Image Edge Detection Algorithm Research Articles

A New Medical Image Edge Detection Algorithm Based on BC-ACO

Taking the improved ant colony algorithm based on bacterial chemotaxis as a means, this paper proposes one new swarm intelligence optimization algorithm to solve the medical image edge detection problem. The improved ant colony algorithm based on bacterial chemotaxis mainly aims at the shortcoming that the basic ant colony algorithm lacks initial pheromone, and combines bacterial chemotaxis algorithm with basic ant colony algorithm. Firstly, feasible better solution can be found through bacterial chemotaxis algorithm and fed back as initial pheromone. Then ant colony algorithm is implemented to search for the global optimal solution. The algorithm test indicates that the improved ant colony algorithm is more effective in the aspects of searching precision, reliability, optimization speed and stability compared with basic ant colony algorithm. Finally, the improved ant colony algorithm is applied into the edge detection of medical image. It can be seen from the computer simulation that compared with other operators and basic ant colony algorithm on the issue of solving medical image edge detection, the improved ant colony algorithm has superiority and the detected edge is clearer.

草地图像边缘检测算法研究

本文针对草地图像边缘检测进行研究，传统的草地图像边缘检测算法，如canny算法，不仅边缘不够清晰，而且运算时间较长，不能达到智能机器人对实时性的要求。本文运用k-means算法对色彩进行分类进而选定绿色为目标色进行提取，再利用膨胀和腐蚀运算，选取合适的结构元素对图像进行填充和细化，通过实验对比其他传统边缘分割方法，探讨了数学形态学在割草机器人工作区域划分中的重要应用。实验证明，本文选用的边缘检测策略不仅能够清晰准确的识别出草地边缘，而且相比传统的边缘检测算子，运算更快，实用性更强。 This paper aims at a study of lawn image edge detection. Traditional grass image edge detection algorithm such as the canny, its results are not clear enough and the operation time is longer, which can not meet the real-time requirements of intelligent robots. In this paper, the k-means algorithm is used to classify the colors and select the green as the target color. Then, the appro-priate structural elements are selected by expansion and corrosion calculations. Finally, the image is filled and refined using this structural element. This paper discusses the important application of mathematical morphology in the division of working area of mowing robot by comparing other traditional edge segmentation methods. In conclusion, the algorithm presented in this article not only can identify the edge of the grass accurately, but also faster operation and more practical than traditional algorithms.

Curve Fitting Based Sub-pixel Edge Detection Algorithm

A novel high-accuracy image edge detection algorithm at sub-pixel level based on curve fitting of gauss function is proposed. Firstly, approximate positioning of edge detection is carried out by means of canny operator to find location of edge point at pixel level; Secondly, gauss function is employed as fitting function and least square method is employed as curve fitting method to find location of edge point at sub-pixel level. The experiment results show that the proposed algorithm can position accurate edge at sub-pixel level, and has strong robustness to the noise and shorter running time, and effectively improve the positioning precision of image edge extraction.

Particle Swarm Optimization based Edge Detection Algorithms for Computer Tomography Images

Background/Objectives: Detection of image edges plays an important role in medical image processing, segmentation and computer vision applications. Methods: It is necessary to have a better edge detection algorithm for the diagnosis of the abnormalities in the images and based on the diagnosis, a treatment procedure can be decided. The existing edge detection algorithms like Canny and Sobel are lack in Edge Preservation Factor (EPF) and they pose a low Signal to Noise Ratio (SNR). These algorithms are not good for noisy images. Findings: To overcome these issues, in this paper a Particle Swarm Optimization (PSO) based algorithm is proposed. Improvements/Applications: Experimental result proves that the PSO is better when compared with the existing edge detection techniques.

Novel VLSI Architectures for Image Segmentation and Edge Detection Algorithm

Field programmable gate arrays (FPGA) are the devices which can be easily employed for image and video processing applications. FPGA implementation is always faster than any other digital signal processor due to its parallel image processing capabilities. This paper proposes the hardware cosimulation model of different traffic signs carried out using Xilinx System Generator tool. The proposed system uses image pre-processing, color conversion, thresholding and edge detection of still grayscale images taken from a distance of 50m. Experimental results show that hardware co-simulation was successful in SPARTAN-3E DSP xc6slx45-3csg324 development board operating at 100MHz system clock. General Terms Image pre-processing, Traffic Signs, Image Segmentation, Edge detection.

