Showing papers on "Edge enhancement published in 2019"

Edge enhancement of potential field data using the logistic function and the total horizontal gradient

Abstract: Locating the edges of anomalous bodies provides a fundamental tool in the geologic interpretation of potential field data. This paper compares the effectiveness of the commonly used edge detection methods such as the total horizontal gradient, analytic signal, tilt angle, theta map and their modified versions in terms of their accuracy on the determination of edges of source bodies. This paper also introduces an edge detector method for the enhancement of potential field anomalies, which is based on the logistic function of the total horizontal gradient. The new method is tested on synthetic data calculated using 3 models, and also on real magnetic and gravity data from Vietnam. The effectiveness of the method is evaluated by comparing the results with those of other popular methods. These results demonstrate that the method is a useful tool for the qualitative interpretation of potential field data.

Selective near-perfect absorbing mirror as a spatial frequency filter for optical image processing

Abstract: Spatial frequency filtering is a fundamental enabler of information processing methods in biological and technical imaging. Most filtering methods, however, require either bulky and expensive optical equipment or some degree of computational processing. Here, we experimentally demonstrate real-time, on-chip, all-optical spatial frequency filtering using a thin-film perfect absorber structure. We experimentally demonstrate edge enhancement of an amplitude image and conversion of phase gradients to intensity modulation in an image. The device is used to demonstrate enhancement of an image of pond algae.

Up-Conversion Imaging Processing With Field-of-View and Edge Enhancement

Abstract: Spiral phase contrast (SPC) imaging is an important technique in edge detection. For infrared wavelengths, though, typical charge-coupled-device detectors are inefficient, slow, and noisy; to exploit them, one should instead work in the visible part of the spectrum. Here up-conversion SPC imaging is realized, based on sum-frequency generation, which also has the advantage of enhancing the field of view. This versatile technique is quite promising for $e.g.$ reagent-free biological imaging, pattern recognition, and up-conversion edge detection.

Domain-independent severely noisy image segmentation via adaptive wavelet shrinkage using particle swarm optimization and fuzzy C-means

Abstract: Noisy image segmentation is a hot topic in natural, medical, and remote sensing image processing. It is among the non-trivial problems of computer vision having to address denoising and segmentation at the same time. Fuzzy C-means (FCM) is a clustering algorithm that has been shown to be effective at dealing with both segmentation-oriented denoising and segmentation at the same time. Moreover, with a high level of noise and other imaging artifacts, FCM loses its ability to perform image segmentation effectively. This paper introduces a Particle Swarm Optimization (PSO)-based feature enhancement approach in the wavelet domain for noisy image segmentation. This approach applies adaptive wavelet shrinkage using FCM clustering performance as an evaluation mechanism and also as the segmentation algorithm. The PSO-based process helps to enhance intensity features for clustering-based denoising, and also provides adaptivity for the system that performs well on a range of real, synthetic, and simulated noisy images with different noise levels and range/spatial properties. Furthermore, the algorithm applies edge enhancement based on Canny edge detector in order to further improve accuracy. Experiments are presented using three different datasets each degraded with different types of common noise. The presented algorithms show effective and consistent performance over a range of severe noise levels without the need for any parameter tuning.

LAS: A combination of the analytic signal amplitude and the generalised logistic function as a novel edge enhancement of magnetic data

Abstract: In the evaluation of magnetic field data, edge enhancement and detectiontechniques are important treatments for the interpretation of geological structures. Ingeneral geological sense, contiguity of deep and shallow magnetic sources leads to weakand intense anomalies that complicates the interpretation to disclose adjacent anomaloussources. Many of the existing filters for edge detection in magnetics mostly have the disadvantagethat they require a reduction to pole transformation as the pre-process of thedata or they cannot balance weak and intense anomalies and therefore fail in detectingedges of deep and shallow sources simultaneously. This study presents an improved edgedetection filter LAS (logistic function of the analytical signal), based on the generalisedlogistic function configured by the ratio of derivatives of the analytical signal. This novelapproach has the capability of reducing the dependence on the direction of the magnetizationand also balancing anomalies of sources at different levels of depth. The feasibility ofthe method is examined on both theoretical and real data cases comparatively with someother methods that utilize the analytical signal in their basis. In comparison, the resultsdemonstrate that the LAS method provides more accurate estimation of edge localization.

