Orchestrating Image Retrieval and Storage Over a Cloud System

Since massive numbers of images are now being communicated from, and stored in different cloud systems, faster retrieval has become extremely important. This is more relevant, especially after COVID-19 in bandwidth-constrained environments. However, to the best of our knowledge, a coherent solution to overcome this problem is yet to be investigated in the literature. In this article, by customizing the Progressive JPEG method, we propose a new Scan Script to ensure Faster Image Retrieval. Furthermore, we also propose a new lossy PJPEG architecture to reduce the file size as a solution to overcome our Scan Script's drawback. In order to achieve an orchestration between them, we improve the scanning of Progressive JPEG's picture payloads to ensure Faster Image Retrieval using the change in bit pixels of distinct Luma and Chroma components ([Formula Omitted], [Formula Omitted], and [Formula Omitted]). The orchestration improves user experience even in bandwidth-constrained cases. We evaluate our proposed orchestration in a real-world setting across two continents encompassing a private cloud. Compared to existing alternatives, our proposed orchestration can improve user waiting time by up to 54% and decrease image size by up to 27%. Our proposed work is tested in cutting-edge cloud apps, ensuring up to 69% quicker loading time.

Video Compression using Deep Neural Networks

Advanced video compression is required due to the rise of online video content. A strong compression method can help convey video data effectively over a constrained bandwidth. We observed how more internet usage for video conferences, online gaming, and education led to decreased video quality from Netflix, YouTube, and other streaming services in Europe and other regions, particularly during the COVID-19 epidemic. They are represented in standard video compression algorithms as a succession of reference frames after residual frames, and these approaches are limited in their application. Deep learning's introduction and current advancements have the potential to overcome such problems. This study provides a deep learning-based video compression model that meets or exceeds current H.264 standards. © 2022 IEEE.

Feature Adaptation Predictive Coding for Quantized Block Compressive Sensing of COVID-19 X-Ray Images

With the development of remote X-ray detection for Corona Virus Disease 2019 (COVID-19), the quantized block compressive sensing technology plays an important role when remotely acquiring the chest X-ray images of COVID-19 infected people and significantly promoting the portable telemedicine imaging applications. In order to improve the encoding performance of quantized block compressive sensing, a feature adaptation predictive coding (FAPC) method is proposed for the remote transmission of COVID-19 X-ray images. The proposed FAPC method can adaptively calculate the block-wise prediction coefficients according to the main features of COVID-19 X-ray images, and thus provide the optimal prediction candidate from the feature-guided candidate set. The proposed method can implement the high-efficiency encoding of X-ray images, and then swiftly transmit the telemedicine-oriented chest images. The experimental results show that compared with the state-of-the-art predictive coding methods, both rate-distortion and complexity performance of our FAPC method have enough competitive advantages. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth ( ∼ 100 Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos ('talking-head videos') to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users ( n=242 ) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at https://github.com/tpulkit/txt2vid.git. © 1983-2012 IEEE.

Deep CNN Based Video Compression With Lung Ultrasound Sample

Video compression and transmission is an ever-growing area of research with continuous development in both software and hardware domain, especially when it comes to medical field. Lung ultra sound (LUS) is identified as one of the best, inexpensive and harmless option to identify various lung disorders including COVID-19. The paper proposes a model to compress and transfer the LUS sample with high quality and less encoding time than the existing models. Deep convolutional neural network is exploited to work on this, as it focusses on content, more than pixels. Here two deep convolutional neural networks, ie, P(prediction)-net and B(bi-directional)-net model are proposed that takes the input as Prediction, Bidirectional frame of existing Group of Pictures and learn. The network is trained with data set of lung ultrasound sample. The trained network is validated to predict the P, B frame from the GOP. The result is evaluated with 23 raw videos and compared with existing video compression techniques. This also shows that deep learning methods might be a worthwhile endeavor not only for COVID-19, but also in general for lung pathologies. The graph shows that the model outperforms the replacement of block-based prediction algorithm in existing video compression with P-net, B-net for lower bit rates. © The Author('s).

