Papers by Nassir Hussien Salman
<title>Edge detection and image segmentation based on K-means and watershed techniques</title>
Proceedings of SPIE, Sep 20, 2001
In this paper, we present a method that incorporates k-means and watershed segmentation technique... more In this paper, we present a method that incorporates k-means and watershed segmentation techniques for performing image segmentation and edge detection tasks. Firstly we used k-means techniques to examine each pixel in the image and assigns it to one of the clusters depending on the minimum distance to obtain primary segmented image into different intensity regions. We then employ a watershed transformation technique works on that image. This includes: First, Gradient of the segmented image. Second, Divide the image into markers. Third, Check the Marker Image to see if it has zero points (watershed lines) then delete the watershed lines in the Marker Image created by watershed algorithm. Fourth, Create Region Adjacency Graph (RAG) and the Region Adjacency Boundary (RAB) between two regions from Marker Image and finally; Fifth, Region Merging according to region average intensity and edge strength (T1, T2), where all the regions with the same merged label belong to one region. Our approach was tested on remote sensing and brain MR medical images and the final segmentation is one closed boundary per actual region in the image.
Image Segmentation and Edge Detection Based on Chan-Vese Algorithm
The International Arab Journal of Information Technology, 2006
The main idea in this paper is to detect regions (objects) and their boundaries, and to isolate a... more The main idea in this paper is to detect regions (objects) and their boundaries, and to isolate and extract individual components from a medical image. This can be done using K-means firstly to detect regions in a given image. Then based on techniques of curve evolution, Chan-Vese for segmentation and level sets approaches to detect the edges around each selected region. Once we classified our images into different intensity regions based on K-means method, to facilitate separating each region with its boundary and its area individually in the next steps. Then we detect regions whose boundaries are not necessarily defined by gradient using Chan-Vese algorithm for segmentation. In the level set formulation, the problem becomes a mean-curvature flow like evolving the active contour, which will stop on the desired boundary of our selected region which results from K-means step. The final image segmentation results are one closed boundary per actual region in the image and a segmented map.
Iraqi journal of science, Apr 30, 2022
Face detection is one of the important applications of biometric technology and image processing.... more Face detection is one of the important applications of biometric technology and image processing. Convolutional neural networks (CNN) have been successfully used with great results in the areas of image processing as well as pattern recognition. In the recent years, deep learning techniques specifically CNN techniques have achieved marvellous accuracy rates on face detection field. Therefore, this study provides a comprehensive analysis of face detection research and applications that use various CNN methods and algorithms. This paper presents ten of the most recent studies and illustrate the achieved performance of each method.
New Image Compression/Decompression Technique Using Arithmetic Coding Algorithm
گۆڤاری زانکۆی سلێمانی بەشی A, Oct 16, 2016
Xinan Jiaotong Daxue Xuebao, 2020
Image compression is one of the data compression types applied to digital images in order to redu... more Image compression is one of the data compression types applied to digital images in order to reduce their high cost for storage and/or transmission. Image compression algorithms may take the benefit of visual sensitivity and statistical properties of image data to deliver superior results in comparison with generic data compression schemes, which are used for other digital data. In the first approach, the input image is divided into blocks, each of which is 16 x 16, 32 x 32, or 64 x 64 pixels. The blocks are converted first into a string; then, encoded by using a lossless and dictionary-based algorithm known as arithmetic coding. The more occurrence of the pixels values is codded in few bits compare with pixel values of less occurrence through the sub intervals between the range 0 and 1. Finally, the stream of compressed tables is reassembled for decompressing (image restoration). The results showed a compression gain of 10-12% and less time consumption when applying this type of coding to each block rather than the entire image. To improve the compression ratio, the second approach was used based on the YCbCr colour model. In this regard, images were decomposed into four sub-bands (low-low, highlow, low-high, and high-high) by using the discrete wavelet transform compression algorithm. Then, the low-low sub-band was transmuted to frequency components (low and high) via discrete wavelet transform. Next, these components were quantized by using scalar quantization and then scanning in a zigzag way. The compression ratio result is 15.1 to 27.5 for magnetic resonance imaging with a different peak signal to noise ratio and mean square error; 25 to 43 for X-ray images; 32 to 46 for computed tomography scan images; and 19 to 36 for magnetic resonance imaging brain images. The second approach showed an improved compression scheme compared to the first approach considering compression ratio, peak signal to noise ratio, and mean square error.
International Journal of Computers and Applications, 2003
A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was... more A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was used to perform image segmentation and edge detection tasks. We obtained an initial segmentation based on K-means clustering technique. Starting from this, we used two techniques; the first is watershed technique with new merging procedures based on mean intensity value to segment the image regions and to detect their boundaries. The second is edge strength technique to obtain an accurate edge maps of our images without using watershed method. In this paper: We solved the problem of undesirable oversegmentation results produced by the watershed algorithm, when used directly with raw data images. Also, the edge maps we obtained have no broken lines on entire image and the final edge detection result is one closed boundary per actual region in the image.