De-scattering and edge-enhancement algorithms for underwater image restoration

Abstract: Image restoration is a critical procedure for underwater images, which suffer from serious color deviation and edge blurring. Restoration can be divided into two stages: de-scattering and edge enhancement. First, we introduce a multi-scale iterative framework for underwater image de-scattering, where a convolutional neural network is used to estimate the transmission map and is followed by an adaptive bilateral filter to refine the estimated results. Since there is no available dataset to train the network, a dataset which includes 2000 underwater images is collected to obtain the synthetic data. Second, a strategy based on white balance is proposed to remove color casts of underwater images. Finally, images are converted to a special transform domain for denoising and enhancing the edge using the non-subsampled contourlet transform. Experimental results show that the proposed method significantly outperforms state-of-the-art methods both qualitatively and quantitatively.

Efficient edge-preserved sonar image enhancement method based on CVT for object recognition

Abstract: In the field of computer-aided recognition, edge feature is one of the key factors to determine recognition performance Comparing to an optical image, since sonar image via acoustic wave is easily influenced by underwater environments such as particle density, temperature, and current, edge information should be boosted Some image preprocessing techniques based on transform domain such as wavelet and curvelet may be good candidates but conventional methods show not only the possibility of enhancing edge features but also the limitation due to the absence of consideration to the edge direction This study proposes an improved edge enhancement method based on curvelet transform (CVT), which is able to find out edge direction The proposed method (PM) calculates the maximum value by ridgelet coefficients on each angular line, derived from the sub-step of the CVT, and the real edge direction is determined by local maxima selection after finding the azimuth of this value In addition, selective sharpening is performed according to the feature information of edge Experimental results have shown that the PM is comparable with conventional methods in terms of edge intensity, recognition rate, and peak signal-to-noise ratio

Multi-scale fusion algorithm of intensity and polarization-difference images based on edge information enhancement

Abstract: To better integrate complementary and redundant information from different source images, improve the edge information, and facilitate the target detection. A multi-scale fusion algorithm of intensity and polarization-difference (PD) images based on edge information enhancement is proposed. Firstly, intensity images are obtained by the polarization information analysis method. PD images are obtained by the adaptive polarization-difference imaging approach based on the principle of minimum mutual information. Secondly, guided filter, affine transformations and Block-Matching and 3D filtering are embedded in visibility enhancement to improve the intensity and PD images. Thirdly, the two images are decomposed into high-frequency and low-frequency images by the dual-tree complex wavelet transform (DT-CWT). The high-frequency and low-frequency images are fused by the fusion rules based on edge detection and the regional variance matching degree respectively. Finally, the fusion image is obtained by the inverse DT-CWT. Experimental results demonstrate that fusion images of the proposed algorithm are significantly improved in information entropy, average gradient, and spatial frequency. Compared with the existing methods, it can achieve a better edge enhancement for images in a turbid medium.

Low dose cone-beam computed tomography reconstruction via hybrid prior contour based total variation regularization (hybrid-PCTV).