A Color Image Edge Detection Algorithm Based on Color Difference

Although image edge detection algorithms have been widely applied in image processing, the existing algorithms still face two important problems. On one hand, to restrain the interference of noise, smoothing filters are generally exploited in the existing algorithms, resulting in loss of significant edges. On the other hand, since the existing algorithms are sensitive to noise, many noisy edges are usually detected, which will disturb the subsequent processing. Therefore, a color image edge detection algorithm based on color difference is proposed in this paper. Firstly, a new operation called color separation is defined in this paper, which can reflect the information of color difference. Then, for the neighborhood of each pixel, color separations are calculated in four different directions to detect the edges. Experimental results on natural and synthetic images show that the proposed algorithm can remove a large number of noisy edges and be robust to the smoothing filters. Furthermore, the proposed edge detection algorithm is applied in road foreground segmentation and shadow removal, which achieves good performances.

Study on Improved Algorithm for Image Edge Detection Based on Genetic Fuzzy

Study on Improved Algorithm for Image Edge Detection Based on Genetic Fuzzy

Study on Defects Edge Detection in Infrared Thermal Image Based on Ant Colony Algorithm

Edge extraction is an important part in the detection of infrared thermal images. Ant colony algorithm has the characteristics of high efficiency, high noise suppression, and comprehensive information of edge information. The basic principle of ant colony algorithm is analyzed. An ant colony optimization algorithm for image edge detection is established. And to have defective parts for analysis of infrared thermography The ant colony algorithm and the classical Canny operator are compared and analyzed. The experimental results show that the algorithm has high efficiency, comprehensive information and high computational efficiency.

An improved teaching–learning based robust edge detection algorithm for noisy images

This paper presents an improved Teaching Learning Based Optimization (TLO) and a methodology for obtaining the edge maps of the noisy real life digital images. TLO is a population based algorithm that simulates the teaching–learning mechanism in class rooms, comprising two phases of teaching and learning. The ‘Teaching Phase’ represents learning from the teacher and ‘Learning Phase’ indicates learning by the interaction between learners. This paper introduces a third phase denoted by “Avoiding Phase” that helps to keep the learners away from the worst students with a view of exploring the problem space more effectively and escaping from the sub-optimal solutions. The improved TLO (ITLO) explores the solution space and provides the global best solution. The edge detection problem is formulated as an optimization problem and solved using the ITLO. The results of real life and medical images illustrate the performance of the developed method.

Improving the performance of optical systems for a tool presetter

A tool presetter is a non-contact precision measuring instrument that is used to measure the parameters of NC cutting tools rapidly and precisely. An optical system is its kernel component of non-contact measurement which directly influences measuring accuracy. It is a limited luxury to increase the measuring accuracy only through the use of a better optical system, it is more effective to increase the measuring accuracy through software and algorithms. The main algorithms that influence the measuring accuracy of an optical system include: image edge detection algorithm and image positioning algorithm. This paper provides analysis of these and puts forth two newly developed algorithms for improving the measuring accuracy of a tool presetter. The first algorithm is image edge detection based on subpixels that increases the edge positioning accuracy more than ten times. The second one is uniformity compensation for whole view measurement that is able to capture accurate real pixel size making image movement more precise, which further increases the measuring accuracy. These two algorithms are tested in CoVis software and the results demonstrate that the total measuring accuracy of the tool presetter is dramatically improved to 2 µm.

A Doubly Adaptive Algorithm for Edge Detection in 3D Images

This paper proposes a new algorithm (DA3DED) for edge detection in 3D images. DA3DED is doubly adaptive because it is based on the adaptive algorithm EDAS-1 for detecting edges in functions of one variable and a second adaptive procedure based on the concept of projective complexity of a 3D image. DA3DED has been tested on 3D images that modelize real problems (composites and fractures). It has been much faster than the 1D edge detection algorithm for 3D images derived from EDAS-1.