Journal of Engineering and Applied Sciences, Dec 20, 2019
Smoothing an image under the curvature of its level sets (Mean curvature flow), create contour pl... more Smoothing an image under the curvature of its level sets (Mean curvature flow), create contour plot of image data were used. To do that, a high level function (evolve2D) was used that can utilize any combination of: 1) a force in the normal direction to the curve, 2) a curvature-based force, and 3) evolution under the influence of an external vector field. This function takes an input, evolves it N iterations and returns the result. So; in this paper, all level sets of the image are smoothed under curvature-based forces and the level sets of the original image are calculated. Then the image was smoothed after 25-50 iterations of smoothing, and then we calculated its corresponding level sets. Also in this paper the Matlab function IMCONTOUR (img) was used to draw a contour plot of the intensity image (img). The method gives us accurately the level sets of our image before and after smoothing. The processing time for different processed images was calculated. Finally the results were compared with active contour method and levelset without re-initialization method.
The International Arab Journal of Information Technology, 2006
A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was... more A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was used to perform image segmentation and edge detection tasks. We obtained an initial segmentation based on K-means clustering technique. Starting from this, we used two techniques; the first is watershed technique with new merging procedures based on mean intensity value to segment the image regions and to detect their boundaries. The second is edge strength technique to obtain an accurate edge maps of our images without using watershed method. In this paper: We solved the problem of undesirable oversegmentation results produced by the watershed algorithm, when used directly with raw data images. Also, the edge maps we obtained have no broken lines on entire image and the final edge detection result is one closed boundary per actual region in the image.
Iraqi journal of science, Dec 30, 2021
Image segmentation is a basic image processing technique that is primarily used for finding segme... more Image segmentation is a basic image processing technique that is primarily used for finding segments that form the entire image. These segments can be then utilized in discriminative feature extraction, image retrieval, and pattern recognition. Clustering and region growing techniques are the commonly used image segmentation methods. K-Means is a heavily used clustering technique due to its simplicity and low computational cost. However, K-Means results depend on the initial centres" values which are selected randomly, which leads to inconsistency in the image segmentation results. In addition, the quality of the isolated regions depends on the homogeneity of the resulted segments. In this paper, an improved K-Means clustering algorithm is proposed for image segmentation. The presented method uses Particle Swarm Intelligence (PSO) for determining the initial centres based on Li"s method. These initial centroids are then fed to the K-Means algorithm to assign each pixel into the appropriate cluster. The segmented image is then given to a region growing algorithm for regions isolation and edge map generation. The experimental results show that the proposed method gives high quality segments in a short processing time.
Mammograms Segmentation and extraction for breast cancer regions based on region growing
Journal of Baghdad College of Economic sciences University, 2019
Iraqi Journal of Science
The past years have seen a rapid development in the area of image compression techniques, mainly ... more The past years have seen a rapid development in the area of image compression techniques, mainly due to the need of fast and efficient techniques for storage and transmission of data among individuals. Compression is the process of representing the data in a compact form rather than in its original or incompact form. In this paper, integer implementation of Arithmetic Coding (AC) and Discreet Cosine Transform (DCT) were applied to colored images. The DCT was applied using the YCbCr color model. The transformed image was then quantized with the standard quantization tables for luminance and chrominance. The quantized coefficients were scanned by zigzag scan and the output was encoded using AC. The results showed a decent compression ratio with high image quality.
Journal of Engineering
Early detection of brain tumors is critical for enhancing treatment options and extending patient... more Early detection of brain tumors is critical for enhancing treatment options and extending patient survival. Magnetic resonance imaging (MRI) scanning gives more detailed information, such as greater contrast and clarity than any other scanning method. Manually dividing brain tumors from many MRI images collected in clinical practice for cancer diagnosis is a tough and time-consuming task. Tumors and MRI scans of the brain can be discovered using algorithms and machine learning technologies, making the process easier for doctors because MRI images can appear healthy when the person may have a tumor or be malignant. Recently, deep learning techniques based on deep convolutional neural networks have been used to analyze medical images with favorable results. It can help save lives faster and rectify some medical errors. In this study, we look at the most up-to-date methodologies for medical image analytics that use convolutional neural networks on MRI images. There are several approach...
An Improved Probability Density Function (PDF) for Face Skin Detection
Iraqi Journal of Science
Face Detection by skin color in the field of computer vision is a difficult challenge. Dete... more Face Detection by skin color in the field of computer vision is a difficult challenge. Detection of human skin focuses on the identification of pixels and skin-colored areas of a given picture. Since skin colors are invariant in orientation and size and rapid to process, they are used in the identification of human skin. In addition features like ethnicity, sensor, optics and lighting conditions that are different are sensitive factors for the relationship between surface colors and lighting (an issue that is strongly related to color stability). This paper presents a new technique for face detection based on human skin. Three methods of Probability Density Function (PDF) were applied to detect the face by skin color; these are the Extreme Value Distribution Function and the Exponential Distribution Function methods, in addition to a new proposed model, over the HSV (Hue, Saturation, and Value) color space. The suggested technique aims to enhance skin pixel detection and impro...
