Image Edge Detection Using FPGA

Bonfring International Journal of Research in Communication Engineering, 2016

The digitisation of medical images tend to suffer from poor image quality, lack of proper contrast and most importantly presence of shading and artefacts In order to overcome the poor image quality of the image, enhancement is the key method which is followed. Enhancement improves the effectiveness or attractiveness of the image. Enhancement involves conversion of image from gray to adoptive histogram and then 2D-DWT is applied on it. This decomposes the image into 4 sub-bands and the low frequency sub band is smoothened using geometric mean filter. Then IDWT is applied using new low frequency and remaining sub bands. The experimental results vividly displays the proposed algorithm is efficient to enough to remove the noise resulting good enhancement and then achieved increased value of PSNR and reducing value of MSE. In order to effectively present both gray values and spatial information of image pixels, a fusion method for image segmentation by jointly utilizing direct fusion method and edge detection method is being proposed. The technique involved here is division of image into small sub blocks each sub block consisting of a vector and those vectors are further classified as edge and non-edge patterns by using edge detection algorithm. Boundary detection is further applied to extract the finest boundary curves in the edge pattern vectors and finally a fusion method is employed to synthesise the results of Pixel Based Fusion Method and Boundary Detection to accomplish the segmentation.

2015

Edge detection is an important tool in digital image processing applications for extracting information from image. Sobel operator based edge detection algorithm creates an image which highlights edges and transitions. In real-time image processing applications, it is required to process large data of pixels in a given timing constraints. Hence, speed of image processing is a big problem. Reconfigurable device like FPGAs deploy parallelism techniques in image processing algorithms thereby reducing execution times and increasing speed of operation. This paper presents implementation of sobel edge detection algorithm on FPGA. Xilinx ISE Design Suite-14.2 software platform is used to design an algorithm using Verilog language.

Advances in Image and Video Processing, 2015

In this article a new combination of image segmentation techniques including K-means clustering, watershed transform, region merging and growing algorithm was proposed to segment computed tomography(CT) and magnetic resonance(MR) medical images. The first stage in the proposed system is "preprocessing" for required image enhancement, cropped, and convert the images into .mat or png ...etc image file formats then the image will be segmented using combination methods (clustering , region growing, and watershed, thresholding). Some initial over-segmentation appears due to the high sensitivity of the watershed algorithm to the gradient image intensity variations. Here, K-means and region growing with correct thresholding value are used to overcome that over segmentations. In our system the number of pixels of segmented area is calculated which is very important for medical image analysis for diseases or medicine effects on affected area of human body also displaying the edge map. The results show that using clustering method output to region growing as input image, gives accurate and very good results compare with watershed technique which depends on gradient of input image, the mean and the threshold values which are chosen manually. Also the results show that the manual selection of the threshold value for the watershed is not as good as automatically selecting, where data misses may be happen.

—Field Programmable Gate Array (FPGA) is an effective device to realize real-time parallel processing of vast amounts of video data because of the fine-grain reconfigurable structures. This paper presents a kind of parallel processing construction of Sobel edge detection enhancement algorithm, which can quickly get the result of one pixel in only one clock periods. The algorithm is designed with a FPGA chip called XC3S200-5ft256, and it can process 1024×1024×8 Gray Scale Image successfully. The design can locate the edge of the gray image quickly and efficiently.

Cardiovascular diseases are among the most common diseases in the world, killing more than 13 million people each year. Hence, the necessity of good automatic segmentation tools that are able to segment vascular structures and detect abnormalities. Thus, the work performed during the last months includes a review of vessel segmentation and analysis techniques, and the implementation of some of those methodologies within the Alma3D medical image visualization software.

Biomedical Research

Vessel segmentation in X-Ray Coronary Angiography (XCA) images, which is used for the diagnosis and treatment of anomalies in coronary vessels, has been an intriguing topic in recent years. Due to dynamic background and ambiguous brightness distribution, success rate in segmentation is low and realization has been a challenging process. This paper presents a new approach to increase the success rate of segmentation in XCA images. For this purpose, the vessel structure position is first determined with foreground detection algorithm in the XCA image sequences. Next, state of the art methods of vessel identification and image thresholding used for vessel structure segmentation are being experimented in full and foreground images. The contribution of the suggested method to the success of the segmentation is revealed with the experiments carried out. The scales of sensitivity, specificity and accuracy are given in the paper to evaluate the success of the segmentation. The results were compared with the angiography images segmented manually by a specialist physician. Without proposed detection of candidate vessel location, highest accuracy results 92.4 is achieved with Multiscale Gabor filter and P-Tile thresholding. Frangi Filter and Otsu thresholding algorithm reached the highest success rate of 93.81 by using the proposed method. All the experiments have shown that accuracy of vessel segmentation is increase by the proposed approach.

Indonesian Journal of Electrical Engineering and Computer Science, 2022

The microscopic-blood image has been used to diagnose various diseases according to the morphological specifications of red and white blood cells. However, the manual analysis and procedures are not accurate due to the human error. Therefore, several studies conducted to find new techniques to perform this analysis using computer algorithms. The complexity of these algorithms led to thinking in simpler ways or to the hardware solutions. On the other hand, edge detection is a mathematical procedure that play an essential role in the field of medical image processing. It is considered as one of the foundations' processes for other procedures, such as the segmentation and the classification of the image. The Sobel filter is one of the conventional methods that is used to perform the edge detection process. It is based on finding the local contrast for the level of intensity of the image. This paper presents a proposed and a new method for detecting the edges of cells in the microscopic blood images using Sobel filter and its hardware implementation on the field programmable gate array (FPGA) chip. Three different techniques are proposed: MATLAB, OpenCV standard code, and FPGA customize code which give the best visual results, minimum timing results than the others.

A methodology for implementing real-time DSP applications on a field programmable gate arrays (FPGA) using Xilinx System Generator (XSG) for MATLAB is presented in this paper. It presents architecture for Edge Detection using Sobel Filter & Canny Filter for image processing using Xilinx System Generator. The design was implemented targeting a Spartan3A DSP 3400device (XC3S200-4TQ144). The Edge Detection method has been verified successfully with no visually perceptual errors in the resulted images and also comparing the both filters with an individually performance is justified clearly with Practical and Theoretical.

The second algorithm uses an adaptive thresholding to obtain the vessel mask and then the morphological operations for removing the spurs. The third algorithm applies the seeded region growing method on the maximum magnitude image from the Frangi vesselness filtering and then morphological operations for removing the spurs. The algorithms are evaluated having as gold standard two vessel masks provided from two different medical experts. The comparison of the reliability of the three segmentation methods is made by using standard indices found in the scientific literature [8-9] from which the most important ones are the specificity and sensitivity.