ABSTRACT
Currently, it is ever more common to access online services for activities which formerly required physical attendance. From banking operations to visa applications, a significant number of processes have been digitised, especially since the advent of the COVID-19 pandemic, requiring remote biometric authentication of the user. On the downside, some subjects intend to interfere with the normal operation of remote systems for personal profit by using fake identity documents, such as passports and ID cards. Deep learning solutions to detect such frauds have been presented in the literature. However, due to privacy concerns and the sensitive nature of personal identity documents, developing a dataset with the necessary number of examples for training deep neural networks is challenging. This work explores three methods for synthetically generating ID card images to increase the amount of data while training fraud-detection networks. These methods include computer vision algorithms and Generative Adversarial Networks. Our results indicate that databases can be supplemented with synthetic images without any loss in performance for the print/scan Presentation Attack Instrument Species (PAIS) and a loss in performance of 1% for the screen capture PAIS. Author
ABSTRACT
In this paper, we provide an overview of the upcoming ImageCLEF campaign. ImageCLEF is part of the CLEF Conference and Labs of the Evaluation Forum since 2003. ImageCLEF, the Multimedia Retrieval task in CLEF, is an ongoing evaluation initiative that promotes the evaluation of technologies for annotation, indexing, and retrieval of multimodal data with the aim of providing information access to large collections of data in various usage scenarios and domains. In its 21st edition, ImageCLEF 2023 will have four main tasks: (i) a Medical task addressing automatic image captioning, synthetic medical images created with GANs, Visual Question Answering for colonoscopy images, and medical dialogue summarization;(ii) an Aware task addressing the prediction of real-life consequences of online photo sharing;(iii) a Fusion task addressing late fusion techniques based on the expertise of a pool of classifiers;and (iv) a Recommending task addressing cultural heritage content-recommendation. In 2022, ImageCLEF received the participation of over 25 groups submitting more than 258 runs. These numbers show the impact of the campaign. With the COVID-19 pandemic now over, we expect that the interest in participating, especially at the physical CLEF sessions, will increase significantly in 2023. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Simulating human mobility contributes to city behavior discovery and decision-making. Although the sequence-based and image-based approaches have made impressive achievements, they still suffer from respective deficiencies such as omitting the depiction of spatial properties or ordinal dependency in trajectory. In this article, we take advantage of the above two paradigms and propose a semantic-guiding adversarial network (TrajSGAN) for generating human trajectories. Specifically, we first devise an attention-based generator to yield trajectory locations in a sequence-to-sequence manner. The encoded historical visits are queried with semantic knowledge (e.g., travel modes and trip purposes) and their important features are enhanced by the multihead attention mechanism. Then, we designate a rollout module to complete the unfinished trajectory sequence and transform it into an image that can depict its spatial structure. Finally, a convolutional neural network (CNN)-based discriminator signifies how “real”the trajectory image looks, and its output is regarded as a reward signal to update the generator by the policy gradient. Experimental results show that the proposed TrajSGAN model significantly outperforms the benchmarks under the MTL-Trajet mobility dataset, with the divergence of spatial-related metrics such as radius of gyration and travel distance reduced by 10%–27%. Furthermore, we apply the real and synthetic trajectories, respectively, to simulate the COVID-19 epidemic spreading under three preventive actions. The coefficient of determination metric between real and synthetic results achieves 91%–98%, indicating that the synthesized data from TrajSGAN can be leveraged to study the epidemic diffusion with an acceptable difference. All of these results verify the superiority and utility of our proposed method. IEEE
ABSTRACT
Detection of the novel Corona virus in the early stages is crucial, since no known vaccines exist. Artificial Intelligence- aided prognosis using CT scans can be used as an effective method to identify symptoms of the virus and can thus significantly reduce the workload on the radiologists, who have to perform this task using their eyes. Among the most widely used deep learning convolutional neural networks, research shows that the Xception, Inception and the ResNet50 provide the best accuracy in detecting Covid-19. This paper proposes that using General Adversarial Network (GAN) as a data augmentation technique, in combination with these models will significantly improve the accuracy and thereby increase the chances of detecting the same. The paper also compares and contrasts how each of the three GANs namely DCGAN, LSGAN, CoGAN, perform in association with the aforementioned models. The main aim of this paper is to determine the most credible GAN network to carry out the task of data augmentation as well to prove that involving GANs would improve the existing accuracy of our model, paving way for an effective approach to train the model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
Covid-19 has disrupted lives throughout the world. It has spread all over the world and detection of the virus is an imperative step in beating the virus. Methods such as the RTPCR and Rapid antigen tests are not only time consuming but also complex and expensive. Since the virus attacks the lungs, the Xray images of the chest can be used for the detection of coronavirus. This paper summarizes as well as gives a detailed study of the research and various techniques used for this subject. Methods used for COVID-19 detection using medical imaging using Chest X-Ray (CXR) and CT scan images as well as role and usage of GANs in tackling this problem have been summarized. © 2022 IEEE.
