Improved Edge Detection Algorithm Research Articles

Non-contact measurement of structural dynamic displacement based on improved edge detection and video interpolation

In structural health monitoring (SHM), smartphones are increasingly used for non-contact dynamic displacement measurement using computer vision. To overcome limitations in capturing high-frame-rate data, a non-contact measurement method of structural dynamic displacement based on an improved edge detection algorithm and video frame interpolation is proposed. Initially, a smartphone is employed to capture the structure’s vibration video and then generates intermediary frames between adjacent frames that match the structure’s motion state by using a video frame interpolation algorithm to obtain a video with a high frame rate. Subsequently, the improved edge detection algorithm is applied to measure the displacement within the interpolated video. In order to address the problem that traditional edge detection may have false edges leading to the degradation of measurement accuracy, a feature point tracking technique is proposed based on the traditional edge detection technique, which effectively excludes the interference of false edges in ROI and improves the accuracy of displacement monitoring. Experimental validation on a cantilever beam and steel frame bridge demonstrates the method’s viability and precision, highlighting its effectiveness in improving displacement measurement accuracy compared to traditional methods.

PiDiNet-TIR: An improved edge detection algorithm for weakly textured thermal infrared images based on PiDiNet

In order to solve the problems such as difficulties in extracting image edge information caused by low contrast and blurred edges of thermal infrared images, a thermal infrared image edge detection algorithm PiDiNet-TIR constructed based on the PiDiNet model is proposed. On the basis of the visible light image dataset BSDS500, the visible light image is grayed out, noise is added, and contrast is reduced to construct the thermal infrared image edge dataset I R-BSDS500, which provides image data for model training and testing. Deeply study the theory of PiDiNet model, add rich convolution mechanism to its backbone network, improve the activation function, pooling layer and up-sampling module, study the SimAM attention mechanism and add it to the side network. Using the open-source thermal infrared image dataset and homemade thermal infrared images for testing, we compare and analyze the mean square error (MSE), structural similarity of image (SSIM), feature similarity of image (FSIM), and Frames Per Second (FPS)of different detection algorithms, such as HED, RCF, DexiNet, PiDiNet, and the algorithm proposed in this paper. The results of image evaluation parameters prove that the edge detection algorithm proposed in this paper has high feature extraction efficiency and feature expression ability, and the algorithm detection performance is higher than other algorithms.

Machine vision recognition system for aerospace machined parts based on edge detection

Aerospace T-shaped machined parts are varied and have small structural differences. Manual identification has the problems of low efficiency and low accuracy. In order to realize efficient and accurate classification of aerospace machining parts, we built an image acquisition platform. To improve the edge detail extraction capability, we improved the edge detection algorithm based on deep learning. Furthermore, we employed the VisionTrain software to train recognition classification models for both large classes and subclasses. We then established a cross-granularity image classification process using VisionMaster software. Experimental results show that the improved edge detection algorithm in this paper is better than the existing common algorithm. The system achieves the goal of quickly and accurately recognizing all 60 machined parts.

Precise seam tracking in robotic welding by an improved image processing approach

The intelligent welding robots have been widely developed and applied into the industrial production lines to improve the manufacturing efficiency. The main and important factor to improve the robotic welding performance, quality, and intelligence is the seam recognition accuracy. Higher industrial production and demands of higher precision in gas metal arc welding (GMAW) process have increased robot use. Vision feedback in robotic welding provides flexibility, productivity, and precision and promotes vaster range of applicability. In this case, machine vision techniques that are widely used to identify and locate the welding seam allow planning an industrial robot path. Previous investigations have proposed various approaches to address the precise tracking of welding seam curve. In majority of cases, the simultaneous uses of laser-based and optical lighting approaches to determine the location of the seam were suggested. However, complex seams remain a big challenge in robotic welding, and no definite way has been proposed to produce a precise robot path. This paper aims to develop a comprehensive robot trajectory extraction method for complex welding seam through processing of noisy images and laser data. Since the structured light on laser basis and stereo vision propose more possibility in specifying the place of the seam, this study considers a two-source processing for GMAW. A new improved edge detection algorithm is also proposed to enclose the weld zone and determine the seam and the pool parameters. To evaluate the performance of this method, experimenting different types of work pieces under random welding conditions are carried out, and the results are verified. A considerable improvement in speed and detection of error between the measured and real seam coordinates is reported.

