تنزيل السيرة الذاتية

معلومات الاتصال

الباحث العلمي

أ. فرج جمعة اعمار ازبيدة

  • المؤهل العلمي: ماجستير
  • الدرجة العلمية: محاضر
  • كلية الهندسة - جامعة الزيتونة

ملخص

فرج ازبيدة هو احد اعضاء هيئة التدريس بقسم الحاسب الآلي بكلية كلية الهندسة. يعمل السيد فرج ازبيدة بجامعة الزيتونة كـمحاضر منذ 2016-10-01 وله العديد من المنشورات العلمية في مجال تخصصه

المؤهلات

11 ,2008

ماجستير

هندسة حاسب آلي
أكاديمية الدراسات العليا , طرابلس - ليبيا

7 ,2002

بكالوريوس

هندسة حاسب آلي
المعهد العالي للإلكترونات بني وليد

المنشورات

Principal Component Analysis for Face Recognition

Abstract - Humans have used Biometric characteristics such as face, voice, and gait for thousands of years to recognize each other. Biometrics (also known as biometry) is defined as the identification of an individual based on biological traits, such as fingerprints, iris patterns, and facial features. The main objective of this paper is to implement face recognition system using Principle Component Analysis (PCA), where a model is trained for each user. This target can be mainly decomposed into image preprocessing, feature extraction and feature matching. The Euclidean distance and Chessboard distance classifiers were used. Finally, the comparisons between the two classifiers is reported.
Farag J Zbeda, (12-2008)


PCA-HOG Descriptors for Face Recognition in very Small Images

Abstract - Face recognition has become an important issue in many applications such as security systems, credit card verification and criminals identification. In tiny images people appear very small, but we may still be interested in detecting faces for recognition or analysis. In this paper we take advantage of both HOG and PCA for object recognition in very small images, where firstly we use HOG to extract features from the images at different scales and then apply PCA to reduce the dimensionality of these feature vectors.
Farag J Zbeda, (9-2016)
Publisher's website


Improved Cascade and Recursive Median Filters to detect and suppress random impulse noise from images

Abstract - In Digital Image Processing, Image Restoration involves the reconstruction or recovery of the original image from the degraded image, there are many algorithms used in this area depend on the types of noise. An improved cascaded and recursive median filters for the restoration of gray scale images that are corrupted by impulse noise is proposed in this paper. The main objective of this paper is to improve and compare two filtering algorithms," Cascade Median Filter and Recursive Median Filter ". Every pixel in the original image will be tested first to determine whether it is corrupted with noise or not, then the filters will be applied on the corrupted pixel while the uncorrupted pixels will be retained. The results of comparative analysis is measured using Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR).
Farag J Zbeda, (10-2018)


Modified Enhanced Recursive Median Filter for Image De-noising

Abstract ـــ Despite begin known for many years that an enhancement and analysis of digital image has been played an important role in many engineering applications. The enhancement technique usually performed through nonlinear filter rather than linear filter. The performance of an image filtering system depends on algorithms ability to detect the presence of noisy pixels in the image. This paper, deals with impulse noise in every pixel in the image, which will be tested first to determine whether if it is corrupted or not. So the Modified Enhanced Recursive Median Filter will be applied on the corrupted pixels while the uncorrupted pixels is retained. The performance of proposed filter is measured visually and also numerically using Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) of different filtered images. It shows the capability to remove low and high density impulsive noise and preserving the edges.
Farag J Zbeda, (3-2019)


Noise Reduction from Video Using Linear and Nonlinear Filters

Abstract - Video and image processing is a form of signal processing where the input is an image, such as photographs or frames of video, and the output can be either an image or a set of characteristics or parameters related to the image. When a device such as a camera or scanner captures an image, the device sometimes adds extraneous noise to the image, or the noise may be added to the video or image during the transmission process from source to destination, this. Some types of noise can be simply removed, but most noise requires more involved filtering. this paper will compare reduction of noise from video using Finite impulse response filter and median filter in spatial domain.
Farag J Zbeda, (10-2009)