Edge detection and image segmentation based on K-means and watershed techniques
Image Matching and Analysis, 2001
In this paper, we present a method that incorporates k-means and watershed segmentation technique... more In this paper, we present a method that incorporates k-means and watershed segmentation techniques for performing image segmentation and edge detection tasks. Firstly we used k-means techniques to examine each pixel in the image and assigns it to one of the clusters depending on the minimum distance to obtain primary segmented image into different intensity regions. We then employ a
Journal of Southwest Jiaotong University, 2019
Medical image compression is considered one of the most important research fields nowadays in bio... more Medical image compression is considered one of the most important research fields nowadays in biomedical applications. The majority of medical images must be compressed without loss because each pixel information is of great value. With the widespread use of applications concerning medical imaging in the health-care context and the increased significance in telemedicine technologies, it has become crucial to minimize both the storage and bandwidth requirements needed for archiving and transmission of medical imaging data, rather by employing means of lossless image compression algorithms. Furthermore, providing high resolution and image quality preservation of the processed image data has become of great benefit. The proposed system introduces a lossless image compression technique based on Run Length Encoding (RLE) that encodes the original magnetic resonance imaging (MRI) image into actual values and their numbers of occurrence. The actual image data values are separated from thei...
International journal of simulation: systems, science & technology, 2020
Breast cancer is one of the most common malignant diseases among women. Mammography is at present... more Breast cancer is one of the most common malignant diseases among women. Mammography is at present one of the available methods for early detection of abnormalities, which is related to breast cancer different lesions to show characteristics such as masses, which can be detected through this technique. The images are divided according to the Mini-MIAS database. In order to classify the cluster as malignant or benign, the 2nd order co-occurrence statistical properties of the image such as contrast, correlation, homogeneity, and energy were adopted. The gray-scale convergent matrices (GLCM) are used with a suggested feature of gray level density matrices (GLDM) to identify abnormal tissues (malignant) and natural tissue (benign). The proposed method of analysis is tested on several images (taken from a UK organization interested in understanding breast X-ray images) from the database of digital mammograms and outstanding results were obtained for breast cancer detection. The proposed multilayered design performance significantly improved the diagnosis of breast cancer by more than 95% and 95.8% sensitivity, 95.5% specificity for all datasets, 91.1% with 100% sensitivity and 84% specificity for 70% training data and 30% testing data.
International Journal of Computers and Applications, 2003
A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was... more A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was used to perform image segmentation and edge detection tasks. We obtained an initial segmentation based on K-means clustering technique. Starting from this, we used two techniques; the first is watershed technique with new merging procedures based on mean intensity value to segment the image regions and to detect their boundaries. The second is edge strength technique to obtain an accurate edge maps of our images without using watershed method. In this paper: We solved the problem of undesirable oversegmentation results produced by the watershed algorithm, when used directly with raw data images. Also, the edge maps we obtained have no broken lines on entire image and the final edge detection result is one closed boundary per actual region in the image.
Computer Science & Information Technology ( CS & IT ), 2013
In the first study [1], a combination of K-means, watershed segmentation method, and Difference I... more In the first study [1], a combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map were used to perform image segmentation and edge detection tasks. We obtained an initial segmentation based on K-means clustering technique. Starting from this, we used two techniques; the first is watershed technique with new merging procedures based on mean intensity value to segment the image regions and to detect their boundaries. The second is edge strength technique to obtain accurate edge maps of our images without using watershed method. In this technique: We solved the problem of undesirable over segmentation results produced by the watershed algorithm, when used directly with raw data images. Also, the edge maps we obtained have no broken lines on entire image. In the 2nd study level set methods are used for the implementation of curve/interface evolution under various forces. In the third study the main idea is to detect regions (objects) boundaries, to isolate and extract individual components from a medical image. This is done using an active contours to detect regions in a given image, based on techniques of curve evolution, Mumford-Shah functional for segmentation and level sets. Once we classified our images into different intensity regions based on Markov Random Field. Then we detect regions whose boundaries are not necessarily defined by gradient by minimize an energy of Mumford-Shah functional for segmentation, where in the level set formulation, the problem becomes a mean-curvature which will stop on the desired boundary. The stopping term does not depend on the gradient of the image as in the classical active contour. The initial curve of level set can be anywhere in the image, and interior contours are automatically detected. The final image segmentation is one closed boundary per actual region in the image.
Advances in Image and Video Processing, 2015
In this article a new combination of image segmentation techniques including K-means clustering, ... more 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.
Uploads
Papers by Nassir Hussien Salman