research centers


Search results: Found 3

Listing 1 - 3 of 3
Sort by

Article
Hand Written Recognition Using Neural Network Algorithm

Author: Ammar O. Hoori
Journal: Journal of Engineering مجلة الهندسة ISSN: 17264073 25203339 Year: 2010 Volume: 16 Issue: 4 Pages: 5855- 5862
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Hand written recognition problem can be done in two major steps, first by separating each character alone and second by detecting the separated shape to its corresponding like alphabetic letter. A backpropagation neural network found to be a good artificial intelligence algorithm in facing character recognition problem. In this work, backpropagation neural network is used with 3-layers to detect and separate 26 English letter from (A to Z). In addition, a previous steps should be taken to detect the boundaries of each single written letter. Detecting a complete text can be done by separating each character through finding its boundaries, resizing the separated character to be suitable for pre-trained neural network, detecting the hand-written letter and finally saving the guessed letter to a text file. This work is developed using Matlab 2008 version 7.6. The obtained results show good representations of letter contaminated by noise and non-trained letters.

مشكلة تمييز خط اليد المكتوب تتم على خطوتين رئيسيتين ، أولاً من خلال فصل كل شكل على حدة وثانياً بتمييز الشكل المفصول للحرف الأبجدي المشابه له. الخلية العصبية ذات الانتشار الخلفي وجدت كلوغارتمية ذكاء اصطناعي جيدة في مواجهة مشكلة تمييز الأشكال.في هذا العمل، . الخلية العصبية ذات الانتشار الخلفي استخدمت بثلاث طبقات لإيجاد وفصل 26 حرف انكليزي من (A إلى Z). بالإضافة لذلك ، هنالك خطوات مسبقة يجب أن تتخذ ، وذلك لإيجاد حدود كل حرف مكتوب بخط اليد. إيجاد نص كامل ممكن أن يتم بعزل كل شكل من خلال إيجاد حدوده ، ثم تعديل حجم الشكل المعزول ليكون ملائماً للخلية العصبية المُعلمة مسبقاً، ثم بإيجاد الحرف المكتوب بخط اليد ، وأخيراً حفظ الحرف المحزور في ملف كتابة. هذا العمل أنجز باستخدام برنامج Matlab الإصدار 7.6 لعام 2008. النتائج المكتسبة أظهرت تمثيل جيد للأحرف الملوثة بالشوائب والأحرف الغير معلمة مسبقاً.


Article
Cosine Transform and Shift Number Coding uses for 24-Bit Bitmap image Coding

Author: Ammar O. Hassan Al-barznji
Journal: Journal Of Wassit For Science & Medicine مجلة واسط للعلوم والطب ISSN: 58161992 Year: 2011 Volume: 4 Issue: 1 Pages: 166-178
Publisher: Wassit University جامعة واسط

Loading...
Loading...
Abstract

Abstract:
This paper represents an approach for image coding which consists of three parts: The first part is DCT which is used one dimensional discrete cosine transform converts each (n-pixel) into frequency domain, then reduces number of frequency domain elements by deleting half number of elements. The second part applies SNC (Shift Number Coding) on the remained coefficient elements, these elements are converted to integer number. SNC does not need to compute the probability for an image file, just compute the values for each coefficient in frequency domain matrix. The value is computed by selecting maximum number in matrix, then it divides the interval {0…1} by maximum number. This value is shifted by shift function then sum with previous value, the total values represent Compression Value. Finally the arithmetic coding used to compress the matrix of compression value into stream of bits. This approach is tested with three types of images, and compared with JPEG, PNG, and TIFF by using Compression Ratio and PSNR.

Keywords


Article
Numerical Investigation for Enhancement of Heat Transfer in Internally Finned Tubes Using ANSYS CFX Program

Authors: Ali Shakir --- Ammar O --- Nofil Baqer
Journal: Basrah Journal for Engineering Science مجلة البصرة للعلوم الهندسية ISSN: Print: 18146120; Online: 23118385 Year: 2015 Volume: 15 Issue: 1 Pages: 32-42
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

In this study, a numerical investigation has been carried out for single phase flow behavior for thirty six internally finned tubes to demonstrate the effect of axial pitch to fin height ratio (p/e) for 0.8≤p/e≤6.345, helix angle of internal fins (β) for 30°≤β≤70°, apex angle of internal fins (α) for 0°≤α≤53.13°, internal fin height (e) for 0.6mm≤e≤1.0mm, internal tube diameter (di) with 14 mm and Reynolds number (Re) of single phase flow for 10000≤Re≤50000 on enhancement of forced convection heat transfer and reduction of friction factor by using ANSYS CFX program. It solves the three-dimensional Navier-Stokes equations for steady state turbulent with SST model and enhance wall treatment. The numerical analysis provided at fully developed velocity and temperature. Numerical results showed that the smallest axial pitch to fin height ratio (p/e) =0.8 and with apex angle α=10 degree provided enhancement of heat transfer of 2.8 to 3.55 times higher than of smooth tube. Finally, present numerical results are seen to be in good agreement with literature experimental correlations.

Listing 1 - 3 of 3
Sort by
Narrow your search

Resource type

article (3)


Language

English (3)


Year
From To Submit

2015 (1)

2011 (1)

2010 (1)