research centers


Search results: Found 3

Listing 1 - 3 of 3
Sort by

Article
Indian Number Handwriting Features Extraction and Classification using Multi-Class SVM

Author: H.A. Jeiad
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 1 Part (A) Engineering Pages: 33-40
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

In this paper, an Indian Number Handwriting Recognition Model (INHRM) is proposed. Mainly, the proposed model consists of four phases which are the image acquisition, image preprocessing, features extraction, and classification model. Initially, the captured images of the handwritten Indian numbers were enhanced and preprocessed to obtain the skeleton for the interested object. The extracted features of the handwritten Indian numbers were obtained by calculating four parameters for each captured number sample, these parameters are the number of starting points, the number of intersection points, the average zoning which consists of four values, and finally, the normalized chain vector of length of 10 elements. So, the resulted 16 values of the four parameters were arranged in a vectors of length of 16 elements. These features vectors were used in the training and testing processes of the proposed INHRM model. Multi-class SVM (MSVM) approach is suggested for the classification phase. An accumulation of 600 samples of various handwritten Indian numbers styles has been gathered from a group of 60 students. These samples were preprocessed, features extracted, then delivered to the classification phase by utilizing 500 samples of them for training while the remaining 100 samples were used for testing of the MSVM-classifier model. The results showed that the proposed INHRM achieved relatively high percentage of exactness of around 97%.


Article
Combine SVM and KNN classifiers for Handwriting Arabic Word Recognition based on Multifeatures
دمج مصنفات الجار الاقرب والة دعم المتجهات لتمييز الكلمات العربية المكتوبة بخط اليد بالاعتماد على الصفات المتعددة

Author: Alia Karim Abdul Hassan علياء كريم عبد الحسن
Journal: Al-Rafidain University College For Sciences مجلة كلية الرافدين الجامعة للعلوم ISSN: 16816870 Year: 2018 Issue: 43 Pages: 303-323
Publisher: Rafidain University College كلية الرافدين الجامعة

Loading...
Loading...
Abstract

This paper presents a proposed system for recognizing the handwritten Arabic words. The proposed system recognized the Arabic word as one entity without using segmentation stage, which converted the word into parts. A proposed method for feature extraction stage used two groups of feature extraction techniques. First group combines two techniques and the second group used single technique. First group combines gradient (directional) feature method with the Run Length Count method and second group based on Discrete Cosine Translation technique. Classification stage is based on combined SVM with KNN classifiers. A standard data set which is AHDB database is used to simulate the proposed system. The recognition accuracy for the experimental results of the proposed system is 97.11 %.

نقدم في هذا البحث نظاما مقترحا لتمييز الكلمات العربية المكتوبة بخط اليد. النظام المقترح يمييز الكلمة العربية ككيان واحد دون استخدام مرحلة التقسيم والتي تحول الكلمة إلى أجزاء. في مرحلة استخراج الصفات تم دمج تقنيات استخلاص الصفات الى مجموعتين. المجموعة الأولى تتالف من تقنيتين. تجمع بين طريقة اتجاه الانحدار gradient (directional) feature مع طريقة حساب طول المسار Run Length Count بينما المجموعة الثانية تستخدم تقنية واحدة وهي طريقة تحويل الجيب تمام المنقطع Discrete Cosine Transform. مرحلة التصنيف تعتمد على دمج نوعين من المصنفات وهما SVM و KNNآلة دعم المتجهات و الجار الاقرب. تم اختبار النظام المقترح باستخدام قاعدة بيانات قياسية التي هيAHDB . ان دقة التميز النتائج التجريبية للنظام المقترح هي 97.11٪.


Article
ON-LINE HANDWRITTEN ARABIC CHARACTER RECOGNITION BASED ON GENETIC ALGORITHM
تشخیص الاحرف العربیة بالكتابة المباشرة إعتمادا على الخوارزمیة الجینیة

Author: Haithem Abd Al-RaheemTaha هیثم عبد الرحیم طه
Journal: DIYALA JOURNAL OF ENGINEERING SCIENCES مجلة ديالى للعلوم الهندسية ISSN: 19998716/26166909 Year: 2012 Volume: 5 Issue: 1 Pages: 79-87
Publisher: Diyala University جامعة ديالى

