Edge Detection Process Research Articles

Arduino-controlled Reflectance Transformation Imaging to the study of cultural heritage objects

This article examines the development of a low-cost and portable set-up controlled by an Arduino board to perform Reflectance Transformation Imaging technique, from the information derived from 45 digital photographs of an object acquired using a stationary camera. The set-up consists of 45 high-intensity light emitting diodes (LEDs) distributed over a hemispherical dome of 70 cm in diameter and a digital camera on the top of the dome. The LEDs are controlled by an Arduino board, and the user can individually control the LEDs state (ON or OFF) and duration of illumination. An old manuscript written with iron-gall ink and a set of 1 Euro coins mint in 2002 were photographed with the set-up. The interactive re-lighting and the mathematical enhancement of the object’s surface revealed corrosion, loss of material, scratches and other details, which were not perceived in standard images. These unique features, which can be extracted using edge detection processing, have immediate application in different fields such as cultural heritage or forensic studies, where they can be used as fingerprints to identify unique objects, allowing also recognizing the use of tools to alter the surface of coins to increase the price in the market.

Internal Waves at the UK Continental Shelf: Automatic Mapping Using the ENVISAT ASAR Sensor

Oceanic internal waves occur within stratified water along the boundary between water layers of different density and are generated when strong tidal currents flow over seabed topography. Their amplitude can exceed 50 m and they transport energy over long distances and cause vertical mixing when the waves break. This study presents the first fully automated methodology for the mapping of internal waves using satellite synthetic aperture radar (SAR) data and applies this to explore their spatial and temporal distribution within UK shelf seas. The new algorithm includes enhanced edge detection and spatial processing to target the appearance of these features on satellite images. We acquired and processed over 7000 ENVISAT ASAR scenes covering the UK continental shelf between 2006 and 2012, to automatically generate detailed maps of internal waves. Monthly and annual internal wave climatology maps of the continental shelf were produced showing spatial and temporal variability, which can be used to predict where internal waves have the most impact on the seabed environment and ecology in UK shelf seas. These observations revealed correlations between the temporal patterns of internal waves and the seasons when the continental shelf waters were more stratified. The maps were validated using well-known seabed topographic features. Concentrations of internal waves were automatically identified at Wyville-Thomson Ridge in June 2008, at the continental shelf break to the east of Rosemary Bank in January 2010 and in the Faroe-Shetland Channel in June 2011. This new automated methodology has been shown to be robust for mapping internal waves using a large SAR dataset and is recommended for studies in other regions worldwide and for SAR data acquired by other sensors.

Comparison of image edge detection methods on potholes road images

Dinas pekerjaan Umum (DPU) in Surabaya in carrying out road repairs, especially in potholes, must know the position, area and depth. So it is important to do research to find out the surface area of potholes. To find out the surface area of the hole, the edge detection process is done first. Edge detection functions to get the edge of an object. Edge detection is obtained by utilizing a drastic change in the intensity value at the boundary of two areas. In this study, to determine the edge of an object (potholes road) by comparing three edge detection methods consisting of the Frei-Chen, Laplacian and Laplacian of Gaussian (LoG) methods. From the results of testing the Laplacian of Gaussian method has an average value of accuracy of 67%, sensitivity of 81.97% and specificity of 65.16%.The measurement results obtained by the Lapalacian of Gaussian method which is the best method for edge detection in potholes road images, because it produces the highest accuracy, sensitivity and specificity.

Realistic Mathematical Model of Retinal Outer Plexiform Layer for Edge Detection.

