Magda Fayek

Dr. Magda Fayek


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Nehal AhmedNehal Ahmed
Nehal Ahmed
EHElsayed Hemayed
Elsayed Hemayed
MFMagda Fayek
Magda Fayek
In this paper, we propose an unconstrained face verification approach that is dependent on Hybrid Siamese architecture under limited resources. The general face verification trend suggests that larger training datasets and/or complex architectures lead to higher accuracy. The proposed approach tends to achieve high accuracy while using a small dataset and a simple architecture by directly learn face’s similarity/dissimilarity from raw face pixels, which is critical for various applications. The proposed architecture has two branches; the first part of these branches is trained independently, while the other parts shared their parameters. A multi-batch algorithm is utilized for training. The training process takes a few hours on a single GPU. The proposed approach achieves near-human accuracy (98.9%) on the Labeled Faces in the Wild (LFW) benchmark, which is competitive with other techniques that are presented in the literature. It reaches 99.1% on the Arabian faces dataset. Moreover, features learned by the proposed architecture are used in building a face clustering system that is based on an updated version of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN). To handle the cluster quality challenge, a novel post-clustering optimization procedure is proposed. It outperforms popular clustering approaches, like K-Means and spectral by 0.098 and up to 0.344 according to F1-measure.

18 May 2017 in Data Science Journal
Verified
Journal Article
Open access
PDF file
MGMohamed A. Gawwad
Mohamed A. Gawwad
MAMona F. Ahmed
Mona F. Ahmed
MFMagda Fayek
Magda Fayek
The discovery of frequent itemsets is one of the very important topics in data mining. Frequent itemset discovery techniques help in generating qualitative knowledge which gives business insight and helps the decision makers. In the Big Data era the need for a customizable algorithm to work with big data sets in a reasonable time becomes a necessity. In this paper we propose a new algorithm for frequent itemset discovery that could work in distributed manner with big datasets. Our approach is based on the original Buddy Prima algorithm and the Greatest Common Divisor (GCD) calculation between itemsets which exist in the transaction database. The proposed algorithm introduces a new method to parallelize the frequent itemset mining without the need to generate candidate itemsets and also it avoids any communication overhead between the participated nodes. It explores the parallelism abilities in the hardware in case of single node operation. The proposed approach could be implemented using map-reduce technique or Spark. It was successfully applied on different size transactions DBs and compared with two well-known algorithms: FP-Growth and Parallel Apriori with different support levels. The experiments showed that the proposed algorithm achieves major time improvement over both algorithms especially with datasets having huge number of items

Verified
Journal Article
Open access
PDF file
RBRanda mohamed bayoumi
Randa mohamed bayoumi
EHElsayed Hemayed
Elsayed Hemayed
MRMohammad Ehab Ragab
Mohammad Ehab Ragab
MFMagda Fayek
Magda Fayek
Video-based person re-identification has become quite attractive due to its importance in many vision surveillance problems. It is a challenging topic due to the inter/intra changes, occlusion, and pose variations involved. In this paper, we propose a pyramid-attentive framework that relies on multi-part features and multiple attention to aggregate features of multi-levels and learns attention-based representations of persons through various aspects. Self-attention is used to strengthen the most discriminative features in the spatial and channel domains and hence capture robust global information. We propose the use of part-relation attention between different multi-granularities of features’ representation to focus on learning appropriate local features. Temporal attention is used to aggregate temporal features. We integrate the most robust features in the global and multi-level views to build an effective convolution neural network (CNN) model. The proposed model outperforms the previous state-of-the art models on three datasets. Notably, using the proposed model enables the achievement of 98.9% (a relative improvement of 2.7% on the GRL) top1 accuracy and 99.3% mAP on the PRID2011, and 92.8% (a relative improvement of 2.4% relative to GRL) top1 accuracy on iLIDS-vid. We also explore the generalization ability of our model on a cross dataset.