Facial expression recognition has been an active area of research over the past few decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem ...rely on hand-crafted features such as SIFT, HOG, and LBP, followed by a classifier trained on a database of images or videos. Most of these works perform reasonably well on datasets of images captured in a controlled condition but fail to perform as well on more challenging datasets with more image variation and partial faces. In recent years, several works proposed an end-to-end framework for facial expression recognition using deep learning models. Despite the better performance of these works, there are still much room for improvement. In this work, we propose a deep learning approach based on attentional convolutional network that is able to focus on important parts of the face and achieves significant improvement over previous models on multiple datasets, including FER-2013, CK+, FERG, and JAFFE. We also use a visualization technique that is able to find important facial regions to detect different emotions based on the classifier's output. Through experimental results, we show that different emotions are sensitive to different parts of the face.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Vehicle detection and tracking play an important role in autonomous vehicles and intelligent transportation systems. Adverse weather conditions such as the presence of heavy snow, fog, rain, dust or ...sandstorm situations are dangerous restrictions on camera's function by reducing visibility, affecting driving safety. Indeed, these restrictions impact the performance of detection and tracking algorithms utilized in the traffic surveillance systems and autonomous driving applications. In this article, we start by proposing a visibility enhancement scheme consisting of three stages: illumination enhancement, reflection component enhancement, and linear weighted fusion to improve the performance. Then, we introduce a robust vehicle detection and tracking approach using a multi-scale deep convolution neural network. The conventional Gaussian mixture probability hypothesis density filter based tracker is utilized jointly with hierarchical data associations (HDA), which splits into detection-to-track and track-to-track associations. Herein, the cost matrix of each phase is solved using the Hungarian algorithm to compensate for the lost tracks caused by missed detection. Only detection information (i.e., bounding boxes with detection scores) is used in HDA without visual features information for rapid execution. We have also introduced a novel benchmarking dataset designed for research in applications of autonomous vehicles under adverse weather conditions called DAWN. It consists of real-world images collected with different types of adverse weather conditions. The proposed method is tested on DAWN, KITTI, and MS-COCO datasets and compared with 21 vehicle detectors. Experimental results have validated effectiveness of the proposed method which outperforms state-of-the-art vehicle detection and tracking approaches under adverse weather conditions.
•A segmentation framework to detect infected chest regions in CT images.•A regularization term based on 2D-anisotropic total-variation is added to the loss function.•A relatively largescale CT ...segmentation dataset of around 900 images.•Identifying infected regions with mIoU rate of 99%, and a Dice score of 86%.
The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. By October 2020, more than 44 million people were infected, and more than 1,000,000 deaths were reported. Computed Tomography (CT) images can be used as an alternative to the time-consuming RT-PCR test, to detect COVID-19. In this work we propose a segmentation framework to detect chest regions in CT images, which are infected by COVID-19. An architecture similar to a Unet model was employed to detect ground glass regions on a voxel level. As the infected regions tend to form connected components (rather than randomly distributed voxels), a suitable regularization term based on 2D-anisotropic total-variation was developed and added to the loss function. The proposed model is therefore called ”TV-Unet”. Experimental results obtained on a relatively large-scale CT segmentation dataset of around 900 images, incorporating this new regularization term leads to a 2% gain on overall segmentation performance compared to the Unet trained from scratch. Our experimental analysis, ranging from visual evaluation of the predicted segmentation results to quantitative assessment of segmentation performance (precision, recall, Dice score, and mIoU) demonstrated great ability to identify COVID-19 associated regions of the lungs, achieving a mIoU rate of over 99%, and a Dice score of around 86%.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
We propose an algorithm for separating the foreground (mainly text and line graphics) from the smoothly varying background in screen content images. The proposed method is designed based on the ...assumption that the background part of the image is smoothly varying and can be represented by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity and cannot be modeled by this smooth representation. The algorithm separates the background and foreground using a least absolute deviation method to fit the smooth model to the image pixels. This algorithm has been tested on several images from HEVC standard test sequences for screen content coding, and is shown to have superior performance over other popular methods, such as k-means clustering based segmentation in DjVu and shape primitive extraction and coding (SPEC) algorithm. Such background/foreground segmentation are important pre-processing steps for text extraction and separate coding of background and foreground for compression of screen content images.
COVID-19 has led to a pandemic, affecting almost all countries in a few months. In this work, we applied selected deep learning models including multilayer perceptron, random forest, and different ...versions of long short-term memory (LSTM), using three data sources to train the models, including COVID-19 occurrences, basic information like coded country names, and detailed information like population, and area of different countries. The main goal is to forecast the outbreak in nine countries (Iran, Germany, Italy, Japan, Korea, Switzerland, Spain, China, and the USA). The performances of the models are measured using four metrics, including mean average percentage error (MAPE), root mean square error (RMSE), normalized RMSE (NRMSE), and R2. The best performance was found for a modified version of LSTM, called M-LSTM (winner model), to forecast the future trajectory of the pandemic in the mentioned countries. For this purpose, we collected the data from January 22 till July 30, 2020, for training, and from 1 August 2020 to 31 August 2020, for the testing phase. Through experimental results, the winner model achieved reasonably accurate predictions (MAPE, RMSE, NRMSE, and R2 are 0.509, 458.12, 0.001624, and 0.99997, respectively). Furthermore, we stopped the training of the model on some dates related to main country actions to investigate the effect of country actions on predictions by the model.
