Keywords : digital image


Medical Image Classification Using Different Machine Learning Algorithms

Sami H. Ismael; Shahab W. Kareem; Firas H. Almukhtar

AL-Rafidain Journal of Computer Sciences and Mathematics, 2020, Volume 14, Issue 1, Pages 135-147
DOI: 10.33899/csmj.2020.164682

The different types of white blood cells equips us an important data for diagnosing and identifying of many diseases. The automation of this task can save time and avoid errors in the identification process. In this paper, we explore whether using shape features of nucleus is sufficient to classify white blood cells or not. According to this, an automatic system is implemented that is able to identify and analyze White Blood Cells (WBCs) into five categories (Basophil, Eosinophil, Lymphocyte, Monocyte, and Neutrophil). Four steps are required for such a system; the first step represents the segmentation of the cell images and the second step involves the scanning of each segmented image to prepare its dataset. Extracting the shapes and textures from scanned image are performed in the third step. Finally, different machine learning algorithms such as (K* classifier, Additive Regression, Bagging, Input Mapped Classifier, or Decision Table) is separately applied to the extracted (shapes and textures) to obtain the results. Each algorithm results are compared to select the best one according to different criteria’s.
 

Digital Image Compression using Karhunen-Loève Transform

Ghada Thanoon Younes

AL-Rafidain Journal of Computer Sciences and Mathematics, 2013, Volume 10, Issue 3, Pages 47-59
DOI: 10.33899/csmj.2013.163535

In this research present the digital image compression using by  Karhunen-Loève Transform (KLT), by convert a color digital  image to a gray square digital image, then select the no. of eigen values and eigen vectors that can reconstruct the image,  that be very near to the original image.
And then calculate compression ratio and a high result reach it, after applied fidelity criteria on image produce from compression represented by (PSNR, MSE, correlation coefficient and compression ratio), and using a matlab language programming for execute this research.
 

Using Genetic Algorithm to Reduce the Noise Effect on Images

Baydaa S Bhnam

AL-Rafidain Journal of Computer Sciences and Mathematics, 2012, Volume 9, Issue 2, Pages 127-142
DOI: 10.33899/csmj.2012.163723

This paper deals with a problem that concentrates on the noise removal that the images are affected from different resources employing Genetic Algorithm with filters. To achieve the aims of the paper, six types of genetic filters are suggested for noise removal from the images. These suggested genetic filters depending on filters (mean, median, min and max) as an objective function for them.
These suggested genetic filters are applied on several real images contaminated by two types of noise with different levels for comparison and to show the effectiveness of them. The result show that The fifth genetic filter that depends on the median filter as an objective function and heuristic crossover and  adding and subtracting mutation, gives the best results with RMSE=15.7243 and PSNR=24.1646 for Lena.bmp image and with RMSE=8.6197 and PSNR=29.4210 for girl.png image when add 0.05 salt & paper noise.
 

Comparison on Color Quantization Techniques

Alyaa taqi

AL-Rafidain Journal of Computer Sciences and Mathematics, 2008, Volume 5, Issue 1, Pages 95-115
DOI: 10.33899/csmj.2008.163965

Due to the fast and high development in computer technology and the reflection of this development on digital images ,many image processing algorithms became in need to initialization steps for the image before starting the actual operations of the algorithms and the program. Image quantization is one of the important operations in image processing field and it is the first step in  many digital image applications.
This technique is based on taking the best colors  from the original image and produce a new image with a new quality with less colors and with small error ratio. There are many image quantization methods ,but this research focuses on studying three different methods of image quantization and compares  them. These methods are:

Quantization by mask
Uniform Quantization
Half toning Quantization


After programming the methods we could reach a high degree of clarity in image after reducing  its color. The research was applied on different types of images to find the best method for each image  with small error ratio and that depends on the contents and on color distributions in the image .(Matlab7) was used for programming these methods.