Abstract: Background Previously, we developed a prior contour based total variation (PCTV) method to use edge information derived from prior images for edge enhancement in low-dose cone-beam computed tomography (CBCT) reconstruction. However, the accuracy of edge enhancement in PCTV is affected by the deformable registration errors and anatomical changes from prior to on-board images. In this study, we develop a hybrid-PCTV method to address this limitation to enhance the robustness and accuracy of the PCTV method. Methods Planning-CT is used as prior images and deformably registered with on-board CBCT reconstructed by the edge preserving TV (EPTV) method. Edges derived from planning CT are deformed based on the registered deformation vector fields to generate on-board edges for edge enhancement in PCTV reconstruction. Reference CBCT is reconstructed from the simulated projections of the deformed planning-CT. Image similarity map is then calculated between reference and on-board CBCT using structural similarity index (SSIM) method to estimate local registration accuracy. The hybrid-PCTV method enhances the edge information based on a weighted edge map that combines edges from both PCTV and EPTV methods. Higher weighting is given to PCTV edges at regions with high registration accuracy and to EPTV edges at regions with low registration accuracy. The hybrid-PCTV method was evaluated using both digital extended-cardiac-torso (XCAT) phantom and lung patient data. In XCAT study, breathing amplitude change, tumor shrinkage and new tumor were simulated from CT to CBCT. In the patient study, both simulated and real projections of lung patients were used for reconstruction. Results were compared with both EPTV and PCTV methods. Results EPTV led to blurring bony structures due to missing edge information, and PCTV led to blurring tumor edges due to inaccurate edge information caused by errors in the deformable registration. In contrast, hybrid-PCTV enhanced edges of both bone and tumor. In XCAT study using 30 half-fan CBCT projections, compared with ground truth, relative errors (REs) were 1.3%, 1.1% and 0.9% and edge cross-correlation were 0.66, 0.68 and 0.71 for EPTV, PCTV and hybrid-PCTV, respectively. Moreover, in the lung patient data, hybrid-PCTV avoided the wrong edge enhancement in the PCTV method while maintaining enhancements of the correct edges. Conclusions Hybrid-PCTV further improved the robustness and accuracy of PCTV by accounting for uncertainties in deformable registration and anatomical changes between prior and onboard images. The accurate edge enhancement in hybrid-PCTV will be valuable for target localization in radiation therapy.

Partial Differential Equation-Based Enhancement and Crack Detection

Abstract: This paper presents an effective partial differential equation- (PDE-) based preprocessing algorithm for automated image-based crack detection. The proposed formulation combines various relevant and multiple processes such as contrast and selective edge enhancement in addition to edge-preserving smoothing to enhance the image prior to detection. The approach is adaptive and controlled by reliable image metrics to determine the stopping time of the PDE ensuring optimum results for various images. Additionally, a simplified thresholding algorithm based on local global maximum gradient matching is used to extract the crack features from the image. The proposed scheme does not require arbitrary or manually tuned parameters nor a large dataset for training to obtain good results. Experiments indicate that the proposed approach performs better when compared to several other algorithms in the literature.

A Preprocessing Algorithm Based on Heterogeneity Detection for Transmitted Tissue Image

Abstract: In hyperspectral transmission imaging (mainly refers to transmission breast imaging), the strong scattering characteristics of the tissue cause the blurred image and weak image signal, which hinders heterogeneity detection in tissue. In this paper, we designed the simulation experiment of collecting phantom images, and a joint preprocessing algorithm suitable for transmission tissue image is proposed and verified: the algorithm combining single channel frame accumulation and edge enhancement algorithm. The result shows that the PSNR of the phantom image is increased to 57.3 dB and the edge of phantom image processed by the joint preprocessing algorithm is preserved; the standard deviation is 19.8998 higher than original image, that is, the contrast is greatly improved. In our previous work, the detection accuracy of the image processed by this algorithm is higher than that without processed when the image detected in object detection algorithm based on deep learning; the mAP reaches 99.9%. Therefore, the preprocessing algorithm in this paper provides a highly compatible and easier preprocessing method for heterogeneity detection of multispectral tissue images, which improves the detection accuracy of heterogeneity to some extent. And it may be a new way to improve the quality of such multispectral and hyperspectral transmission tissue images.

Remote Sensing Image Enhancement via Robust Guided Filtering

Abstract: Remote sensing image enhancement methods have to preserve the original reflectance values as possible as they can, whereas emphasising the edges and increasing the contrast. In this study, a remote sensing image enhancement method based on robust guided filtering is proposed. We propose a multiscale decomposition with the robust guided filtering to obtain the approximation and detail layers of the image. Then the extracted details are amplified and added to the approximation layer to obtain the enhanced image. Both visual and quantitative comparisons show that the proposed method has a better preservation capability than the former methods, as well as a better contrast improvement along-with edge enhancement.

Infrared upconverted image edge enhancement using spiral phase filter

Abstract: We present a theoretical and experimental demonstration of infrared upconverted image edge enhancement, acquired with quasi-phase-matching for the sum-frequency conversion process and a spiral phase filter. By illuminating a transmission mask with a 1559.5 nm Gaussian beam to create an infrared image and pumped with a 1064 nm vortex beam, an upconverted edge-enhanced image at 632.5 nm is generated. The theoretical model for the process is derived, which well explains the deviation of experimental results. The proposed technique can be further adapted for other spectral regions and nonlinear optical processes.

