Biometrics represent the most practical method for swiftly and reliably verifying and identifying individuals based on their unique biological traits. This study addresses the increasing demand for dependable biometric identification systems by introducing an efficient approach to automatically recognize ear patterns using Convolutional Neural Networks (CNNs). Despite the widespread adoption of facial recognition technologies, the distinct features and consistency inherent in ear patterns provide a compelling alternative for biometric applications. Employing CNNs in our research automates the identification process, enhancing accuracy and adaptability across various ear shapes and orientations. The ear, being visible and easily captured in an image, possesses the unique characteristic that no two individuals share the same ear patterns. Consequently, our research proposes a system for individual identification based on ear traits, comprising three main stages: (1) pre-processing to extract the ear pattern (region of interest) from input images, (2) feature extraction, and (3) classification. Convolutional Neural Network (CNN) is employed for the feature extraction and classification tasks. The system remains invariant to scaling, brightness, and rotation. Experimental results demonstrate that the proposed system achieved an accuracy of 99.86% for all datasets.
In the present study, a novel ligand (L) made of 2-hydroxynaphthaldehyde and 3-hydrazone-1,3-dihydro-indole-2-one(3-[(3-hydroxynaphthalen-2-yl-ethylidene)-hydrazono]-1,3-dihydro-indol-2-one). The ligand was characterized by FTIR, UV-vis, mass, 1H-NMR, 13C-NMR, and CHN elemental analysis. New complexes of this ligand were created by treating methanol and a drop of DMF solution of the produced ligand with the hydrated metal salts of Mn(II), Co(II), Ni(II), Cu(II), and Zn(II) in a molar ratio of 2:1 (L:M). As a result, complexes have been emerged and identified FTIR, UV-vis, C.H.N., chloride-containing, molar conductance, magnetic susceptibility, and atomic absorption. The characterization result for each complex indicated complexes wi
... Show MoreThis paper deals with the design and implementation of an ECG system. The proposed system gives a new concept of ECG signal manipulation, storing, and editing. It consists mainly of hardware circuits and the related software. The hardware includes the circuits of ECG signals capturing, and system interfaces. The software is written using Visual Basic languages, to perform the task of identification of the ECG signal. The main advantage of the system is to provide a reported ECG recording on a personal computer, so that it can be stored and processed at any time as required. This system was tested for different ECG signals, some of them are abnormal and the other is normal, and the results show that the system has a good quality of diagno
... Show MoreThe predilection for 5G telemedicine networks has piqued the interest of industry researchers and academics. The most significant barrier to global telemedicine adoption is to achieve a secure and efficient transport of patients, which has two critical responsibilities. The first is to get the patient to the nearest hospital as quickly as possible, and the second is to keep the connection secure while traveling to the hospital. As a result, a new network scheme has been suggested to expand the medical delivery system, which is an agile network scheme to securely redirect ambulance motorbikes to the nearest hospital in emergency cases. This research provides a secured and efficient telemedicine transport strategy compatible with the
... Show MoreActivity recognition (AR) is a new interesting and challenging research area with many applications (e.g. healthcare, security, and event detection). Basically, activity recognition (e.g. identifying user’s physical activity) is more likely to be considered as a classification problem. In this paper, a combination of 7 classification methods is employed and experimented on accelerometer data collected via smartphones, and compared for best performance. The dataset is collected from 59 individuals who performed 6 different activities (i.e. walk, jog, sit, stand, upstairs, and downstairs). The total number of dataset instances is 5418 with 46 labeled features. The results show that the proposed method of ensemble boost-based classif
... Show MoreGender classification is a critical task in computer vision. This task holds substantial importance in various domains, including surveillance, marketing, and human-computer interaction. In this work, the face gender classification model proposed consists of three main phases: the first phase involves applying the Viola-Jones algorithm to detect facial images, which includes four steps: 1) Haar-like features, 2) Integral Image, 3) Adaboost Learning, and 4) Cascade Classifier. In the second phase, four pre-processing operations are employed, namely cropping, resizing, converting the image from(RGB) Color Space to (LAB) color space, and enhancing the images using (HE, CLAHE). The final phase involves utilizing Transfer lea
... Show MoreContent-based image retrieval has been keenly developed in numerous fields. This provides more active management and retrieval of images than the keyword-based method. So the content based image retrieval becomes one of the liveliest researches in the past few years. In a given set of objects, the retrieval of information suggests solutions to search for those in response to a particular description. The set of objects which can be considered are documents, images, videos, or sounds. This paper proposes a method to retrieve a multi-view face from a large face database according to color and texture attributes. Some of the features used for retrieval are color attributes such as the mean, the variance, and the color image's bitmap. In add
... Show More