctive; face images with a minimum resolution of 600×700 (0.4 mega) pixels contain sufficient details to perform a reliable matching in different poses. Generally, our algorithm can establish between 500 and 2000 correct correspondences on a pair of uncalibrated face images of the same person. Furthermore, the proposed methods can be applied to face recognition, 3D reconstruction, etc. [ABSTRACT FROM AUTHOR]