Advances of image edge enhancement based on vortex filtering

Abstract: As an important means of image processing, the edge enhancement techniques play an important role in amplitude-contrast and phase-contrast objects imaging. The vortex filtering techniques based on radial Hilbert transform have attracted much attention because it can achieve isotropic edge enhancement. However, the classical vortex filtering causes background noise and contrast reduction due to diffraction caused by central singularities and sharp edges. In recent years, many research groups have proposed new types of vortex filters for vortex filtering side lobe suppression. In addition, the isotropic and anisotropic edge enhancement techniques based on vortex filtering have also developed rapidly. In this paper, several methods for suppressing vortex side lobes were summarized in recent years, including Laguerre Gaussian amplitude modulation, Bessel-like amplitude modulation, and Airy amplitude modulation. What's more, from two aspects:scalar vortex filtering and vector vortex filtering, the isotropic and anisotropic edge enhancement methods and progress were reviewed.

Image enhancement method and image enhancement apparatus

Abstract: Disclosed are an image enhancement method and an image enhancement apparatus which can realize the edge enhancement for an image generated after a demosaicing process according to local characteristics of an input image (ie the image sharpening) and can realize the brightness noise suppression and the chroma noise suppression for the image Thus, by using the image enhancement method and the image enhancement apparatus provided by the present disclosure, clear images can be generated

High-contrast anisotropic edge enhancement free of shadow effect.

Abstract: We propose a Bessel-like composite vortex filter to perform high-contrast and power-controlled anisotropic edge enhancement with shadow-effect-free and low background noise. The background noise, which is commonly found and strongly decreases the filtered image quality in previous anisotropic vortex filters, is effectively reduced by suppressing the side lobes of the system point spread function, thereby increasing the image edge contrast to 0.98. The shadow effect is totally eliminated by keeping the radial symmetry of the filtering process, which makes edges sharper and improves image resolution. By introducing a weighting factor between two opposite vortex filter components, the power of edge enhancement becomes controllable. Numerical simulations and experimental results prove that the proposed filter achieves higher-contrast edge enhancement for both phase-contrast and amplitude-contrast objects.

Edge enhancement of IBP reconstruction by using sharp infinite symmetrical exponential filter

Abstract: This study contributes to provide an enhancement technique for improving the Iterative Back Projection (IBP) Super Resolution technique by using the Sharp Infinite Symmetrical Filter (SISEF). Theoretically, the IBP technique operates as minimizer the error reconstruction iteratively until it refined the High Resolution (HR) image. However, due to iterative manner and lack of edge guidance during the back projection operation, this technique has suffered from produced the ringing artefact on the HR image appearances. Additionally, the IBP reconstruction also demands for large number iteration for accomplishing the prediction HR image. This problem arose when the IBP estimator tended to oscillate at the same solution frequently. In order to overcome these constraints, the SISEF is deployed as regulator to improve the IBP estimator with provides an accurate edge information for enhancing the edge image and reduce the ringing artefacts. Fortunately, highly precision of edge information provided by SISEF capable to reduce amount of estimation process repetition.

Image super-resolution reconstruction method and system and computer storage medium

Abstract: The invention relates to an image super-resolution reconstruction method and system, and a computer storage medium. The image super-resolution reconstruction method comprises the following steps: S1,reconstructing an original image into an image with a fixed size, obtaining an original high-resolution image, and carrying out the interpolation downsampling of the original high-resolution image, and obtaining a low-resolution image; S2, performing super-resolution reconstruction based on edge enhancement on the low-resolution image based on a generative network to obtain a super-resolution image; and S3, performing authenticity discrimination on the super-resolution image based on the discrimination network and the original high-resolution image. According to the image super-resolution reconstruction method, a single low-resolution image is expressed through edge detail information enhancement, and an edge enhancement fusion network is added into an original super-resolution reconstruction generation network, so that the super-resolution reconstruction performance of the image is improved, and a clearer reconstructed image is obtained; and in addition, the discrimination network canalso improve the reconstruction performance of the edge enhancement generative adversarial network.

