A Review of Image Processing Techniques for Deepfakes

Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica
Universidad Internacional Iberoamericana México > Investigación > Artículos y libros
Universidad Internacional do Cuanza > Investigación > Producción Científica
Abierto Inglés Deep learning is used to address a wide range of challenging issues including large data analysis, image processing, object detection, and autonomous control. In the same way, deep learning techniques are also used to develop software and techniques that pose a danger to privacy, democracy, and national security. Fake content in the form of images and videos using digital manipulation with artificial intelligence (AI) approaches has become widespread during the past few years. Deepfakes, in the form of audio, images, and videos, have become a major concern during the past few years. Complemented by artificial intelligence, deepfakes swap the face of one person with the other and generate hyper-realistic videos. Accompanying the speed of social media, deepfakes can immediately reach millions of people and can be very dangerous to make fake news, hoaxes, and fraud. Besides the well-known movie stars, politicians have been victims of deepfakes in the past, especially US presidents Barak Obama and Donald Trump, however, the public at large can be the target of deepfakes. To overcome the challenge of deepfake identification and mitigate its impact, large efforts have been carried out to devise novel methods to detect face manipulation. This study also discusses how to counter the threats from deepfake technology and alleviate its impact. The outcomes recommend that despite a serious threat to society, business, and political institutions, they can be combated through appropriate policies, regulation, individual actions, training, and education. In addition, the evolution of technology is desired for deepfake identification, content authentication, and deepfake prevention. Different studies have performed deepfake detection using machine learning and deep learning techniques such as support vector machine, random forest, multilayer perceptron, k-nearest neighbors, convolutional neural networks with and without long short-term memory, and other similar models. This study aims to highlight the recent research in deepfake images and video detection, such as deepfake creation, various detection algorithms on self-made datasets, and existing benchmark datasets. metadata Shahzad, Hina Fatima; Rustam, Furqan; Soriano Flores, Emmanuel; Vidal Mazón, Juan Luis; de la Torre Diez, Isabel y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, emmanuel.soriano@uneatlantico.es, juanluis.vidal@uneatlantico.es, SIN ESPECIFICAR, SIN ESPECIFICAR (2022) A Review of Image Processing Techniques for Deepfakes. Sensors, 22 (12). p. 4556. ISSN 1424-8220

[img] Texto
sensors-22-04556-v2.pdf
Available under License Creative Commons Attribution.

Descargar (2MB)

Resumen

Deep learning is used to address a wide range of challenging issues including large data analysis, image processing, object detection, and autonomous control. In the same way, deep learning techniques are also used to develop software and techniques that pose a danger to privacy, democracy, and national security. Fake content in the form of images and videos using digital manipulation with artificial intelligence (AI) approaches has become widespread during the past few years. Deepfakes, in the form of audio, images, and videos, have become a major concern during the past few years. Complemented by artificial intelligence, deepfakes swap the face of one person with the other and generate hyper-realistic videos. Accompanying the speed of social media, deepfakes can immediately reach millions of people and can be very dangerous to make fake news, hoaxes, and fraud. Besides the well-known movie stars, politicians have been victims of deepfakes in the past, especially US presidents Barak Obama and Donald Trump, however, the public at large can be the target of deepfakes. To overcome the challenge of deepfake identification and mitigate its impact, large efforts have been carried out to devise novel methods to detect face manipulation. This study also discusses how to counter the threats from deepfake technology and alleviate its impact. The outcomes recommend that despite a serious threat to society, business, and political institutions, they can be combated through appropriate policies, regulation, individual actions, training, and education. In addition, the evolution of technology is desired for deepfake identification, content authentication, and deepfake prevention. Different studies have performed deepfake detection using machine learning and deep learning techniques such as support vector machine, random forest, multilayer perceptron, k-nearest neighbors, convolutional neural networks with and without long short-term memory, and other similar models. This study aims to highlight the recent research in deepfake images and video detection, such as deepfake creation, various detection algorithms on self-made datasets, and existing benchmark datasets.