Edge information is essential for object recognition and motion detection. It is reported that photoreceptors, horizontal cells and bipolar cells in the outer retina involved for edge detection. Moreover, it is known that the center and the surround receptive field structure found in the bipolar cell layer is thought to be related to an initial process of edge detection. In the present study, we constructed retinal network models including photoreceptors, horizontal cells, and bipolar cells using single-compartment neurons to investigate those contributions for edge detection. We simulate fixation of a natural image with changing the size of the horizontal cell receptive field and confirmed that the constructed model successfully extracts edges in the image. Furthermore, most of the edge in the scene is extracted when the size of the horizontal cell receptive field matched with that reported in anatomical evidence. To evaluate the performance of edge detection, we compare the result of edge detection with the Canny algorithm. As a result, we conformed that the model well detects fine edges similar to the Canny edge detection.

DETEKSI TEPI UNTUK VALIDASI MODEL TIGA DIMENSI TULANG PANGGUL PADA PERENCANAAN DESAIN DAN FABRIKASI IMPLAN

In the process of implant design and fabrication planning, the anatomical background of human bone is an important aspect to determine the accuracy of implant design. To help in understanding the human bone anatomy, replicas of human bone can be reconstructed using three-dimensional (3D) printing technology. This study aims to validate the digital model of human bone and the imaging data of human bone in order to have an appropriate recommendation for designing the total hip replacement (THR). Achieved data from computed tomography scanning (CT-Scan) modality was deciphered to build the digital 3D model human bone. The bone and the digital 3D model of bone were captured to be two-dimensional(2D) data in the same dimension and processed using the algorithm of edge detection. The images from the edge detection process were processed for finding the similarity of the images. The percentage of similarity, precision, and accuracy between the bone and the digital 3D model have been validated and can be used as a reference in the THR designs.

Development of Edge Detection for Image Segmentation

The edge detection technique is a fundamental phase of image segmentation. The purpose of the image segmentation algorithm is to distinguish the boundary of objects in different regions and it relies on discontinuities in image values between distinct regions. The objectives of this research are to a) develop an interface for image edge detection based on derivatives using MATLAB and b) measure the PSNR, SNR and MSE values for analysis based on experiments conducted. Results show that, Lena image produces PSNR values of 20.9 dB (Canny), 20.0 dB (Log), 20.1 dB (Prewitt), 20.0 dB (Sobel) and 20.0 dB (Robert). Meanwhile, MSE gives 80.5 dB (Canny), 83.1 dB (Log), 80.9 dB (Prewitt), 81.0 dB (Sobel) and 81.0 dB (Robert) after the edge detection process. The finding shows that Canny has given a winning performance in PSNR value and low in noise rate for JPEG type of image in image segmentation. Finally, the impact of edge detection techniques produces a better solution for image segmentation.

Fish Larvae Counting System Using Image Processing Techniques

This paper presents the use of computer technology based on image processing techniques to count the number of fish larvae with less time processing. Computer technology used is as an alternative solution to the manual counting approach method in term of determination fish larvae survival rate, stock assessment and monitoring fish growth population. Generally, the fish larvae counting is performed with sequential process with laborintensive task which difficult to be used for counting large sample dataset. Traditional counting method has been used for many years, however many researchers highlighted several drawbacks of the manual counting process such as time consuming, laborious, required human skills-eyes, less-accurate, less consistent, difficult to estimate with many large sample and too many involve with human intervention. Since the problems is addressed, many researchers are interested to develop many techniques to facilitate the process of fish counting with fast assessment. In this study, we present combination of image processing techniques that consists of image enhancement, edge detection, and thresholding process. Meanwhile, the blob analysis is used as the statistical information to measure the objects properties in the image automatically. Total number of 150 samples dataset of Nile Tilapia (Oreochromis niloticus) were used in the experiment. All the samples are divided into three part which are small dataset (50 samples), medium dataset (50 samples) and large dataset (50 samples). The performance of the proposed method and the manual approach method are compared based on the number of fish that was successfully estimated and processing time taken through the experiment. All 150 samples of fish larvae were collected from the Freshwater Hatchery of University Malaysia Terengganu. The experimental results shows that the proposed method based on computer technology is outperformed compared to the manual counting approach in the experiment. This is because, the number of fish larvae measurement by using the proposed method is almost similar and some of samples present accurate result compared to the traditional approach. Moreover, the proposed method is promising on the processing time for measuring all samples with less time processing and more reliable.