Full text
Available for:
DOBA, FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, SIK, UILJ, UKNU, UL, UM, UPUK
Moving object detection in a given video sequence is a pivotal step in many computer vision applications such as video surveillance. Robust Principal Component Analysis (RPCA) performs low-rank and ...sparse decomposition to accomplish such a task when the background is stationary and the foreground is dynamic and relatively small. A fundamental issue with the RPCA is the assumption that the low-rank and sparse components are added at each pixel, whereas in reality, the moving foreground is overlaid on the background. We propose the masked decomposition (i.e. an overlaying model) where each element either belongs to the low-rank or the sparse component, decided by a mask. We introduce the Masked-RPCA (MRPCA) algorithm to recover the mask (hence the sparse object) and the low-rank components simultaneously, via a non-convex formulation. An adapted version of the Douglas-Rachford splitting algorithm is utilized to solve the proposed formulation. Our experiments using real-world video sequences show consistently better performance for both cases of static and dynamic background videos compared to RPCA and its variants based on the additive model. Additionally, we show that utilizing non-convex priors in our formulation leads to improved results without any added complexity compared to a relaxed formulation using convex surrogates and methods based on the additive model.
Deep Learning--based Text Classification Minaee, Shervin; Kalchbrenner, Nal; Cambria, Erik ...
ACM computing surveys,
04/2022, Volume:
54, Issue:
3
Journal Article
Peer reviewed
Deep learning--based models have surpassed classical machine learning--based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, ...and natural language inference. In this article, we provide a comprehensive review of more than 150 deep learning--based models for text classification developed in recent years, and we discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification. Finally, we provide a quantitative analysis of the performance of different deep learning models on popular benchmarks, and we discuss future research directions.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, SAZU, UL, UM, UPUK
Signal decomposition is a classical problem in signal processing, which aims to separate an observed signal into two or more components, each with its own property. Usually, each component is ...described by its own subspace or dictionary. Extensive research has been done for the case where the components are additive, but in real-world applications, the components are often non-additive. For example, an image may consist of a foreground object overlaid on a background, where each pixel either belongs to the foreground or the background. In such a situation, to separate signal components, we need to find a binary mask which shows the location of each component. Therefore, it requires solving a binary optimization problem. Since most of the binary optimization problems are intractable, we relax this problem to the approximated continuous problem and solve it by alternating optimization technique. We show the application of the proposed algorithm for three applications: separation of text from a background in images, separation of moving objects from a background undergoing global camera motion in videos, and separation of sinusoidal and spike components in 1-D signals. We demonstrate in each case that considering the non-additive nature of the problem can lead to a significant improvement.
•Preparing a dataset of around 5000 X-ray images for COVID-19 detection.•Training 4 state-of-the-art convolutional networks for COVID-19 detection.•Presenting the sensitivity, specificity, ROC curve, ...AOC, and confusion matrix for each model.•Achieving sensitivity and specificity rate of higher than 90% with high confidence interval.
Display omitted
The COVID-19 pandemic is causing a major outbreak in more than 150 countries around the world, having a severe impact on the health and life of many people globally. One of the crucial step in fighting COVID-19 is the ability to detect the infected patients early enough, and put them under special care. Detecting this disease from radiography and radiology images is perhaps one of the fastest ways to diagnose the patients. Some of the early studies showed specific abnormalities in the chest radiograms of patients infected with COVID-19. Inspired by earlier works, we study the application of deep learning models to detect COVID-19 patients from their chest radiography images. We first prepare a dataset of 5000 Chest X-rays from the publicly available datasets. Images exhibiting COVID-19 disease presence were identified by board-certified radiologist. Transfer learning on a subset of 2000 radiograms was used to train four popular convolutional neural networks, including ResNet18, ResNet50, SqueezeNet, and DenseNet-121, to identify COVID-19 disease in the analyzed chest X-ray images. We evaluated these models on the remaining 3000 images, and most of these networks achieved a sensitivity rate of 98% ( ± 3%), while having a specificity rate of around 90%. Besides sensitivity and specificity rates, we also present the receiver operating characteristic (ROC) curve, precision-recall curve, average prediction, and confusion matrix of each model. We also used a technique to generate heatmaps of lung regions potentially infected by COVID-19 and show that the generated heatmaps contain most of the infected areas annotated by our board certified radiologist. While the achieved performance is very encouraging, further analysis is required on a larger set of COVID-19 images, to have a more reliable estimation of accuracy rates. The dataset, model implementations (in PyTorch), and evaluations, are all made publicly available for research community at https://github.com/shervinmin/DeepCovid.git
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Image Segmentation Using Deep Learning: A Survey Minaee, Shervin; Boykov, Yuri; Porikli, Fatih ...
IEEE transactions on pattern analysis and machine intelligence,
07/2022, Volume:
44, Issue:
7
Journal Article
Peer reviewed
Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, ...augmented reality, and image compression, among others, and numerous segmentation algorithms are found in the literature. Against this backdrop, the broad success of deep learning (DL) has prompted the development of new image segmentation approaches leveraging DL models. We provide a comprehensive review of this recent literature, covering the spectrum of pioneering efforts in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multiscale and pyramid-based approaches, recurrent networks, visual attention models, and generative models in adversarial settings. We investigate the relationships, strengths, and challenges of these DL-based segmentation models, examine the widely used datasets, compare performances, and discuss promising research directions.