Tipo de Documento: Artículo
Palabras Clave: image processing; deep learning; video altering; deepfake
Clasificación temática: Materias > Ingeniería
Divisiones: Universidad Europea del Atlántico > Investigación > Producción Científica
Universidad Internacional Iberoamericana México > Investigación > Artículos y libros
Universidad Internacional do Cuanza > Investigación > Producción Científica
Depositado: 27 Jun 2022 23:30
Ultima Modificación: 11 Jul 2023 23:30
URI: https://repositorio.unini.edu.mx/id/eprint/2531

Acciones (logins necesarios)

Ver Objeto Ver Objeto

<a class="ep_document_link" href="/10290/1/Influence%20of%20E-learning%20training%20on%20the%20acquisition%20of%20competences%20in%20basketball%20coaches%20in%20Cantabria.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Influence of E-learning training on the acquisition of competences in basketball coaches in Cantabria

The main aim of this study was to analyse the influence of e-learning training on the acquisition of competences in basketball coaches in Cantabria. The current landscape of basketball coach training shows an increasing demand for innovative training models and emerging pedagogies, including e-learning-based methodologies. The study sample consisted of fifty students from these courses, all above 16 years of age (36 males, 14 females). Among them, 16% resided outside the autonomous community of Cantabria, 10% resided more than 50 km from the city of Santander, 36% between 10 and 50 km, 14% less than 10 km, and 24% resided within Santander city. Data were collected through a Google Forms survey distributed by the Cantabrian Basketball Federation to training course students. Participation was voluntary and anonymous. The survey, consisting of 56 questions, was validated by two sports and health doctors and two senior basketball coaches. The collected data were processed and analysed using Microsoft® Excel version 16.74, and the results were expressed in percentages. The analysis revealed that 24.60% of the students trained through the e-learning methodology considered themselves fully qualified as basketball coaches, contrasting with 10.98% of those trained via traditional face-to-face methodology. The results of the study provide insights into important characteristics that can be adjusted and improved within the investigated educational process. Moreover, the study concludes that e-learning training effectively qualifies basketball coaches in Cantabria.

Producción Científica

Josep Alemany Iturriaga mail josep.alemany@uneatlantico.es, Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es, Javier Jorge mail , Kamil Giglio mail ,

Alemany Iturriaga

<a href="/14206/1/mnm_2024_17-3_mnm-17-3-mnm240038_mnm-17-mnm240038.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Exploring body composition and somatotype profiles among youth professional soccer players

OBJECTIVE: This study aimed to analyze the body composition and somatotype of professional soccer players, investigating variations across categories and playing positions. METHODS: An observational, cross-sectional, and analytical study was conducted with 51 male professional soccer players in the U-19 and U-20 categories. Data about sex, age, height, and weight were collected between March and May 2023. Body composition analysis utilized the ISAK protocol for the restricted profile, while somatotype categorization employed the Heath and Carter formula. Statistical analysis was performed using IBM SPSS Statistics V.26, which involved the application of Mann-Whitney and Kruskal-Wallis tests to discern differences in body composition variables and proportionality based on categories and playing positions. The Dunn test further identified specific positions exhibiting significant differences. RESULTS: The study encompassed 51 players, highlighting meaningful differences in body composition. The average body mass in kg was 75.8 (±6.9) for U-20 players and 70.5 (±6.1) for U-19 players. The somatotype values were 2.6-4.6-2.3 for U-20 players and 2.5-4.3-2.8 for U-19 players, with a predominance of muscle mass in all categories, characterizing them as balanced mesomorphs. CONCLUSIONS: Body composition and somatotype findings underscore distinctions in body mass across categories and playing positions, with notably higher body mass and muscle mass predominance in elevated categories. However, the prevailing skeletal muscle development establishes a significant semblance with the recognized somatotype standard for soccer.

Producción Científica

Raynier Zambrano-Villacres mail , Evelyn Frias-Toral mail , Emily Maldonado-Ponce mail , Carlos Poveda-Loor mail , Paola Leal mail , Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es, Alice Leonardi mail , Bruno Trovato mail , Federico Roggio mail , Alessandro Castorina mail , Xu Wenxin mail , Giuseppe Musumeci mail ,

Zambrano-Villacres

<a class="ep_document_link" href="/14280/1/journal.pone.0305708.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Deep transfer learning-based bird species classification using mel spectrogram images

The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342.