An Effective Parallelism Topology in Ant Colony Optimization algorithm for Medical Image Edge Detection with Critical Path Methodology (PACO-CPM)

In the digital world of medical transcription involving various dimensions of processes, detecting the edge of a standard medical image for clinical research/diagnosis, telemedicine and other applicative purposes requires various efficient and effective methodologies to address the needs of the processes. Among these various meta-heuristics, as the size of the problem tends to increase along with time, the processes and their elemental techniques, proven to have been providing viable solutions appeals for reserve management and lesser computation times, with the efficiency of such algorithms and algorithmic operations to be enhanced at suitable levels of abstraction. 
 In this paper we propose an effective topological algorithm, which inhibits the characteristic features of high performance parallel enumeration in such heterogeneous computation environments. The proposed scheduler in the defined topological algorithm takes into consideration the metrics generated by As Built Critical Path (ABCP) - A hybrid methodological process. These metrics are re-initialized and processed to address the management of resources and the realization of search space. We also propose a methodology for shared memory access by the ants to perform parallel computation and as well implement the optimization factor in detecting the edge. An in-depth analysis with respect to the Speedup factor and the Execution time metrics are analyzed for various scenarios under consideration. The differentiations are evaluated and plotted for further futuristic analysis

VLSI Design of a Depth Map Estimation Circuit Based on Structured Light Algorithm

In this paper, depth map estimation circuit design based on structured light is proposed, wherein a projection light source and an image sensor are utilized in combination to achieve a depth map estimation chip, an accurate, low complex circuit is presented to measure the depth value of an object, and it is applied to 3-D television through depth image-based rendering technology to implement a multiview image display system. The chip that integrates image preprocessing, object segmentation, edge detection, and depth map quantization algorithms performs depth map estimation of objects accurately and quickly. Besides, the effect of human visual sensing effect is taken into consideration and the presented chip achieves a depth map quantified according to the nonlinear depth value in compliance with human visual system. Measurement results show that the chip that is verified using a Taiwan Semiconductor Manufacturing Company 0.18- $\mu $ m 1P6M CMOS process operates at 83.3 MHz with 19 845 gate counts and performs real time depth map estimation.

Research on the improvement of image edge detection algorithm based on artificial neural network

Image edge detection is an essential basis of computer vision that has made rapid progress these years. Given the importance of the edge detection and the maturity of ANN (artificial neural network), we provide a research paper on the algorithms of image edge detection based on ANN. Firstly, we review the classic methods of edge detection and introduce some new methods proposed these years. Secondly, the foundations of ANN are briefly introduced. Subsequently, we present a traditional edge detection method based on ANN and summarize some disadvantages of this method. Finally, a new edge detection method based on ANN and parallel computing is put forward. The new method is superior to the old one in the efficiency and accuracy of detection.

Ultrasonic C-scan detection for stainless steel spot welding based on wavelet package analysis

An ultrasonic test of spot welding for stainless steel is conducted. Based on wavelet packet decomposition, the ultrasonic echo signal has been analyzed deeply in time - frequency domain, which can easily distinguish the nugget from the corona bond. The 2D C-scan images produced by ultrasonic C scan which contribute to quantitatively calculate the nugget diameter for the computer are further analyzed. The spot welding nugget diameter can be automatically obtained by image enhancement, edge detection and equivalent diameter algorithm procedure. The ultrasonic detection values in this paper show good agreement with the metallographic measured values. The mean value of normal distribution curve is 0.006 67, and the standard deviation is 0.087 11. Ultrasonic C-scan test based on wavelet packet signal analysis is of high accuracy and stability.

A Tree-based Approach Towards Edge Detection of Medical Image using MDT

To develop any autonomous computerized algorithm for abnormality detection based on medical image analysis essentially requires a robust segmentation algorithm. To achieve this goal of accurate segmentation of medical image it requires an effective edge detection algorithm. Generalized edge detection algorithms like Sobel, Canny, though effective in normal images but often fails in case of medical images. Medical images obtained from devices such as Ultrasonography, X-Ray, CT and MRI exhibit diverse image characteristics but are essentially collection of intensity variations from which specific abnormalities are needed to be isolated. Homogeneity enhancement, followed by edge detection and resulting segmentation is essential prerequisite for all medical image analysis system. This paper proposes a robust medical image enhancement and edge detection algorithm that is equally effective with most medical images that are popular now-a-days yielding excellent segmentation results in all cases.