OCR for TIFF Compressed Document Images Directly in Compressed Domain Using Text segmentation and Hidden Markov Model

In today's technological era, document images play an important and integral part in our day to day life, and specifically with the surge of Covid-19, digitally scanned documents have become key source of communication, thus avoiding any sort of infection through physical contact. Storage and transmission of scanned document images is a very memory intensive task, hence compression techniques are being used to reduce the image size before archival and transmission. To extract information or to operate on the compressed images, we have two ways of doing it. The first way is to decompress the image and operate on it and subsequently compress it again for the efficiency of storage and transmission. The other way is to use the characteristics of the underlying compression algorithm to directly process the images in their compressed form without involving decompression and re-compression. In this paper, we propose a novel idea of developing an OCR for CCITT (The International Telegraph and Telephone Consultative Committee) compressed machine printed TIFF document images directly in the compressed domain. After segmenting text regions into lines and words, HMM is applied for recognition using three coding modes of CCITT-horizontal, vertical and the pass mode. Experimental results show that OCR on pass modes give a promising results. © 2022 IEEE.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth (~100 Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos (“talking-head videos”) to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users (n = 242) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at https://github.com/tpulkit/txt2vid.git. IEEE

RL Based Unsupervised Video Summarization Framework for Ultrasound Imaging

The need for summarizing long medical scan videos for automatic triage in Emergency Departments and transmission of the summarized videos for telemedicine has gained significance during the COVID-19 pandemic. However, supervised learning schemes for summarizing videos are infeasible as manual labeling of scans for large datasets is impractical by frontline clinicians. This work presents a methodology to summarize ultrasound videos using completely unsupervised learning schemes and is validated on Lung Ultrasound videos. A Convolutional Autoencoder and a Transformer decoder is trained in an unsupervised reinforcement learning setup i.e., without supervised labels in the whole workflow. Novel precision and recall computation for ultrasound videos is also presented employing which high Precision and F1 scores of 64.36% and 35.87% with an average video compression rate of 78% is obtained when validated against clinically annotated cases. Even though demonstrated using lung ultrasound videos, our approach can be readily extended to other imaging modalities. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Covid-19 Detection Based on Chest X-Ray Images Using DCT Compression and NN

Covid-19 is a highly contagious virus spreading all over the world. It is caused by SARS-CoV-2. virus. Some of the most common symptoms are fever, cough, sore throat, tiredness, and loss of smell or taste. There are two types of tests for COVID-19: the PCR test and the antigen test. Automatic detection of Covid-19 from publicly available resources is essential. This paper employs the commonly available chest x-ray (CXR) images in the classification of Covid-19, normal and viral pneumonia cases. The proposed method divides the CXR images into subblocks and computes the Discrete Cosine Transform (DCT) for every subblock. The DCT energy compaction capability is employed to produce a compressed version for each CXR image. Few spectral DCT components are incorporated as features for each image. The compressed images are scanned by average pooling windows to reduce the dimension of the final feature vectors. A multilayer artificial neural network is employed in the 3-set classification. The proposed method achieved an average accuracy of 95 %. While the proposed method achieves comparable accuracy relative to recent state-of-the-art techniques, its computational burden and implementation time is much less. © 2022 IEEE.

Comparative Analysis of Image Enhancement Techniques for Chest X-ray Images

X-ray radiography plays a crucial part in diagnosis of various diseases in human body like Covid-19, Cancer and Pneumonia. The images obtained through X-ray radiography is interpreted by Surgeons, Pathologists and Radiologists for detecting anomaly in scanned body part. Chest X-ray is one of the cheapest and easily accessible tests of functioning of chest and lungs. However, images obtained through X-ray are not very clear, low in contrast and with lesser variation in gray level. Image enhancement is done for better visualization of images and bringing forward the underlying details of image. The Kaggle repository of total 6334 chest X-ray images were used for experimentation and calculation works. In this paper, we have compared various combinations of contrast enhancement techniques such as CLAHE, Morphological operations (black and white hat transforms) and noise reduction techniques like Median filter, DCT and DWT. The Comparison was done on the basis of image quality assessment parameters such as MSE, PSNR, and AMBE. The results showed that fusion of CLAHE and DWT techniques gave best results with highest PSNR value and lowest AMBE among the various models discussed. The proposed methodology shall be very helpful in diagnosis of diseases from chest X-ray images. © 2022 IEEE.