Edge detection in non-linear scalable space

Automatic image processing and computer vision applications often include object extraction and recognition. To extract object boundaries better, high-quality methods of edge detection are required. Objects in real-world photos usually have complex structure, and discovering their edges with higher precision is a very important and tough task. Better edge detection drastically increases the quality of the entire process. Unfortunately, edge detection problem still has no satisfactory solution in the case of real-world color images, because efficient approaches exist for grayscale images only. Known edge detection techniques usually either consist of special filters applied to a grayscale image, or implement rather unpredictably behaving artificial intelligence solutions. We propose a new powerful mathematical tool to extract edge information not only from intensity but from color distribution as well. Correctness of edge detection gets better by means of an adaptive mathematical model of non-linearly scalable color space. In our research, we consider flexible non-linear transformation of the color space with a few parameters. It helps reliably extracting otherwise faded edges delimiting the objects. We compare the results of edge detection process based on this new technique to well-known base-line approaches of Canny, Prewitt, Sobel and Wallace filters.

Retina Image and Bat-Inspird Algorithm for Artificial Key Generation

The process of key generation is utilized in different applications based on encryption techniques. Thecharacteristics of the generated key should satisfy the required security as potential. The traditionaltechniques used for generating keys are based on various equations based on chaos maps or modulation formaking these keys as one-time pads. Also, there are many techniques that utilized the block cipher or hashfunction for generating keys. In this paper, a retina image and bat-inspired algorithm are used for generatingsecure keys. Several processes have been applied to the input retina images like enhancement and edgedetection processes. In the proposed technique, some parameters are adjusted for controlling the results andevery output represents a bat solution and depending on the fitness function, the keys are generated. Thesegenerated keys are tested and evaluated using NIST tests. As a case study, some images are encrypted usingthe generated keys and the obtained encrypted images passed all the required security tests.

Feature Extraction for the Discrimination of Crop and Weed in Digital Images using Open CV and Python

Variable rate herbicide spraying technology has become integral part of precision agriculture and this system works based on the weed density map of agriculture field. To improve the accuracy of crop/weed discrimination process this paper presents different image processing techniques. Edge detection process for obtaining contour is performed by using sobel operator with 5X5 gradient operator and canny edge detector. Grayscale morphological operations are performed to remove gray overlap due to background of the image in order to improve the accuracy of the segmentation process. In order to check the discrimination accuracy and extracting image features, the experiment was performed on 100 images of maize plant and weed plant leaves. From the experimental results, it is concluded that the proposed method can accurately extract leaf parameters for discrimination process with soil background.

Robust ellipse fitting based on Lagrange programming neural network and locally competitive algorithm

Given a set of 2-dimensional (2D) scattering points, obtained from the edge detection process, the aim of ellipse fitting is to construct an elliptic equation that best fits the scattering points. However, the 2D scattering points may contain some outliers. To address this issue, we devise a robust ellipse fitting approach based on two analog neural network models, Lagrange programming neural network (LPNN) and locally competitive algorithm (LCA). We formulate the fitting task as a nonsmooth constrained optimization problem, in which the objective function is an approximated l0-norm term. As the LPNN model cannot handle non-differentiable functions, we utilize the internal state concept of LCA to avoid the computation of the derivative at non-differentiable points. Simulation results show that the proposed ellipse fitting approach is superior to several state-of-the-art algorithms.

