Design and Implementation of Image Edge Detection Algorithm on FPGA

Image processing is an important task in data processing systems for applications such as medical sectors, remote sensing, and microscopy tomography. Edge recognition is a sort of image division method that is used to simplify the image records so as to reduce the amount of data to be processed. Edges are considered the most important in image processing because they are used to characterize the boundaries of an image. The performance of the Canny edge recognition algorithm remarkably surpasses the present edge recognition technology in various computer visualization methods. The main drawback of using Canny edge boundary is that it consumes lot of period due to its complex computation. In order to tackle this problem a hybrid edge recognition method is proposed in block stage to locate edges with no loss. It employs the Sobel operator estimate method to calculate the value and direction of the gradient by substituting complex processes by hardware cost savings, traditional non-maximum suppression adaptive thresholding block organization, and conventional hysteresis thresholding. Pipeline was presented to lessen latency. The planned strategy is simulated using Xilinx ISE Design Suite14.2 running on a Xilinx Spartan-6 FPGA board. The synthesized architecture uses less hardware to detect edges and operates at maximum frequency of 935 MHz.

Toward the recognition of spacecraft feature components: A new benchmark and a new model

Countries are increasingly interested in spacecraft surveillance and recognition which play an important role in on-orbit maintenance, space docking, and other applications. Traditional detection methods, including radar, have many restrictions, such as excessive costs and energy supply problems. For many on-orbit servicing spacecraft, image recognition is a simple but relatively accurate method for obtaining sufficient position and direction information to offer services. However, to the best of our knowledge, few practical machine-learning models focusing on the recognition of spacecraft feature components have been reported. In addition, it is difficult to find substantial on-orbit images with which to train or evaluate such a model. In this study, we first created a new dataset containing numerous artificial images of on-orbit spacecraft with labeled components. Our base images were derived from 3D Max and STK software. These images include many types of satellites and satellite postures. Considering real-world illumination conditions and imperfect camera observations, we developed a degradation algorithm that enabled us to produce thousands of artificial images of spacecraft. The feature components of the spacecraft in all images were labeled manually. We discovered that direct utilization of the DeepLab V3+ model leads to poor edge recognition. Poorly defined edges provide imprecise position or direction information and degrade the performance of on-orbit services. Thus, the edge information of the target was taken as a supervisory guide, and was used to develop the proposed Edge Auxiliary Supervision DeepLab Network (EASDN). The main idea of EASDN is to provide a new edge auxiliary loss by calculating the L2 loss between the predicted edge masks and ground-truth edge masks during training. Our extensive experiments demonstrate that our network can perform well both on our benchmark and on real on-orbit spacecraft images from the Internet. Furthermore, the device usage and processing time meet the demands of engineering applications.

An Advanced Image Processing Prototype for Corrosion Finding Using Image Processing

The main objective of the research work is to recognize the rust of the substance with the help of Image Processing. The recognition of the rust portion of an image is carried out by quantizing of image in matrix form. The quantization process helps to perform the fundamental operation on image and also helps to identify the desired oxidation portion of an image. The corrosion portion was identified through the threshold operation, edge detection and segmentation. Threshold value assists to describe the types of the rust. Further the abrupt modification of colour in the images was captured by the edge detection method. Consequently partitioning of an image find the colour changes in the oxidized image. The corrosion portion was recognized by combining the edge recognition and partitioning process. Finally recommended methods provide the 98% accuracy to detect the rust.