ABSTRACT
With the increase in the cases of COVID-19, the necessity of improving testing and treatment is increasing rapidly. Many techniques are currently being used by the medical fraternity for detection of COVID-19 in a patient such as RT-PCR, Chest CT Scan Images, Chest X-Ray scans, etc. Among these techniques, a Chest CT scan has proven to be highly accurate for screening of the novel coronavirus. But a trained professional like a radiologist is needed to analyze the CT scan and determine whether the patient is positive or not. Due to the sudden spike in the number of infections, there is a shortage of such professionals. A machine learning based system can be highly effective in assisting the doctors if it can accurately predict COVID-19 from a chest CT scan. However, the number of chest CT scan images available are very less in order to build an accurate machine learning based predictive model. We present a generative model for data augmentation of COVID-19 positive and negative Chest CT images. We use Conditional DCGAN for generating nearly 1502 COVID-19 positive and 1510 negative images thus extending a publicly available dataset. We also build predictive models using pre-trained models like VGG and ResNet to detect COVID-19, achieving an accuracy upto 87.7%. We also apply the technique of knowledge distillation to build a lightweight and computationally cheap predictive model that has an accuracy of 86.2% and is nearly 11 times smaller than the best model available on the dataset. © 2022 IEEE.
ABSTRACT
The novel Coronavirus Disease 2019 (nCOVID-19) pandemic is a global health challenge, that requires collaborative efforts from multiple research communities. Effective screening of infected patients is a significant step in the fight against COVID-19, as radiological examination being an important screening methods. Early findings reveal that anomalies in chest X-rays of COVID-19 patients exist. As a result, a number of deep learning methods have been developed, and studies have shown that the accuracy of COVID-19 patient recognition using chest X-rays is very high. In this paper, we propose an attention based deep neural network for classifying the COVID-19 images, and extracting useful clinical information. Generative adversarial network is used to generate the synthetic COVID-19 images, as well as a good latent representation of both COVID-19 and normal images. Experiment results on public datasets shows the effectiveness of the proposed approach. © 2021 IEEE.
ABSTRACT
COVID-19 has emerged as a global crisis with unprecedented socio-economic challenges, jeopardizing our lives and livelihoods for years to come. The unavailability of vaccines for COVID-19 has rendered rapid testing of the population instrumental in order to contain the exponential rise in cases of infection. Shortage of RT-PCR test kits and delays in obtaining test results calls for alternative methods of rapid and reliable diagnosis. In this article, we propose a novel deep learning-based solution using chest X-rays which can help in rapid triaging of COVID-19 patients. The proposed solution uses image enhancement, image segmentation, and employs a modified stacked ensemble model consisting of four CNN base-learners along with Naive Bayes as meta-learner to classify chest X-rays into three classes viz. COVID-19, pneumonia, and normal. An effective pruning strategy as introduced in the proposed framework results in increased model performance, generalizability, and decreased model complexity. We incorporate explainability in our article by using Grad-CAM visualization in order to establish trust in the medical AI system. Furthermore, we evaluate multiple state-of-the-art GAN architectures and their ability to generate realistic synthetic samples of COVID-19 chest X-rays to deal with limited numbers of training samples. The proposed solution significantly outperforms existing methods, with 98.67% accuracy, 0.98 Kappa score, and F-1 scores of 100, 98, and 98 for COVID-19, normal, and pneumonia classes, respectively, on standard datasets. The proposed solution can be used as one element of patient evaluation along with gold-standard clinical and laboratory testing.