Image investigation using higher moment statistics and edge detection for recognizing abnormal skin

This paper discusses the recognition of skin abnormalities by investigating the images using high-level statistics and edge detection. Six images of skin diseases were analyzed using several statistical parameters, including high-level moments such as skewness and kurtosis. In comparison, some images from other categories such as animal, architecture, art, vehicle, food, people, and scenery have been analyzed as well. The results were compared to skin disease images. It is expected that the general pattern of statistical parameters can distinguish skin images against images from other categories. MatLab is used as a medium to calculate the values of statistical parameters. The mean and median of the skin disease image are much larger. Meanwhile, the standard deviation is the smallest compared to other categorical images. Almost all the analyzed images close to symmetry. Nearly all images category are distributed more leaning to the left, except for the images of the art category, which is slightly more leaning to the right. Moreover, the edge detection process has been done using the Sobel algorithm. The result, however, cannot clearly distinguish a skin's abnormality. This difficulty is because of the lack of accuracy in selection the intensity.

Research on crack monitoring at the trailing edge of landslides based on image processing

Currently, the frequency of landslides is increasing. Scientific monitoring methods are playing an essential role in effectively reducing landslide disasters. This paper proposes a method for identifying the cracks at the trailing edge of a landslide (TEL) based on image processing technology and adopts the custom interval median comparison algorithm (IMCA) to calculate the crack motion parameters. First, we perform a series of processes on the TEL images, including image preprocessing, Otsu’s algorithm processing, and Canny edge detection processing, to identify the outline of the TEL. Then, we propose using the azimuth and displacement to characterize the motion of the cracks and using the IMCA to calculate the changes before and after motion of any two groups of cracks. Finally, we design a computer program using a free and open-source widget toolkit (named QT platform) based on the calculation model that corresponds to the proposed method, and we apply the crack monitoring test to a 3D simulation model, a gravel model, a soil model, and a collapsed body of the Panzhihua Airport landslide in southwestern China. From the results, it can be assessed that the method can identify the outline of the TEL and calculate the azimuth and displacement of two crack curves before and after motion. These two parameters can describe the movement of the trailing edge cracks of the monitored landslide. Thus, this method can be used in early warning system for landslide hazards.

Edge Detection using Guided Image Filtering and Enhanced Ant Colony Optimization

Abstract Edge detection is an important process in many classes of engineering problems. An edge is a boundary between two regions. In the edge detection process, the input is a grayscale image while the output image is a binary image showing edge and non-edge pixels. As a state of art, methods are based on gradient operator, but the accuracy level is poor. Therefore, in recent past soft computing based methods are proposed which are more accurate, still, these methods fail to detect some of the true edges. In this paper, the two-level approach is adopted for edge detection, firstly image edges are enhanced using guided image filtering, and secondly on these enhanced images enhanced ant colony optimization method is applied for edge detection.

Analog Optical Spatial Differentiators Based on Dielectric Metasurfaces

AbstractAnalog spatial differentiator is an important optical computational device that can be potentially used in the field of high‐speed edge detection and optical image processing. In the current stage, a general method is still required to robustly design compact devices for various spectrum or complex situation. In this work, a dielectric metasurface method is proposed and experimentally demonstrated to build optical spatial differentiators. This is physically realized by a high‐quality magnetic resonance mode that is hybridized with the classic bounded surface wave via grating coupling. Experimentally, a well‐defined first‐order differentiation effect is observed at oblique light incidence. The application potential of this device is evaluated by inputting various figures. It is shown that it can perform an optical processor to trace the profiles of the figure content with a resolution better than 30.8 µm. This work may pave a robust way to build ultracompact optical computation devices for real‐time image processors, which can be freely extended to various frequencies.

EDGE DETECTION PARAMETER OPTIMIZATION BASED ON THE GENETIC ALGORITHM FOR RAIL TRACK DETECTION

One of the most important parameters in an edge detection process is setting up the proper threshold value. However, that parameter can be different for almost each image, especially for infrared (IR) images. Traditional edge detectors cannot set it adaptively, so they are not very robust. This paper presents optimization of the edge detection parameter, i.e. threshold values for the Canny edge detector, based on the genetic algorithm for rail track detection with respect to minimal value of detection error. First, determination of the optimal high threshold value is performed, and the low threshold value is calculated based on the well-known method. However, detection results were not satisfactory so that, further on, the determination of optimal low and high threshold values is done. Efficiency of the developed method is tested on set of IR images, captured under night-time conditions. The results showed that quality detection is better and the detection error is smaller in the case of determination of both threshold values of the Canny edge detector.