Loading...
Loading...
Abstract

ABSTRACT:- On-line Arabic handwritten character recognition is one of the most challenging problems in pattern recognition field. By now, printed Arabic character recognition and on-line Arabic handwritten recognition has been gradually practical, while offline Arabic handwritten character recognition is still considered as "The hardest problem to conquer" in this field due to its own complexity. Recently, it becomes a hot topic with the release of database, which is the first text-level database and is concerned about the area of realistic Arabic handwritten character recognition. At the realistic Arabic handwritten text recognition and explore two aspects of the problem. Firstly, a system based on segmentation-recognition integrated framework wasdeveloped for Arabic handwriting recognition. Secondly, the parameters of embedded classifier initialed at character-level training were discriminatively re-trained at string level. The segmentation-recognition integrated framework runs as follows: the written character is first over-segmented into primitive segments, and then the consecutive segments are combined into candidate patterns. The embedded classifier is used to classify all the candidate patterns in segmentation lattice. According to Genetic Algorithm (Crossover, mutation, and population), the system outputs the optimal path in segmentation-recognition lattice, which is the final recognition result. The embedded classifier is first trained at character level on isolated character and then the parameters are updated at string level on string samples.Keywords: Arabic Character, handwritten recognition, Genetic Algorithm.

الخلاصةان تشخیص كتابة الاحرف العربیة في الزمن الحقیقي یعتبر من اكثر التحدیات في مجال التعرف على الاشكال. وهناك دراسات حول التشخیص للاحرف العربیة ما زالت تعتبر من المشاكل المعقده في هذا المجال. الهدف من البحث هو التشخیص للاحرف العربیة بخط الید واستكشاف الجوانب الثلاثة في بحثنا، اولا ان النظامیقوم على ت شخیص بشكل مجزء ضمن الاطار المتكامل للتعرف على خط الید باللغة العربیة، ثانیا،ً ان البارامیترات الخاصة بالتصنیف لعملیة البدء عند مستوى التعلیم لحالة الحرف المخطوط یدویا تقوم بتمییز مستوى الحرف عند مستوىالتدریب.تشخیص المقاطع في اللوحة المهیئة لكتابة الحرف تكون حسب التالي: كتابة الحر ف المقاطع الاولیة، وبعد ذلك یتم جمع المقاطع على التوالي في نموذج ترشیحي.و ثم یتم تصنیف جمیع النماذج في شبكه عبار ة عن مقاطع. وبالاستناد الى الخوارزمیة الجینیة (التبادل، الطفرات، والتوزیع)، فان الاخراج یكون ناتج عن المسار الامثل في للنموذج الترشیحي وهي التي تعتبر الناتج النهائي. یتم تدریب المصنف الأول على مستوى جزءا لا یتجزأ وذلك بعزل حرف على حرف ومن ثم یتم تحدیث المعلمات على مستوى السلسلة على عینات تم حفظها في قاعدة بیانات لمقارنتها مستقبلا بالادخال الجدید.

Keywords

ABSTRACT:- On-line Arabic handwritten character recognition is one of the most challenging problems in pattern recognition field. By now --- printed Arabic character recognition and on-line Arabic handwritten recognition has been gradually practical --- while offline Arabic handwritten character recognition is still considered as "The hardest problem to conquer" in this field due to its own complexity. Recently --- it becomes a hot topic with the release of database --- which is the first text-level database and is concerned about the area of realistic Arabic handwritten character recognition. At the realistic Arabic handwritten text recognition and explore two aspects of the problem. Firstly --- a system based on segmentation-recognition integrated framework was developed for Arabic handwriting recognition. Secondly --- the parameters of embedded classifier initialed at character-level training were discriminatively re-trained at string level. The segmentation-recognition integrated framework runs as follows: the written character is first over-segmented into primitive segments --- and then the consecutive segments are combined into candidate patterns. The embedded classifier is used to classify all the candidate patterns in segmentation lattice. According to Genetic Algorithm --- Crossover --- mutation --- and population --- the system outputs the optimal path in segmentation-recognition lattice --- which is the final recognition result. The embedded classifier is first trained at character level on isolated character and then the parameters are updated at string level on string samples. Keywords: Arabic Character --- handwritten recognition --- Genetic Algorithm.

Listing 1 - 3 of 3
Sort by
Narrow your search

Resource type

article (3)


Language

English (3)


Year
From To Submit

2018 (2)

2012 (1)