Vascular patterns were seen to be a probable identification characteristic of the biometric system. Since then, many studies have investigated and proposed different techniques which exploited this feature and used it for the identification and verification purposes. The conventional biometric features like the iris, fingerprints and face recognition have been thoroughly investigated, however, during the past few years, finger vein patterns have been recognized as a reliable biometric feature. This study discusses the application of the vein biometric system. Though the vein pattern can be a very appealing topic of research, there are many challenges in this field and some improvements need to be carried out. Here, the researchers reviewed

Numeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential a

The challenge in studying fusion reaction when the projectile is neutron or proton rich halo nuclei is the coupling mechanism between the elastic and the breakup channel, therefore the motivation from the present calculations is to estimate the best coupling parameter to introduce the effect of coupled-channels for the calculations of the total cross section of the fusion , the barrier distribution of the fusion and the average angular momentum ⟨L⟩ for the systems 6He+206Pb, 8B+28Si, 11Be+209Bi, 17F+208Pb, 6He+238U, 8He+197Au and 15C+232Th using quantum mechanical approach. A quantum Coupled-Channel Calculations are performed using CC code. The predictions of quantum mechanical approach are comparable with the measured data that is

The challenge in studying fusion reaction when the projectile is neutron or proton rich halo nuclei is the coupling mechanism between the elastic and the breakup channel, therefore the motivation from the present calculations is to estimate the best coupling parameter to introduce the effect of coupled-channels for the calculations of the total cross section of the fusion  , the barrier distribution of the fusion   and the average angular momentum ⟨L⟩ for the systems ⁶He+²⁰⁶Pb, ⁸B+²⁸Si, ¹¹Be+²⁰⁹Bi, ¹⁷F+²⁰⁸Pb, ⁶He+²³⁸U, ⁸He+¹⁹⁷Au and ¹⁵C+²³²Th using quantum mechanical approach.  A

Classifying an overlapping object is one of the main challenges faced by researchers who work in object detection and recognition. Most of the available algorithms that have been developed are only able to classify or recognize objects which are either individually separated from each other or a single object in a scene(s), but not overlapping kitchen utensil objects. In this project, Faster R-CNN and YOLOv5 algorithms were proposed to detect and classify an overlapping object in a kitchen area.  The YOLOv5 and Faster R-CNN were applied to overlapping objects where the filter or kernel that are expected to be able to separate the overlapping object in the dedicated layer of applying models. A kitchen utensil benchmark image database and

With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se