Distance Measurement Method for Obstacles in front of Vehicles Based on Monocular Vision

This paper proposes a new method based on monocular vision to detect and range obstacles in front of the vehicle for anti-collision warning during driving. Firstly, the deep learning object detection YOLOv4 algorithm is used to detect various obstacles in front of the vehicle to obtain the category and location information of the obstacles. Then an improved edge detection algorithm is used to adjust the position of the detection frame to improve the object positioning accuracy of the detection algorithm. Next, according to the camera imaging principle and geometric relationship, conversion model from the three-dimensional coordinates of the road surface to the two-dimensional coordinates of the image plane is obtained and distance measurement is performed. Finally, the cubic curve fitting of the obtained measurement data is performed, and the distance measurement process and algorithms are optimized to improve the distance measurement accuracy. The average error in the range of 50m is 0.54m, and the average error in the range of 80m is 0.78m. Through experimental analysis and comparison, the results show that the method in this paper can achieve accurate and effective monocular vision ranging.

Based on Improved Edge Detection Algorithm for English Text Extraction and Restoration From Color Images

The superimposed text in color images is an important clue to help understand the content of the image. Extracting and translating it into a familiar language is a hot research topic in the current image field. However, because the background of the image is usually complicated, effective text extraction and restoration is very challenging. In view of the above problems, this paper proposes an English text repair and extraction algorithm for color images based on improved edge detection algorithm. Firstly, the text of the color image is repaired by the sample block-based method. Secondly, the traditional edge-based detection method is improved, and the image is grayed out, and the edge detection is performed to obtain the candidate text area. Then, using the restrictive conditions such as text color and size, the text area is filtered out to extract the target text. Finally, the text information embedded in the extracted processed color image is translated into the target language. The experimental results show that the proposed algorithm has higher accuracy and faster computing speed, and achieves a better comprehensive effect. It further illustrates the extraction of English text by image processing technology, which can facilitate machine translation.

Research on edge detection algorithm based on improved sobel operator

In order to solve the shortcomings of traditional Sobel edge detection operator, such as low accuracy of image edge location and rough edge extracted, an improved edge detection algorithm based on Sobel operator is proposed. Firstly, in the aspect of the accuracy of edge detection, the direction template is increased from two directions of horizontal and vertical to eight directions; secondly, in terms of the rough edge extracted and the noise sensitivity, combined with the operation of mathematical morphology, the edge can be refined, and at the same time, some part of the noise can be suppressed. The experiment results show that the improved edge detection algorithm has a better accuracy in image positioning, and a certain ability to suppress noise. Finally, the detected image edge of the image is more delicate and clear than the traditional Sobel operator.

Edge Detection Algorithm for $Musca-Domestica$ Inspired Vision System

Compound vision sensors, mimicking the compound eye of the common housefly, possess motion hyperacuity, resulting in better motion detection and tracking capabilities as compared to traditional camera systems. Therefore, these sensors have applications requiring near instantaneous obstacle avoidance in its field-of-view. However, the obstacle detection algorithms used by current compound vision systems are insufficient to enable these capabilities due to their ability to only detect horizontal or vertical edges. In this paper, we propose an improved edge detection and location algorithm for fly inspired vision sensors which can correctly classify horizontal, vertical, forward diagonal, and backward diagonal edges.

Enhancing Classifier Accuracy in Ayurvedic Medicinal Plants using WO-DNN

Identification of right medicinal plants that goes in to the formation of a medicine is significant in ayurvedic medicinal industry. This paper focuses around the automatic identification proof of therapeutic plants that are regularly utilized in Ayurveda. The fundamental highlights required to distinguish a medicinal plant is its leaf shape, color and texture. In this paper, we propose efficient accurate classifier for ayurvedic medical plant identification (EAC-AMP) utilizing using hybrid optimal machine learning techniques. In EAC-AMP, image corners detect first and top, bottom leaf edges are computed by the improved edge detection algorithm. After preprocessing, the segmentation can achieve using spider optimization neural network (SONN), which segments leaf regions from an image. The time and frequency domain features are computed by the symbolic accurate approximation (SAX); other features shape features, color features and tooth features are computed by the two-dimensional binary phase encoding (2DBPE). Finally, a whale optimization with deep neural network (DNN) classifier is used to characterize the type of plants. Accuracy in identification of any ayurvedic plant leaf is achieved by understanding and extracting the plant features. The main objective of the proposed EAC-AMP approach is to increase the accuracy of classifier. MATLAB experimental analysis showed better results such as accuracy, sensitivity and specificity.

