Keywords : Back Propagation network


Improvement of Color Correction for Digital Photographs

Manar Younis Kashmola; Zahraa Mazin Al Kattan

AL-Rafidain Journal of Computer Sciences and Mathematics, 2010, Volume 7, Issue 3, Pages 57-76
DOI: 10.33899/csmj.2010.163927

In other way misuse of correct illumination at the capture moment could affect the image landmarks ; regarding color brightness and the increasing “color cast “ which might cause the image to appear in an unacceptable Or unexpected manner. Thus; several algorithms have been developed to solve these problems and balancing image color and recover the real color of the landscape.
In this research an algorithm has been developed, depending on some statistics tools like (Mean, Variance and Equivalent Circle). Which leads to finding out the influential color in the image which leads to the alteration of the nature of its colors. It is called “color cast “. It could be classified into evident cast, predominant color, ambiguous cast or no cast. Then removing the cast distortion from the image and using error back propagation network for images classification into color cast carrier or uncarrier. This research has been applied on colored digital photos (BMP). More than (100) colored images were  also used containing all sorts of color cast that will be found out, classified and finally removed  from the image by using algorithm. The percentage of images which have no cast are (27%),The images have evident cast are (25%), where the images which have ambiguous cast are (16%),At the last ;the images which classified as predominant color are (12%),as well as there are (20%) of images classified as wrong .
 

Adoption of Neural Networks to Classified the Gender of the Speaker

Khalil I. Al-Saif; Mason Kh. Al-Nuaimi

AL-Rafidain Journal of Computer Sciences and Mathematics, 2010, Volume 7, Issue 3, Pages 47-56
DOI: 10.33899/csmj.2010.163926

In this research the neural network was adopted to classified the gender of the spoken, by creating the two dimension matrix from the parameters of the spoken speech signal which normal was snigle dimension array.
            The porpose algorithm in this research divided in two stage :-
            In the first stage the seven moment were calculated for a set of spoken signal of 50 persons , to be followed creating database depend on the seven moments .This database will be used to find the threshould value for both genders (male/female) which will be trained  by neural network to classify any  input tothe network.
In the second stage , speech  of any spoken will be selected and the same feature will be extracted , as in the first stage  , to be used as input to the neural network which was traind previously for gender recognition.
Back propagation neural network was achieved for recognition. The result of the applied algorithem on 10 spoken passed on 8 of them and 2 of them was failed .