AI-Based Saliency-Aware Video Coding

The demand for video through over-the-top (OTT) has been constantly increasing in recent years. During the COVID-19 pandemic, demand skyrocketed, hence leading to the need for better video compression. The human visual system (HVS) can quickly select visually important regions in its visual field. These regions are captured at high resolution, while other peripheral regions receive little attention. Saliency maps are a way to imitate the HVS attention mechanism. Recently, deep learning-based saliency models have achieved tremendous improvements. This article leverages state-of-the-art deep learning-based saliency models to improve video coding efficiency. First, a saliency-based rate control scheme is integrated in a high-efficiency video encoder (HEVC). Then, a saliency-guided preprocessing filtering step is introduced. Finally, the two approaches are combined. Objective and subjective evaluations show that it can lower the bitrate from 6% to almost 30% while maintaining the same visual quality. © 2002 Society of Motion Picture and Television Engineers, Inc.

Orchestrating Image Retrieval and Storage over A Cloud System

Since massive numbers of images are now being communicated from, and stored in different cloud systems, faster retrieval has become extremely important. This is more relevant, especially after COVID-19 in bandwidth-constrained environments. However, to the best of our knowledge, a coherent solution to overcome this problem is yet to be investigated in the literature. In this paper, by customizing the Progressive JPEG method, we propose a new Scan Script to ensure Faster Image Retrieval. Furthermore, we also propose a new lossy PJPEG architecture to reduce the file size as a solution to overcome our Scan Script's drawback. In order to achieve an orchestration between them, we improve the scanning of Progressive JPEG's picture payloads to ensure Faster Image Retrieval using the change in bit pixels of distinct Luma and Chroma components (Y, C_b, and C_r). The orchestration improves user experience even in bandwidth-constrained cases. We evaluate our proposed orchestration in a real-world setting across two continents encompassing a private cloud. Compared to existing alternatives, our proposed orchestration can improve user waiting time by up to 54% and decrease image size by up to 27%. Our proposed work is tested in cutting-edge cloud apps, ensuring up to 69% quicker loading time. IEEE

Review of subjective quality assessment methodologies and standards for compressed images evaluation

Acquiring and exchanging a large number of pictures has become nowadays a common practice. Therefore, new image compression solutions to optimize the storage resources are in constant demand. In this context, it is essential to have a solid methodology to evaluate the performance of compression techniques. Such performance is usually measured through objective quality metrics, which are fast and inexpensive but not always reliable. However, performance is best assessed through subjective image quality assessment experiments, which are expensive and time-consuming, but reliable as based on the subjective opinion of a large number of subjects. These experiments are usually conducted in a controlled laboratory environment, with high-quality monitors and controlled lighting conditions. Recently, encouraged by the COVID-19 pandemic, crowdsourcing-based subjective image quality experiments are gaining popularity, and have demonstrated to be a faster and cheaper alternative to traditional approaches in subjective quality assessment. In this paper, different methodologies for subjective image quality assessment experiments are examined, including a review of the released standards as well as a list of publicly available tools. Moreover, the analysis is extended to novel plenoptic imaging techniques, i.e. point clouds and light fields, and to visually lossless quality assessment approaches. Authors hope that this work will help researchers interested in conducting subjective experiments for assessing the quality of compressed media, to better select the appropriate methodology for their use cases.

Breaking Barriers in Emerging Biomedical Applications.

The recent global COVID-19 pandemic has revealed that the current healthcare system in modern society can hardly cope with the increased number of patients. Part of the load can be alleviated by incorporating smart healthcare infrastructure in the current system to enable patient's remote monitoring and personalized treatment. Technological advances in communications and sensing devices have enabled the development of new, portable, and more power-efficient biomedical sensors, as well as innovative healthcare applications. Nevertheless, such applications require reliable, resilient, and secure networks. This paper aims to identify the communication requirements for mass deployment of such smart healthcare sensors by providing the overview of underlying Internet of Things (IoT) technologies. Moreover, it highlights the importance of information theory in understanding the limits and barriers in this emerging field. With this motivation, the paper indicates how data compression and entropy used in security algorithms may pave the way towards mass deployment of such IoT healthcare devices. Future medical practices and paradigms are also discussed.