Keywords : Pattern recognition


Textures Recognition using Elman Neural Network

Fawziya Mahmood Ramo; Alaa Anwr Mohamed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2014, Volume 11, Issue 1, Pages 97-108
DOI: 10.33899/csmj.2014.163741

         In this research building system to recognition  texture images using artificial neural networks. The system consists of two phases: phase extraction important feature of each texture by using an algorithm Principal Components Analysis (PCA)   and recognition phase which recognize these feature by using  Elman network were trained network on a number of various texture  models down to the steady-state network  and then test the network by input  samples  of textures.  The experiments show that the method achieves high performance and produces 92% recognition rate.
 

Hybridization of a hidden Markov model using Elman neural network with application

Omar Saber Qasim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2014, Volume 11, Issue 1, Pages 25-42
DOI: 10.33899/csmj.2014.163737

This research aims to improve the performance of the work of hidden Markov model, which is limited to the positive integers as input, and through the use of Elman artificial neural network that have the ability to accept all types of data in the input space. The proposed model has proved that it is highly efficient in the classification of osteoporosis data compared with Elman artificial neural network on the one hand and the hidden Markov model on the other.
 

Hybridization of the Artificial Immune Network Using the Backpropagation Neural Network

Omar Saber Qasim; Israa Rustum Mohammed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2013, Volume 10, Issue 4, Pages 103-114
DOI: 10.33899/csmj.2013.163559

In this research building style simulation developed is applied in the field of pattern recognition medical patients osteoporosis through a process of integrating and hybridization between artificial immune network and back propagation neural network, where the focus was on the qualities positive and overcome the negative qualities possessed by each of these two technologies by building technology improved, have proven technical hybrid it with better results and high efficiency in the classification of cases patients osteoporosis compared with both artificial immune network (AIN) and back propagation neural network (BP).
 

The Use of the Artificial Immune Network Algorithm AIN in Distinguishing English Character Pattern

Maha Abd Alellah Mohammad

AL-Rafidain Journal of Computer Sciences and Mathematics, 2013, Volume 10, Issue 1, Pages 147-156
DOI: 10.33899/csmj.2013.163448

The focus of the present research is on the issue of patterns compatibility regarding an English letter through the use of a probable research Algorithm called the Artificial Immune Network (AIN(. The research clarifies the algorithm ability in patterns compatibility between the original (ideal) pattern of the letter and the deformed patterns since the Artificial Immune Network (AIN (is good for some tasks that require examples. It applies to the issues that have large (wide) areas and large variables. In addition, it can also be quickly and easily solved as well as it provides a solution that is quite near to the ideal solution of the patterns used, The data base used contain file involves data for each original (ideal) pattern of the English letter, the pattern recognition operation (template matching) provided %94 by using Artificial Immune Network. knowing that we obtain the practical result by using MATLAB 2008.
 

Genetic Pattern Recognition using Intelligent Techniques

Basil Younis Thanoon; Omar Saber Qasim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2010, Volume 7, Issue 3, Pages 161-172
DOI: 10.33899/csmj.2010.163935

In this research a light is shed on converting DNA series to amino acid being responsible for forming protein through intelligent techniques. Some comparisons have been made between particularly Artificial Neural Network, Fuzzy Logic and Genetic Algorithms for discovering the powerful and the week ones in particle way. The hybrid operation has been made between Artificial Neural Network and Fuzzy Logic t to get a hybrid technique in a new formula having robust results than the original ones.
 
 

Use Artificial Neural Network Neococcontron in Distinguishing Handwritten Arabic Numerals

Laheeb Mohammad Ibrahim; Hanan H. Ali

AL-Rafidain Journal of Computer Sciences and Mathematics, 2009, Volume 6, Issue 1, Pages 47-59
DOI: 10.33899/csmj.2009.163784

Artificial Neural Networks have wide applications now a day, Among these are in the field of pattern recognition and image processing. This is due to the fact that it has a good performance and advanced mathematical computation power particularly its flexible adaptation to parallelism technique. That is why this research is conducted for the recognition of hand written Arabic numbers (0 - 9). Recognition artificial neural network is simulated the human eye for tracking the property of entered image (Feature extractor).
The systems  examined on  samples of Arabic  numbers its performance  was found to be balanced in spite of the variations in position and direction of the recognized number.
 

Detect Flame Fire Using Fractal Geometry in Color Digital Images

Laheeb Mohammad Ibrahim; Khalil I. Alsaif; Hasan M. Alnima

AL-Rafidain Journal of Computer Sciences and Mathematics, 2009, Volume 6, Issue 1, Pages 61-78
DOI: 10.33899/csmj.2009.163785

Pattern recognition, which takes features extraction as a basis for decision making, is considered as of the cutting-edge technologies. It is used in various useful applications such as tracking and monitoring objects.
In this research an algorithm for detecting fire flame in the colored digital images is built. The algorithm basically depends an extracting the features of flame spots with all its spectra with reference to fractal dimension. The input image is cut into a set of equal dimension squares, then fractal dimension for each square is calculated using two-dimension variation algorithm, which is are of the algorithms used in calculating fractal dimension. Fractal dimension values in the output fractal dimension array are analyzed to detect flame spots using the computer through determining the common features and characteristics of the flame with all its spectra.