The COVID-19 contagious disease that spread around the world, have a huge risk on people and already caused millions of deaths forcing a global pandemic in 2020. Diagnosing patients with this disease is very critical allowing fast care response and to isolate them from public. As the virus spread widely to millions of people, the fastest way to detect it is by analyzing radiology images. Early studies showed irregularity in the chest X-ray images of patients with high clinical belief of COVID-19 infection. Hence, these studies motivated us to investigate the use of machine learning techniques to help diagnosing COVID-19 patients from chest CT scans. In this paper, we propose to use a robust feature extraction descriptor and to apply a Random Forests classifier to predict COVID-19 disease in a dataset of 5000 images. First, 408 texture features are extracted using a powerful variation of Local Binary Patterns descriptor called Rotation Invariant Co-occurrence among Local Binary Patterns. Then, Random Forests classifier is applied with 250 trees to perform the classification task. Moreover, the performance of our approach was improved by using a multiresolution scheme where features are extracted from both the original input image and the subsampled image. Two metrics were used to evaluate our approach, sensitivity and specificity. We achieved 99.0% and 91.3% for both metrics, respectively. Our results are close to the state-of-the-art deep learning methods on the same dataset.

Automatic image classification systems for indirect immunofluorescence (IIF) labeling of human epithelial (HEp-2) cell specimens are needed to improve the efficient management of autoimmune diseases. In this paper, we propose to classify HEp-2 cell specimen imagery using a combination of local features and deep learning features extracted from the IIF images. Two local descriptors are used to capture texture information, namely: Rotation Invariant Co-occurrence among Local Binary Patterns (RIC-LBP) extending the LBP descriptor and Joint Motif Labels (JML) based on the Peano scan motif concept. Deep learning features are then extracted using the VGG-19 image classification network. Finally, all descriptors are combined using a late fusion approach with a Random Forests (RF) classifier with seven output classes. Experimental results show that our proposed framework achieves a mean class accuracy of 92.11% with five-fold cross validation using the RF classifier with 1000 trees on the HEp-2 specimen benchmark dataset, which outperforms the state-of-the-art accuracy on this dataset.

In the event of natural or man-made disasters, providing rapid situational awareness through video/image data collected at salient incident scenes is often critical to the first responders. However, computer vision techniques that can process the media-rich and data-intensive content obtained from civilian smartphones or surveillance cameras require large amounts of computational resources or ancillary data sources that may not be available at the geographical location of the incident. In this paper, we propose an incident-supporting visual cloud computing solution by defining a collection, computation, and consumption (3C) architecture supporting fog computing at the network edge close to the collection/consumption sites, which is coupled with cloud offloading to a core computation, utilizing software-defined networking (SDN). We evaluate our 3C architecture and algorithms using realistic virtual environment test beds. We also describe our insights in preparing the cloud provisioning and thin-client desktop fogs to handle the elasticity and user mobility demands in a theater-scale application. In addition, we demonstrate the use of SDN for on-demand compute offload with congestion-avoiding traffic steering to enhance remote user quality of experience in a regional-scale application. The optimization between fogs computing at the network edge with core cloud computing for managing visual analytics reduces latency, congestion, and increases throughput.

Human epithelial (HEp-2) cell specimens are obtained from indirect immunofluorescence (IIF) imaging for diagnosis and management of autoimmune diseases. Analysis of HEp2 cells is important and in this work we consider automatic cell segmentation and classification using spatial and texture pattern features and random forest classifiers. In this paper, we summarize our efforts in classification and segmentation tasks proposed in ICPR 2016 contest. For the cell level staining pattern classification (Task 1), we utilized texture features such as rotational invariant co-occurrence (RIC) versions of the well-known local binary pattern (LBP), median binary pattern (MBP), joint adaptive median binary pattern (JAMBP), and motif labels (ML) along with other optimized features. We report the classification results utilizing different classifiers such as the k-nearest neighbors (kNN), support vector machine (SVM), and random forest (RF). We obtained the best accuracy of 94.26% for six cell classes with RIC-LBP combined with a motif pattern co-occurrence labels (MCL). For specimen level staining pattern classification (Task 2) we utilize a combination RIC-LBP with RF classifier and obtain 80% accuracy for seven classes. For cell segmentation (Task 4), we use our optimized multiscale spatial feature bank along with RF classifier for pixel-wise labeling to achieve an F-measure of 84.26% for 1008 images.