NORMALIZED VERTICAL DERIVATIVES IN THE EDGE ENHANCEMENT OF MAXIMUM-EDGE-RECOGNITION METHODS IN POTENTIAL FIELDS

Gravity and magnetic data have unique advantages for studying the lateral extents of geological bodies. There is a class of methods for edge recognition called the maximum-edge-recognition methods that use their extreme values to locate the edges of geological bodies. These methods include the total horizontal derivative, the analytic signal amplitude, the theta map, and the normalized standard deviation. These are all first-order derivative-based techniques. There are also higher-order derivative-based methods that are derived from the first-order filters, for example, the total horizontal derivative of the tilt angle. We present an edge recognition filter that is based on the idea of the normalized vertical derivatives of existing methods. For each maximum-edge-recognition method, we first calculate its nth-order vertical derivative and then use thresholding to locate its peaks. The peak values are subsequently normalized by the values of the original maximum-edge-recognition method. Testing on synthetic and real data shows that the normalized vertical derivatives of the maximum-edge-recognition methods have higher accuracy, better lateral resolution and are more interpretable than existing techniques, and thus are a worthwhile addition to the set of edge-detection tools for potential-field data.

A Proficient Hybrid Framework for Image Retrieval

In this work, an image retrieval system based on three main factors is constructed. The proposed system at first chooses relevant pictures from an enormous information base utilizing colour moment data. Accordingly, canny edge recognition and local binary pattern and strategies are utilized to remove the texture plus edge separately, as of the uncertainty and resultant pictures of the underlying phase of the system. Afterward, the chi-square distance between the red-green and the blue colour channels of the query and the main image are calculated. Then these two (the LBP pattern and the edge feature extracted from the canny edge detection and by chi-square method) data about these two highlights compared to the uncertainty and chosen pictures are determined and consolidated, are then arranged and the nearest ‘n' images are presented. Two datasets, Wang and the Corel databases, are used in this work. The results shown herein are obtained using the Wang dataset. The Wang dataset contains 1,000 images and Corel contains 10,000 images.

A Noncontact Method for Locating Radial Artery above Radial Styloid Process in Thermal Image

A radial artery above the radial styloid process is called GUAN and is a critical position for collecting pulse wave in traditional Chinese medicine theory. Locating GUAN is a precondition for collecting radial pulse wave. However, existing methods for locating GUAN lead to large deviations. This paper proposes a novel nontouch method for locating GUAN based on thermal imaging and image processing. This method consists of three parts: the infrared thermal imaging location imaging platform, the wrist edge contour extraction algorithm based on arbitrary angle edge recognition, and radial protrusion recognition algorithm (x coordinate identification algorithm of GUAN) and radial artery fitting algorithm (y coordinate identification algorithm of GUAN). The infrared thermal imaging positioning imaging platform is used to ensure that the wrist of the subject enters the fixed imaging area in a fixed position during each measurement and transmits the thermal imaging images carrying the image information of radial processes and radial arteries to the upper computer. Arbitrary angle edge recognition algorithm is used to extract wrist contour and radial artery edge information. The x-axis coordinates of the radial artery were provided by the identification algorithm, and the y-axis coordinates of the radial artery were provided by the fitting algorithm. Finally, the x and y coordinates determine the GUAN position. The algorithm for locating GUAN could provide repeatable and reliable x and y coordinates. The proposed method shows that relative standard deviation (RSD) of x distance of GUAN is less than 9.0% and RSD of y distance of GUAN is less than 5.0%. The proposed method could provide valid GUAN coordinates and reduce deviations of locating GUAN.

Applications of Fuzzy dot i* algebra in Computer Vision

Right now shows another route sort of identifying an edges and corners in the computer vision calculation. The Edge location is a key purpose of numerous calculations, both in picture preparing and video handling. It is significant that the calculation is proficient quick to bring out through the whole program. The custom system is to utilize the edge recognition it's not giving the better outcome dependent on the presumptions. In these conventional procedures here and there is vulnerability of the edge, and the man can't recognize whether it is the edge or not. So as to turn the fuzzy dot i* algebra based edge and corner (named as FDIA) all things considered and tackle the above issues. Fuzzy innovation has been a recent rising innovation utilized in numerous fields, particularly in the image handling, and computer vision is one significant piece of the fuzzy innovation. In light of this innovation, the edges and corners recognize by vigilant corner identification, calculation likewise to portray devices from picture preparing and the speed with the assistance of MATLAB programming.