An improved edge detection algorithm for X-Ray images based on the statistical range

Edge detection is the prior stage to object recognition and considered as a pillar for image processing task. It is a process to detect such locations from images in terms of pixels where their intensity changing is abruptly. There are many types of images such as medical images, satellite images, articular images, industrial images, general purpose images etc. X-Ray is a type of medical image in which electronic radiation is passed into the human body to capture image of inner parts for better disease diagnoses by orthopaedics or radiologist. In this research paper, we have proposed an improved method to detect edges from human being's X-Ray images based on Gaussian filter and statistical range. Gaussian filter is used for image preprocessing and enhancement. Whereas, Statistical range is used to calculate difference between maximum and minimum pixels from every 3X3 image matrix partition. These two can work to detect edges from X-Ray images. We have also presented a comprehensive comparison of our proposed method with four existing latest methods/algorithms of edge detection. Apart from X-Ray images, experiments have also been conducted on human X-Ray images to detect edges. Further, we have found that our proposed method is superior in terms of MSE, RMSE, PSNR and computation time to detect edges from X-Ray images of human being.

Sea-Sky Line and its Nearby Ships Detection Based on the Motion Attitude of Visible Light Sensors.

In the maritime scene, visible light sensors installed on ships have difficulty accurately detecting the sea–sky line (SSL) and its nearby ships due to complex environments and six-degrees-of-freedom movement. Aimed at this problem, this paper combines the camera and inertial sensor data, and proposes a novel maritime target detection algorithm based on camera motion attitude. The algorithm mainly includes three steps, namely, SSL estimation, SSL detection, and target saliency detection. Firstly, we constructed the camera motion attitude model by analyzing the camera’s six-degrees-of-freedom motion at sea, estimated the candidate region (CR) of the SSL, then applied the improved edge detection algorithm and the straight-line fitting algorithm to extract the optimal SSL in the CR. Finally, in the region of ship detection (ROSD), an improved visual saliency detection algorithm was applied to extract the target ships. In the experiment, we constructed SSL and its nearby ship detection dataset that matches the camera’s motion attitude data by real ship shooting, and verified the effectiveness of each model in the algorithm through comparative experiments. Experimental results show that compared with the other maritime target detection algorithm, the proposed algorithm achieves a higher detection accuracy in the detection of the SSL and its nearby ships, and provides reliable technical support for the visual development of unmanned ships.

Improved Edge Detection Algorithm and Its Application in Robotic Fish

To get self-adaptive thresholds, the edge detection algorithm of Canny operator is improved in OpenCV library under Linux platform in this paper. Firstly, the gradient graph of the gray image and the maximum value of the gradient are obtained. Then the histogram is calculated and the pixel points corresponding to the gradient values are obtained via the traversion of histogram. Finally, the high and low thresholds are calculated to determine edge. Consequently, there comes the new self-adaptive thresholds algorithm of Canny operator. In the meantime, by simulating on the robotic fish in the water, the new algorithm is compared with the traditional Canny operator in the effect of the output image and the Peak Signal to Noise Ratio. What’s more, the same picture is tested to compare time in the Matlab platform and OpenCV platform. Such comparisons show that the new algorithm has more flexibility and efficiency

A Novel Approach to Improve Sobel Edge Detector

An improved edge detection algorithm based on k-means clustering approach. Being a fundamental tool in image processing, edge detection aims to identify the points in an image at which image brightness changes sharply or regularly. In Medical Science, edge detection is very useful, such as in segmentation of MRI image. Magnetic resonance imaging (MRI) produces a detailed image of any human body part, by using the natural magnetic properties of the body tissues. Since body tissues contain hydrogen atoms, which made to emit radio signals. These radio signals are then detected by a scanner. Magnetic Resonance imaging is a medical test used to diagnose tumors of the brain on the basis of high quality images produced by it. In this paper edge detection is made to determine the location of a tumor. The edge detection technique presented in this paper uses k-means clustering approach to generate the initial groups. These groups are then input to the mamdani fuzzy inference system, which generates different threshold parameters. When these parameters are fed into the classical sobel edge detector, it is found that images obtained are more enhanced and provide exact location of a tumor in a brain.