Producción Científica

Asadullah Shaikh mail , Mrinal Kanti Baowaly mail , Bisnu Chandra Sarkar mail , Md. Abul Ala Walid mail , Md. Martuza Ahamad mail , Bikash Chandra Singh mail , Eduardo René Silva Alvarado mail eduardo.silva@funiber.org, Imran Ashraf mail , Md. Abdus Samad mail ,

Shaikh

<a href="/14281/1/s41598-024-69663-2.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

An enhanced approach for predicting air pollution using quantum support vector machine

The essence of quantum machine learning is to optimize problem-solving by executing machine learning algorithms on quantum computers and exploiting potent laws such as superposition and entanglement. Support vector machine (SVM) is widely recognized as one of the most effective classification machine learning techniques currently available. Since, in conventional systems, the SVM kernel technique tends to sluggish down and even fail as datasets become increasingly complex or jumbled. To compare the execution time and accuracy of conventional SVM classification to that of quantum SVM classification, the appropriate quantum features for mapping need to be selected. As the dataset grows complex, the importance of selecting an appropriate feature map that outperforms or performs as well as the classification grows. This paper utilizes conventional SVM to select an optimal feature map and benchmark dataset for predicting air quality. Experimental evidence demonstrates that the precision of quantum SVM surpasses that of classical SVM for air quality assessment. Using quantum labs from IBM’s quantum computer cloud, conventional and quantum computing have been compared. When applied to the same dataset, the conventional SVM achieved an accuracy of 91% and 87% respectively, whereas the quantum SVM demonstrated an accuracy of 97% and 94% respectively for air quality prediction. The study introduces the use of quantum Support Vector Machines (SVM) for predicting air quality. It emphasizes the novel method of choosing the best quantum feature maps. Through the utilization of quantum-enhanced feature mapping, our objective is to exceed the constraints of classical SVM and achieve unparalleled levels of precision and effectiveness. We conduct precise experiments utilizing IBM’s state-of-the-art quantum computer cloud to compare the performance of conventional and quantum SVM algorithms on a shared dataset.

Producción Científica

Omer Farooq mail , Maida Shahid mail , Shazia Arshad mail , Ayesha Altaf mail , Faiza Iqbal mail , Yini Airet Miro Vera mail , Miguel Angel Lopez Flores mail , Imran Ashraf mail ,

Farooq

<a href="/14282/1/s40537-024-00959-w.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

DiabSense: early diagnosis of non-insulin-dependent diabetes mellitus using smartphone-based human activity recognition and diabetic retinopathy analysis with Graph Neural Network

Non-Insulin-Dependent Diabetes Mellitus (NIDDM) is a chronic health condition caused by high blood sugar levels, and if not treated early, it can lead to serious complications i.e. blindness. Human Activity Recognition (HAR) offers potential for early NIDDM diagnosis, emerging as a key application for HAR technology. This research introduces DiabSense, a state-of-the-art smartphone-dependent system for early staging of NIDDM. DiabSense incorporates HAR and Diabetic Retinopathy (DR) upon leveraging the power of two different Graph Neural Networks (GNN). HAR uses a comprehensive array of 23 human activities resembling Diabetes symptoms, and DR is a prevalent complication of NIDDM. Graph Attention Network (GAT) in HAR achieved 98.32% accuracy on sensor data, while Graph Convolutional Network (GCN) in the Aptos 2019 dataset scored 84.48%, surpassing other state-of-the-art models. The trained GCN analyzed retinal images of four experimental human subjects for DR report generation, and GAT generated their average duration of daily activities over 30 days. The daily activities in non-diabetic periods of diabetic patients were measured and compared with the daily activities of the experimental subjects, which helped generate risk factors. Fusing risk factors with DR conditions enabled early diagnosis recommendations for the experimental subjects despite the absence of any apparent symptoms. The comparison of DiabSense system outcome with clinical diagnosis reports in the experimental subjects was conducted using the A1C test. The test results confirmed the accurate assessment of early diagnosis requirements for experimental subjects by the system. Overall, DiabSense exhibits significant potential for ensuring early NIDDM treatment, improving millions of lives worldwide.

Producción Científica

Md Nuho Ul Alam mail , Ibrahim Hasnine mail , Erfanul Hoque Bahadur mail , Abdul Kadar Muhammad Masum mail , Mercedes Briones Urbano mail mercedes.briones@uneatlantico.es, Manuel Masías Vergara mail manuel.masias@uneatlantico.es, Jia Uddin mail , Imran Ashraf mail , Md. Abdus Samad mail ,

Alam