Application of new advanced CNN structure with adaptive thresholds to color edge detection

Edge detection, especially from colour images, plays very important roles in many applications for image analysis, segmentation and recognition. Most existing methods extract colour edges via fusing edges detected from each colour components or detecting from the intensity image where inter-component information is ignored. In this study, an improved method on colour edge detection is proposed in which the significant advantage is the use of inter-component difference information for effective colour edge detection. For any given colour image C, a grey D-image is defined as the accumulative differences between each of its two colour components, and another grey R-image is then obtained by weighting of D-image and the grey intensity image G. The final edges are determined through fusion of edges extracted from R-image and G-image. Quantitative evaluations under various levels of Gaussian noise are achieved for further comparisons. Comprehensive results from different test images have proved that this approach outperforms edges detected from traditional colour spaces like RGB, YCbCr and HSV in terms of effectiveness and robustness.

Cognitive radio is one of the most promising technologies due to the spectrum scarcity, especially in the microwave band. Spectrum sensing forms an essential functionality for CR systems. However, such detection performance is usually compromised by shadowing and fading channel conditions. Cooperative sensing is one of the crucial solutions to overcome degraded detection performance. A distributed architecture for the processing and fusion of sensing information is proposed to improve sensing performance and reduce reporting error. The decision fusion for cooperated users could be complex in dense network scenarios and reported sensing traffic may require significant bandwidth. The paper presents a new cooperative distributed PUs detection and proposes dynamic threshold based on controlled probability of false alarm to enhance sensing efficiency and reliability in a Rayleigh fading environments. A cooperative distributed PUs detection is realized by fusion node (FNs) that dynamically selected from the group members. The adaptive detection threshold is computed dynamically using the link quality indicators (LQIs) of the sensing channels. Moreover, the proposed scheme can significantly minimize the typically transmitted bits in the reporting channels. This work also deliberated the design parameters of the CR on the performance of fusion values. The simulation evaluation presents that the adapted threshold considerably improves the performance of the distributed cooperative sensing (DCS) process. The simulation results verified that the error was minimized remarkably. The ROC graph is notably enhanced for the sensing process in term of probability of detection and probability of false alarm. Finally, it was presented that with the proposed scheme the sensitivity requirements could be significantly enhanced up to 0.95.

Radar sensors are an attractive technology for different kinds of applications, especially, in the case of safety driving systems. This research deals with designing the target return signal detection algorithm for radar sensors using the generalized detector (GD) with adaptive detection threshold based on a sliding window technique to estimate the noise power. The general GD structure is introduced, and the proposed method to define the adaptive detection threshold is assumed to be employed by 24 GHz frequency modulation continuous wave (FMCW) radar sensor and the simulation results show the better detection performance in comparison with the cell averaging constant false alarm rate (CA-CFAR) detector one which is widely used by radar sensor systems for car applications.

Segmentation based on contour detection is a relevant stage before image interpretation or pattern recognition. This paper is concerned with color image filtering and color edge detection. These two techniques utilize the Dempster-Shafer 91968. 1976) theory. After the description of color image filtering which generalizes Nagao's (1979) filter, a method for computing the orientation and magnitude of a gradient on color images is presented. Both filtering and edge detection use a 5/spl times/5 window. Some choices in the algorithms permit one to reduce the computing complexity of evidential theory. Finally, a method which extracts the local maxima of gradient is described.

Step detection for smartphones plays an important role in the pedestrian dead reckoning (PDR) for indoor positioning. Aiming at the problem of low step detection accuracy of smartphones in complex unconstrained states in PDR, smartphone-based unconstrained step detection method fusing a variable sliding window and an adaptive threshold is proposed. In this method, the dynamic updating algorithm of a peak threshold is developed, and the minimum peak value filtered after a sliding window filter is used as the adaptive peak threshold, which solves the problem that the peak threshold of different motion states is difficult to update adaptively. Then, a variable sliding window collaborative time threshold method is proposed, which solves the problem that the adjacent windows cannot be contacted, and the initial peak and the end peak are difficult to accurately identify. To evaluate the performance of the proposed unconstrained step detection algorithm, 50 experiments in constrained and unconstrained states are conducted by 25 volunteers holding 21 different types of smartphones. Experimental results show: The average step counting accuracy of the proposed unconstrained step detection algorithm is over 98%. Compared with the open source program Stepcount, the average step counting accuracy of the proposed algorithm is improved by 10.0%. The smartphone-based unconstrained step detection fusing a variable sliding window and an adaptive threshold has a strong ability to adapt to complex unconstrained states, and the average step counting accuracy rate is only 0.6% lower than that of constrained states. This algorithm has a wide audience and is friendly for different genders and smartphones with different prices.

Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Threshold setting is crucial for edge detection. Traditional threshold setting method did not use the spatial information of edge, and the detected edges are either missing or have a large number of false edges. Based on the analysis of the change trend of edge connectivity and the number of edge segment as the threshold decrease, we firstly propose an adaptive threshold setting method according to the image self-information. Then, using the adaptive threshold, the gradient map created by first order differential operator and non-max suppression is binarized into edge map. Compared with other traditional single-threshold based edge detection methods, the proposed method can detect edges that are more complete and fewer fake edges, and this method is more stable and reliable.

Smart grids are vulnerable to cyber-attacks, which can cause significant damage and huge economic losses. Generally, state estimation (SE) is used to observe the operation of the grid. State estimation of the grid is vulnerable to false data injection attack (FDIA), so diagnosing this type of malicious attack has a major impact on ensuring reliable operation of the power system. In this paper, we present an effective FDIA detection method based on residual recurrent neural network (R2N2) prediction model and adaptive judgment threshold. Specifically, considering the data contains both linear and nonlinear components, the R2N2 model divides the prediction process into two parts: the first part uses the linear model to fit the state data; the second part predicts the nonlinearity of the residuals of the linear prediction model. The adaptive judgment threshold is inferred through fitting the Weibull distribution with the sum of squared errors between the predicted values and observed values. The thorough simulation results demonstrate that our scheme performs better than other prediction based FDIA detection schemes.

The heart is a vital part of the human organ which is responsible for receiving and pumping blood throughout the body. According to statistical data held by the World Health Organization noted that heart disease accounts for 31% of human deaths worldwide. Examination of heart health conditions usually uses an echocardiography device with sound waves. In echocardiography, images have speckle noise and need a repair process. Noise speckle is the fine-grained texture-like pattern seen in echocardiography, and indeed in all modalities of clinical ultrasound. This study proposed the two and four-chamber cavity segmentation method in the heart wall cavity. Segmentation process to obtain contour the of heart cavity, required several stages. Improve the image using a median filter to reduce speckle noise, high boost filters and morphology is used to clarify information on the part of the heart cavity. Segmentation cavity using adaptive thresholding and canny edge detection filter to the image. The results of edge detection need to be improved using the region area and collinear. Contour results obtained will be reviewed for the open and closed condition of heart cavity. An iterative process is performed, with increasing high boost filter parameter values that may affect the results of the closed contour. Based on these combinations, the accuracy contour area is 89,409%, and the results of calculation the contour similarity level approach the value of 0. The results of the research have conducted contour searches on the heart wall cavity, and future work focused on the tracking process and measurement of heart contour movements using optical flow.

As the basic content of digital image processing, edge detection is increasingly applied in machine vision, face recognition, target tracking and other fields. In particular, edge detection based on Sobel operator is generally applied in industrial practices. However, most current edge detections based on PC-side serial processing are extremely arduous to satisfy real-time processing. This paper proposes FPGA implementation of eight-direction Sobel edge detection algorithm based on adaptive threshold. Specifically, an eight-direction Sobel edge detection algorithm based on adaptive threshold is presented. Subsequently, the specific process of implementing the algorithm on FPGA using the design philosophy of parallel pipeline is described. Finally, a comparison of the performance between traditional Sobel and improved algorithm reveals that the improved algorithm offers distinct advantages in accuracy and detection effectiveness, and the parallel implementation of FPGA hardware can obviously enhance the detection speed and fulfil the real-time requirement.

Image segmentation refers to a process by which a raw input image is partitioned into non-overlapping regions such that each region is homogenous and connected, and the union of no two spatially adjacent regions is homogeneous. The objective of segmentation is to simplify and change the representation of an image into something that is more meaningful and easier to analyze. This paper reviews the modified segmentation method for color images based on CIELAB Color Space and Edge detection of color images using the various edge detectors. This work aims to identify/segment different colors in an image by analyzing the CIELAB color space which enables to quantify these visual differences. This proposed method has been tested with images of various formats, size and resolution and the results are proven to be better.

