M
Muhammad Younus Javed
Researcher at National University of Science and Technology
Publications - 33
Citations - 329
Muhammad Younus Javed is an academic researcher from National University of Science and Technology. The author has contributed to research in topics: Iris recognition & Facial recognition system. The author has an hindex of 10, co-authored 33 publications receiving 313 citations. Previous affiliations of Muhammad Younus Javed include National University of Sciences and Technology & University of the Sciences.
Papers
More filters
Proceedings ArticleDOI
Curvelet-Based Image Compression with SPIHT
TL;DR: The empirical results on standard test images provide higher PSNR than some of the previous approaches, which strengthen the idea of using curvelet transform instead of wavelet transform in order to get lesser bits to represent more prominent features.
Proceedings ArticleDOI
Intelligent vertical handover decision model to improve QoS
TL;DR: The fuzzy logic based decision making is used to select among the available networks and can optimize vertical handover and improve QoS of real-time application running on mobile device which is roaming around heterogeneous wireless networks.
Proceedings ArticleDOI
An Automated Approach for Software Bug Classification
TL;DR: In this research, the bugs in open source bug repositories are classified in different labels on the basis of summary of the bug, using Multinomial Naïve Bayes text classifier for classification purpose.
Low Resolution Single Neural Network Based Face Recognition
TL;DR: This research paper deals with the implementation of face recognition using neural network (recognition classifier) on lowresolution images, and uses single neural network as classifier, which produces straightforward approach towards face recognition.
Proceedings ArticleDOI
Evaluation of retinal vessel segmentation methodologies based on combination of vessel centerlines and morphological processing
TL;DR: A performance comparison of two retinal vessel segmentation approaches based on combination of multi scale morphological reconstruction and morphological bit plane slicing with the vessel centerlines demonstrates that morphologicalbit plane slicing outperforms other approach in respect of processing time without a significant degradation of sensitivity and specificity.