Real-Time Video Edge Enhancement IP Core Based on FPGA and Sobel Operator

Abstract: In order to solve the problems of inefficient retrieval target, visual fatigue and complex algorithm implementation in the monitoring system, this paper proposes an innovative method of image edge enhancement by superimposing edge detection image and source image. Based on this idea, an IP module of edge detection and visual enhancement was designed. This module realized Sobel edge detection algorithm, video alignment and video superposition. I did algorithm verification and code generation on Matlab, and generated IP core in Vivado development environment of Xilinx. The experimental results showed that the system could achieve real-time video processing and enhance the effect of displaying video targets.

Apodized Fourier single-pixel imaging by changing the contrast of patterns using Norton-Beer functions

Abstract: Single-pixel imaging (SPI) has attracted a lot of attention in the last two decades, not only for its imaging ability using a low-level or non-visible light but also for imaging through scattering media. As a special method, Fourier SPI (FSI) projects sinusoids on the object and measures Fourier spectrum using a single-pixel detector. As the information of many natural objects is concentrated in lower frequencies in Fourier space, fewer measurements are required for imaging these objects using FSI. However, the sub-sampling of the Fourier space causes ringing artifacts in the retrieved images. In this paper, we propose changing the contrast of different sinusoids based on Norton-Beer (NB) functions and show its ability to reduce ringing artifacts ('apodized' FSI). This method is investigated using one- and two-dimensional simulations by implementing NB profiles in low-pass and band-pass modes. In this way, the two modes of apodized imaging and edge enhancement are performed during the measuring process. The feasibility of these modes is experimentally proved for a simple and real object. Furthermore, different ways of using varying-contrast patterns are compared with common post-process apodization. We believe that our study can be interesting for both SPI and image processing communities.

Fractional Order Edge Detection Method

Abstract: Edge detection is a key topic in the field of image processing and computer vision. It plays a crucial role in image segmentation, pattern classification and other work. A new fractional order edge detection method is proposed in this paper. This operator combines CRONE operator and compound derivative operator, and a one-dimensional fractional-order integral filter in a complex derivative operator is converted into a two-dimensional fractional-order integral filter, and a two-dimensional differential mask is constructed by extending the horizontal and vertical components of the CRONE operator differential template. Then, the integral filter and the differential mask are simultaneously used for edge detection. The experimental results show that this operator can extract a target with clear edges and complete structures for all kinds of noise and non-noise pictures. Compared with CRONE operator and composite derivative operator, detection selectivity and noise immunity are improved, and edge enhancement and structure retention are realized.

A Fuzzy Approach to Recognize Face Using Contourlet Transform

Abstract: Face recognition addresses identification, verification, and authentication in biometric-based security systems. This work enhances the contrast and edges in face images and recognizes the face using contourlet transform and fuzzy rules. Contourlet transformed image provides multiscale and directional information. The transformed image is divided into low-pass image (low-frequency image) and band-pass image (high-frequency image). The low-pass image is enhanced using fuzzy-based histogram specification since it deals with contrast. Band-pass image contains detailed information about the edges of the image and are enhanced using fuzzy rules and morphological gradient operators. The proposed system achieves the accuracy rate of 99.81% and 99.35% on Yale-B and JAFEE dataset, respectively, which is better than the existing curvelet and wavelet transform-based recognition. The incorporation of fuzzy rules enhances the mean intensity value of the edges to 34.19, which is better than Canny, Sobel, Prewitt, Robert and Laplacian edge detection techniques. Finally Discriminant Correlation Analysis (DCA) feature level fusion is applied to fuse enhanced edge intensities and histogram features for Support Vector Machine (SVM) classification.

Edge Enhancement for Image Segmentation Using a RKHS Method

Abstract: Image segmentation has many important applications, particularly in medical imaging. Often medical images such as CTs have little contrast in them, and segmentation in such cases poses a great challenge to existing models without further user interaction. In this paper we propose an edge enhancement method based on the theory of reproducing kernel Hilbert spaces (RKHS) to model smooth components of an image, while separating the edges using approximated Heaviside functions. By modelling using this decomposition method, the approximated Heaviside function is capable of picking up more details than the usual method of using the image gradient. Further using this as an edge detector in a segmentation model can allow us to pick up a region of interest when low contrast between two objects is present and other models fail.

