Curriculum Vitae

Publications

-Nov. 2009 Kurdish speaker identi.cation using two techniques hybrid MFCC, Journal of Zankoy Sulaimani Part A

We implemented and compared two di.fferent techniques: Hyper Multiwalidelet transformation

and Mel-Frequency Ceptral Coe.cient (MFCC) to identify Kurdish speaker. The experiment

results showed that Hybrid technique carried more original discriminated than MFCC, and gave

better identi.cation rate.

-J. GulMohammed, W. Ammen Mahmud Al-Jaouhar, T. Jawad Abas, Jan. 2014 A generic classi.cation-based method for segmentation of nuclei in 3D images of early embryos BMC Bioinformatics. 

 We developed a novel generic algorithm for segmentation and classi.cation in 3D images. The

method, referred to as Parameter-free Generic Iterative Thresholding Algorithm (PAGITA).

-J. GulMohammed, I. Arganda-Carreras, P. Andrey, V. Galy, T.Boudier, April 2014 Classi.ed region-growing for 3D segmentation of packed nuclei ISBI2014 

We present a new alternative for segmentation and classi.fication by merging them into one

classi.fied region-growing algorithm. The combination of region growing and machine learning

enabled us to both segment touching nuclei, and also classify them, even if their shape is changing

in a dynamic context.