Evaluation of similarity measures for video retrieval

Bekhet, Saddam; Ahmed, Amr

doi:10.1007/s11042-019-08539-4

Cited by 18 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The graph depicts a performance stability after the first 500 epochs, with 96% accuracy. for this part [22]. The accuracy metric is defined in Equation 3, as follows:…”

Section: Resultsmentioning

confidence: 99%

An Artificial Intelligence Based Technique for COVID-19 Diagnosis from Chest X-Ray

Bekhet

Hassaballah

Kenk

et al. 2020

2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)

Self Cite

View full text Add to dashboard Cite

The COVID-19 pandemic had a catastrophic impact on world health and economic. This is attributed to the unavoidable delay in the diagnosis process, due to limitation of COVID-19 test kits. Thus, it is urgently required to establish more cheap and affordable diagnostic approaches. Chest X-ray is an important initial step towards a successful COVID-19 diagnose, where it is easily to detect any chest abnormalities (e.g., lung inflammation). Furthermore, majority of hospitals have X-ray devices that can be used in early COVID-19 diagnosis. However, the shortage of radiologists is a key factor that limits early COVID-19 diagnosis and negatively affects the treatment process. This paper presents an artificial intelligence based technique for early COVID-19 diagnosis from chest X-ray images using medical knowledge and deep Convolutional Neural Networks (CNNs). To this end, a deep learning model is built carefully and fine-tuned to achieve the maximum performance in COVID-19 detection. Experimental results on recent benchmark datasets demonstrate the superior performance of the proposed technique in identifying COVID-19 with 96% accuracy.

show abstract

“…The graph depicts a performance stability after the first 500 epochs, with 96% accuracy. for this part [22]. The accuracy metric is defined in Equation 3, as follows:…”

Section: Resultsmentioning

confidence: 99%

An Artificial Intelligence Based Technique for COVID-19 Diagnosis from Chest X-Ray

Bekhet

Hassaballah

Kenk

et al. 2020

2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The features obtained from hand-crafted and deep feature extractors are compared through the city-block or Manhattan distance [ 7 ]. This distance function is also known as 1-norm distance between two feature vectors.…”

Section: Methodsmentioning

confidence: 99%

Enhanced near-infrared periocular recognition through collaborative rendering of hand crafted and deep features

Vyas

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Periocular recognition leverage from larger feature region and lesser user cooperation, when compared against the traditional iris recognition. Moreover, in the current scenario of Covid-19, where majority of people cover their faces with masks, potential of recognizing faces gets reduced by a large extent, calling for wide applicability of periocular recognition. In view of these facts, this paper targets towards enhanced representation of near-infrared periocular images, by combined use of hand-crafted and deep features. The hand-crafted features are extracted through partitioning of periocular image followed by obtaining the local statistical properties pertaining to each partition. Whereas, deep features are extracted through the popular convolutional neural network (CNN) ResNet-101 model. The extensive set of experiments performed with a benchmark periocular database validates the promising performance of the proposed method. Additionally, investigation of cross-spectral matching framework and comparison with state-of-the-art, reveal that combination of both types of features employed could prove to be extremely effective.

show abstract

“…[315] for automatic alarm-triggering detection of events (e.g. patient health degradations) from collected data by biomedical sensors, Fu et al [128] for the study of income distributions in China, Ha et al [151] for x−ray spectrum reconstruction in computer tomography (CT) systems (with γ = 1), Iqbal & Seghouane [161] for robust sequential dictionary learning, Luppino et al [233] for unsupervised change detection in heterogeneous multitemporal satellite images (with γ = 1 2 ), Sason [320] in connection with data-processing and majorization inequalities, Krömer & Stummer [198] for the smoothing and error-correcting of crude mortality rates (where they even employ non-probability-type vectors), Bekhet & Ahmed [37] for effectiveness evaluations in video retrieval (with γ = −1, γ = 1 2 ), Cai et al [71] for the stabilization of trainings of generative adversarial networks (GANs), Fu et al [129] for automatic molecule optimization, Görtler et al [139] for dimensionality reduction on uncertain data in visualization and computer graphics (with γ = 1 2 ), Kammerer & Stummer [179] for optimal decision making in the presence of pandemics (e.g. COVID-19), Kanapram et al [180] for the development of collective self-awareness in a network of connected and autonomous vehicles through agent-centered detection of abnormal situations (with γ = 1…”

Section: ) Construction Principle For the Estimation Of The Minimum D...mentioning

confidence: 99%

A precise bare simulation approach to the minimization of some distances. Foundations

Broniatowski¹,

Stummer²

2021

Preprint

View full text Add to dashboard Cite

In information theory -as well as in the adjacent fields of statistics, machine learning, artificial intelligence, signal processing and pattern recognition -many flexibilizations of the omnipresent Kullback-Leibler information distance (relative entropy) and of the closely related Shannon entropy have become frequently used tools. To tackle corresponding constrained minimization (respectively maximization) problems by a newly developed dimension-free bare (pure) simulation method, is the main goal of this paper. Almost no assumptions (like convexity) on the set of constraints are needed, within our discrete setup of arbitrary dimension, and our method is precise (i.e., converges in the limit). As a side effect, we also derive an innovative way of constructing new useful distances/divergences. To illustrate the core of our approach, we present numerous examples. The potential for widespread applicability is indicated, too; in particular, we deliver many recent references for uses of the involved distances/divergences and entropies in various different research fields (which may also serve as an interdisciplinary interface).

show abstract

Evaluation of similarity measures for video retrieval

Cited by 18 publications

References 21 publications

An Artificial Intelligence Based Technique for COVID-19 Diagnosis from Chest X-Ray

An Artificial Intelligence Based Technique for COVID-19 Diagnosis from Chest X-Ray

Enhanced near-infrared periocular recognition through collaborative rendering of hand crafted and deep features

A precise bare simulation approach to the minimization of some distances. Foundations

Contact Info

Product

Resources

About