An Inner-Outer Iterative Method for Edge Preservation in Image Restoration and Reconstruction.

Abstract: We present a new inner-outer iterative algorithm for edge enhancement in imaging problems. At each outer iteration, we formulate a Tikhonov-regularized problem where the penalization is expressed in the 2-norm and involves a regularization operator designed to improve edge resolution as the outer iterations progress, through an adaptive process. An efficient hybrid regularization method is used to project the Tikhonov-regularized problem onto approximation subspaces of increasing dimensions (inner iterations), while conveniently choosing the regularization parameter (by applying well-known techniques, such as the discrepancy principle or the ${\mathcal L}$-curve criterion, to the projected problem). This procedure results in an automated algorithm for edge recovery that does not involve regularization parameter tuning by the user, nor repeated calls to sophisticated optimization algorithms, and is therefore particularly attractive from a computational point of view. A key to the success of the new algorithm is the design of the regularization operator through the use of an adaptive diagonal weighting matrix that effectively enforces smoothness only where needed. We demonstrate the value of our approach on applications in X-ray CT image reconstruction and in image deblurring, and show that it can be computationally much more attractive than other well-known strategies for edge preservation, while providing solutions of greater or equal quality.

image enhancement method based on improved non-subsampled Contourlet transformation

Abstract: The invention requests to protect an image enhancement method based on improved non-subsampled Contourlet transform (NSCT). The method comprises the following steps: firstly, carrying out NSCT on an image to obtain low-pass sub-bands and band-pass sub-bands in various scales and directions; carrying out linear enhancement processing on the low-pass sub-band, so that the overall contrast of the image is improved; for a band-pass sub-band, adaptively determining a denoising threshold value of each sub-band according to energy distribution, and a weak edge enhancement algorithm is provided, so that the effects of enhancing detail texture and suppressing noise are achieved. and acquiring a clear palm vein image through Contourlet inverse transformation. And finally, the fractured part of the palm vein is bridged through a Gabor filter bank. Experimental results show that the palm vein detail texture information is effectively enhanced through the algorithm, and the contrast ratio, the information entropy, the average gradient and the variance are improved to 47.9, 9.1, 5.1 and 2594 respectively.

Round hole pose visual detection method based on image super-resolution reconstruction

Abstract: The invention discloses a round hole pose binocular vision detection method based on image super-resolution reconstruction. The method includes: placing the round hole part in a common view of the left and right cameras, photographing the round hole part through the left and right cameras to obtain two images of the left and right images respectively, and performing distortion correction processing on the two images; carrying out super-resolution reconstruction facing edge enhancement on the left image and the right image after distortion correction to obtain high-resolution images; processingthe reconstructed high-resolution images to obtain respective circular hole contours; obtaining round hole poses, namely coordinates of the circle center of the round hole and normal vector pointingof the plane where the round hole is located through round hole contour processing of the left image and the right image. According to the method, the problem of insufficient imaging resolution in theround hole pose visual detection process can be effectively solved, the detection precision is improved, the result is reliable, the hardware performance is prevented from being improved, and the cost is reduced.

Image processing system, computer program, and image processing method

Abstract: To specify and emphasize the edge of a character in an object image appropriately.SOLUTION: An image processing system executes emphasis processing for emphasizing the edge of a specific kind of character, by using object image data. The specific kind of character is a character of first color, located on the backdrop of second color different from the first color. The image processing system determines whether or not a target area including the target pixel is a character area, by using a machine learning model, determines whether or not specific determination conditions, indicating that the target pixel must have the first color, are satisfied by using the value of the target pixel, and when a determination is made that the target area is the character area, and the target pixel satisfies the specific determination conditions, the target pixel is specified as the first pixel that must have the first color, the second pixel located around the specified first pixel and must have second color is specified, thus creating edge enhancement image data where a pixel corresponding to the specified first pixel has the first color, and a pixel corresponding to the specified second pixel has the second color.SELECTED DRAWING: Figure 5