The Design and Research of the Smart Path Tracing Car Based on the Image Recognition

To realize the smart car's automatic path tracing along the different types of path, a smart path tracing car based on car model is developed. In the design of the smart path tracing car, image processing affects the smart car's per- formance directly. This article adopts direct acquisition, direct edge detection algorithm and the improved edge detection algorithm to analyze and compare the road message acquired by COMS camera. Plenty of experiment data show that, un- der different light intensity, the edge detection algorithm can acquire image with better accuracy and efficiency, solving the contradiction between the system's rapidity and stability, and realizing the smart car's running along the guide curve stably and rapidly.

An Improved Edge Detection Algorithm Based on Morphological Operators and Gradient

An Improved Edge Detection Algorithm Based on Morphological Operators and Gradient

An Approach to Improving Edge Detection for Facial and Remotely Sensed Images Using Vector Order Statistics

This paper presents an improved edge detection algorithm for facial and remotely sensed images using vector order statistics. The developed algorithm processes coloured images directly without been converted to grey scale. A number of the existing algorithms converts the coloured images into grey scale before detection of edges. But this process leads to inaccurate precision of recognized edges, thus producing false and broken edges in the output edge map. Facial and remotely sensed images consist of curved edge lines which have to be detected continuously to prevent broken edges. In order to deal with this, a collection of pixel approach is introduced with a view to minimizing the false and broken edges that exists in the generated output edge map of facial and remotely sensed images.

Improved Edge Detection Algorithm for Brain Tumor Segmentation

Abstract Image segmentation is used to separate objects from the background, and thus it has proved to be a powerful tool in bio-medical imaging. In this paper, an Improved Edge Detection algorithm for brain-tumor segmentation is presented. It is based on Sobel edge detection. It combines the Sobel method with image dependent thresholding method, and finds different regions using closed contour algorithm. Finally tumors are extracted from the image using intensity information within the closed contours. The algorithm is implemented in C and its performance is measured objectively as well as subjectively. Simulation results show that the proposed algorithm gives superior performance over conventional segmentation methods. For comparative analysis, various parameters are used to demonstrate the superiority of proposed method over the conventional ones.

Computer vision technology for seam tracking in robotic GTAW and GMAW

Due to ever increasing demand in precision in robotic welding automation and its inherent technical difficulties, seam tracking has become the research hotspot. This paper introduces the research in application of computer vision technology for real-time seam tracking in robotic gas tungsten arc welding (GTAW) and gas metal arc welding (GMAW). The key aspect in using vision techniques to track welding seams is to acquire clear real-time weld images and to process them accurately. This is directly related to the precision of seam tracking. In order to further improve the accuracy of seam tracking, in this paper, a set of special vision system has been designed firstly, which can acquire clear and steady real-time weld images. By analyzing the features of weld images, a new and improved edge detection algorithm was proposed to detect the edges in weld images, and more accurately extract the seam and pool characteristic parameters. The image processing precision was verified through the experiments. Results showed that the precision of this vision based tracking technology can be controlled to be within ?0.17mm and ?0.3mm in robotic GTAW and GMAW, respectively. Using computer vision technology, we have solved some problems of seam tracking in robotic welding automation.We have designed a set of special vision sensor system for seam tracking and it has worked very well.A new improved Canny edge detection algorithm was proposed to detect the edges of weld image.We have further improved the precision of image processing in seam tracking.This paper systematically studied the application of computer vision technology in robotic GTAW and GMAW.

Comparison of Traditional Approach for Edge Detection with Soft Computing Approach

Image processing supports applications in different fields such as medicine, astronomy, product quality, industrial applications. Edge detection plays important role in segmentation and object identification process. Soft computing approach represents a good mathematical framework to deal with uncertainty of information. The performance of the well-known edge detectors, like Canny, Sobel, etc, depends critically on the choice of the input parameters. Threshold decision is the key uncertainty in the edge detection algorithms. In this paper, an improved edge detection algorithm based on fuzzy combination of mathematical morphology and multiscale wavelet transform is proposed. The proposed method overcomes the limitation of wavelet based edge detection and mathematical morphology based edge detection in noisy images. Method present will give best results for noisy images.

Based on the Research of Improved Edge Detection Algorithm

Analysis and several common edge detection algorithm is improved, and put them in the original experiment results were compared with the results in this paper, we defined the new threshold, fully explained in this paper, we define the rationality and validity of the threshold value. Kirsch of traditional algorithm was improved, and improve the efficiency of the algorithm, and verify the rationality of the defined threshold and improve the ability to suppress noise.