Detection of mesoscale thermal fronts from 4 km data using smoothing techniques: Gradient-based fronts classification and basin scale application

In order to optimize frontal detection in sea surface temperature fields at 4km resolution, a combined statistical and expert-based approach is applied to test different spatial smoothing of the data prior to the detection process. Fronts are usually detected at 1km resolution using the histogram-based, single image edge detection (SIED) algorithm developed by Cayula and Cornillon in 1992, with a standard preliminary smoothing using a median filter and a 3×3pixel kernel. Here, detections are performed in three study regions (off Morocco, the Mozambique Channel and north-western Australia) and across the Indian Ocean basin using the combination of multiple windows (CMW) method developed by Nieto, Demarcq and McClatchie in 2012 which improves on the original Cayula and Cornillon algorithm. Detections at 4km and 1km resolution are compared.Fronts are divided into two intensity classes (“weak” and “strong”) according to their thermal gradient. A preliminary smoothing is applied prior to the detection using different convolutions: three type of filters (median, average and Gaussian) combined with four kernel sizes (3×3, 5×5, 7×7, and 9×9pixels) and three detection window sizes (16×16, 24×24 and 32×32pixels) to test the effect of these smoothing combinations on reducing the background noise of the data and therefore on improving the frontal detection. The performance of the combinations on 4km data are evaluated using two criteria: detection efficiency and front length. We find that the optimal combination of preliminary smoothing parameters in enhancing detection efficiency and preserving front length includes a median filter, a 16×16pixel window size, and a 5×5pixel kernel for strong fronts and a 7×7pixel kernel for weak fronts. Results show an improvement in detection performance (from largest to smallest window size) of 71% for strong fronts and 120% for weak fronts. Despite the small window used (16×16pixels), the length of the fronts has been preserved relative to that found with 1km data.This optimal preliminary smoothing and the CMW detection algorithm on 4km sea surface temperature data are then used to describe the spatial distribution of the monthly frequencies of occurrence for both strong and weak fronts across the Indian Ocean basin. In general, strong fronts are observed in coastal areas; whereas weak fronts, with some seasonal exceptions, are mainly located in the open ocean.This study shows that adequate noise reduction achieved by a preliminary smoothing of the data considerably improves the frontal detection efficiency as well as the global quality of the results. Consequently, the use of 4km data enables frontal detections similar to 1km data (using a standard median 3×3 convolution) in terms of detectability, length and location. This method is easily applicable to large regions or at the global scale, with far less constraints of data manipulation and processing time using 4 km data relative to 1 km data.

A Traceable Metrological Method with Nanometer Scale Resolution for Micro-Structure

Micro-structure dimension metrology is a grand challenge to current metrological methods and tools. In this paper, a retraceable metrological scanning electron microscopy (M-SEM) system with precision stage and laser interferometer is presented in detail. The double stages structure is used to realize both sample positioning in 50mm×50mm range and accuracy imaging in several tens of micron scale. In order to acquiring metrological scanning image, the control system based on digital signal processing (DSP) is constructed. Furthermore, this paper focuses on demonstrating a metrological SEM image edge detection algorithm which is the essential part of the metrological SEM system to realize the traceable metrology of line width.

Industrial Flame Edge Detection Algorithm Based on Gray Dominant Filter

Industrial furnace flame detection is directly related to the safety and economic operation of boiler. The flame edge detection is one of the most key parts of the flame detection. At present, there are many edge detection algorithms for normal object but few for industrial flame edge detection which cannot provide fully support for furnace flame combustion stability, flame 3D reconstruction and flame temperature field reconstruction. One new industrial flame image edge detection algorithm based on industrial flame image characteristics is proposed in this paper. This algorithm can effectively remove noise level in flame image and well maintain flame image edge features, compute the gradients from multiple-directions for entirely detecting flame edge information. Moreover, this algorithm is verified by experiment in this paper to present high performance in resisting noise, and clearly see continuous flame edge curve, which reveals better effect in industrial flame edge detection than other edge detection algorithms.

On Intuitionistic Fuzzy Divergence Measure with Application to Edge Detection

Abstract In the present communication, we propose an exponential entropy of order β for an intuitionistic fuzzy set and a new intuitionistic fuzzy divergence measure for the intuitionistic fuzzy sets along with their proof of validity. Further, a new algorithm for image edge detection has been framed on the basis of the proposed intuitionistic information measures. The implementation and applicability of the proposed algorithm have been illustrated by taking different sample images. The obtained results have been finally analyzed and found to be better than the existing ones.