We developed a dynamic microvascular edge detection method which is based on an adaptive thresholding and multijudgmental criteria. To realize the on-line measurement with video rate, we first set changeable measuring lines which are perpendicular to a microvessel axis and cover the possible edge location at a cross- section of the microvessel as a sampling window. A dynamic threshold, which can frame-by-frame automatically adapt to the change of light intensity in the sampling window, will be generated based on the on-line analysis of light intensity distribution along the measuring lines. The judgment of microvascular edges is based on the pattern characteristics of the light intensity distribution curve in the microvascular edge areas and the possible range of the microvascular diameters. Multiple criteria for the edge detection were set for accurately detecting the edges and skipping the non-edge zones to speed the edge recognizing procedure. To further improve reliability of this edge detection, a dynamic graphic indicator can be generated according to the detected vessel edge location, and simultaneously displayed with the original image. This algorithm has been successfully applied for autotracking measurement of spontaneous vasomotion in microcirculation, even when the microcirculatory image had complex background and low contrast.

We introduce a novel method of splitting up color spaces into different components and then performing edge detection on individual color planes. The two general approaches taken for this are monochromatic and vector based. Also a new color space will be introduced in this paper, which is an improved version of the PCA algorithm. By analyzing the results of these algorithms we are able to determine which color space and edge detector is best suited for each algorithm. We test these methods using a number of well known edge detectors and color spaces. All the algorithms are tested on 17 different color images (12 natural, 5 synthetic). To analyze the results we use Pratt's Figure of Merit and Bovik's SSIM measures.

The denoising of medical images degraded by various types of noises is a major problem in medical image processing. A very good tradeoff between detail preservation and noise removal is obtained while implementing with various successive filtering procedures. This paper presents a wavelet-based multiscale products thresholding and spatial based Bilateral Filter scheme for noise removal of magnetic resonance images. In the first stage, the noisy image is passed through Bilateral Filter (BF) and some amount of noise is reduced but the image becomes blurred, hence adaptive wavelet thresholding is applied with multiscale product rule in the second stage. Rather than using Wavelet Transform, Dyadic Wavelet Transform is employed. After apply the Dyadic Wavelet Transform, wavelet interscale dependencies is exploited by multiply the adjacent wavelet subbands to preserve edge structures while suppressing noise. An adaptive threshold is calculated and implemented on the multiscale products rather than on the wavelet coefficients. Hence to identify important features like edges, curves and textures the thresholding is applied to multiscale products. The proposed method for medical image denoising is performed through a recursive application of simple steps and demonstrated on a number of standard medical images. The results obtained with the proposed method outperform other methods both visually and in terms of objective quality peak-signal-to-noise ratio (PSNR).

Noise-robust color edge detector using gradient matrix and anisotropic Gaussian directional derivative matrix

Additive manufacturing (AM), or 3D printing, has revolutionized the fabrication of complex parts, but assessing their quality remains a challenge. Quality assessment, especially for the interior part geometry, relies on post-print inspection techniques unsuitable for real-time in situ analysis. Vision-based approaches could be employed to capture images of any layer during fabrication, and then segmentation methods could be used to identify in-layer features in order to establish dimensional conformity and detect defects for in situ evaluation of the overall part quality. This research evaluated five image segmentation methods (simple thresholding, adaptive thresholding, Sobel edge detector, Canny edge detector, and watershed transform) on the same platform for their effectiveness in isolating and identifying features in 3D-printed layers under different contrast conditions for in situ quality assessment. The performance metrics used are accuracy, precision, recall, and the Jaccard index. The experimental set-up is based on an open-frame fused filament fabrication printer augmented with a vision system. The control system software for printing and imaging (acquisition and processing) was custom developed in Python running on a Raspberry Pi. Most of the segmentation methods reliably segmented the external geometry and high-contrast internal features. The simple thresholding, Canny edge detector, and watershed transform methods did not perform well with low-contrast parts and could not reliably segment internal features when the previous layer was visible. The adaptive thresholding and Sobel edge detector methods segmented high- and low-contrast features. However, the segmentation outputs were heavily affected by textural and image noise. The research identified factors affecting the performance and limitations of these segmentation methods and contributing to the broader effort of improving in situ quality assessment in AM, such as automatic dimensional analysis of internal and external features and the overall geometry.