Automating field boundary delineation with multi-temporal Sentinel-2 imagery

Knowledge of the extent and location of cultivated fields are critical for agricultural monitoring, food security planning and commodity trading. The increased observational capacity of remotely sensed data, such as Sentinel-2 imagery, constitutes a major advantage over in situ methods, particularly for agricultural applications that require frequent updates. However, the development of fully automated cultivated field delineation methods remains a challenge. In this study an existing object-based image analysis (OBIA) methodology, called Canny edge-detection in conjunction with watershed segmentation (CEWS), was modified to automatically identify and delineate agricultural fields from multi-temporal Sentinel-2 imagery in five diverse agricultural landscapes. The robustness of the technique was evaluated by comparing its outputs to those of standard per-pixel, supervised classifications. Reference field boundaries were manually digitised and used for quantitative accuracy assessments. Area and edge metrics were used to evaluate the accuracy of the extracted boundaries. Results show that, on average, CEWS produced significantly higher field boundary accuracies than the supervised per-pixel approach in terms of both mean absolute error (MAE) (~31 m lower) and overall accuracy (~13.8% higher). The closed field boundaries produced by CEWS, as well as its capability to operate without any a priori knowledge, was found to be its main strengths for integration into operational workflows. However, in complex landscapes (e.g. Swartland and Mooketsi) it was found that some fields had weak boundaries due to the homogeneity between adjacent fields, making edge detection problematic. The incorporation of higher resolution imagery into the edge detection process is proposed, particularly in agricultural areas with very small and irregularly shaped fields. Despite these challenges, it was concluded that the multi-temporal CEWS approach will perform well in most agricultural areas and is suitable for operational implementation.

Recognition of Hand Gesture for a Paralytic Person Using Convolutional Neural Network

According to the Indian statistics, the stroke rate is higher compared to other countries. It is approximately 1.8 million Indians out of 1.2 billion Indians suffering from stroke every year. As a result of this brain cells get damaged which leads to paralysis. To help the stroke patients out of its researchers have found a solution by creating hand gestures that will help them perform daily functions easily. The gesture made by hand will be the input instead of a mouse or keyboard. The main aim is to read and detect the hand gestures by using high-resolution cameras and process the images using convolution neural networks by the process of edge detection.

Enhancement of Satellite Imagesusing Image Sharpening Technique

In many image processing applications, a wide range of image enhancement techniques are being proposed. Many of these techniques demanda lot of critical and advance steps, but the resultingimage perception is not satisfactory. This paper proposes a novel sharpening method which is being experimented with additional steps. In the first step, the color image is transformed into grayscale image, then edge detection process is applied using Laplacian technique. Then deduct this image from the original image. The resulting image is as expected; After performing the enhancement process,the high quality of the image can be indicated using the Tenengrad criterion. The resulting image manifested the difference in certain areas, the dimension and the depth as well. Histogram equalization technique can also be applied to change the images color.

Edge detection based on type-1 fuzzy logic and guided smoothening

Edge detection is an important phenomenon in computer vision. Edge detection is helpful in contour detection and thus helpful in obtaining the important information. Edge detection process heavily depends on chosen technique. Soft computing techniques are considered as powerful edge detection methods due to their adaptability. This paper presents a fuzzy logic based edge detection method where the quality of edges is controlled using sharpening guided filter and noise due to the sharpening is controlled using Gaussian filter. The accuracy of the method is judged using a variety of statistical measures. It has been found that by proper selecting the smoothening parameters a significant improvement in the detected edges can be obtained.