From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

International Journal of Computer and Applications

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

IEEE Transactions on Pattern Analysis and Machine Intelligence

Deep Convolutional Neural Network (CNN) is a special type of Neural Networks, which has shown exemplary performance on several competitions related to Computer Vision and Image Processing. Some of the exciting application areas of CNN include Image Classification and Segmentation, Object Detection, Video Processing, Natural Language Processing, and Speech Recognition. The powerful learning ability of deep CNN is primarily due to the use of multiple feature extraction stages that can automatically learn representations from the data. The availability of a large amount of data and improvement in the hardware technology has accelerated the research in CNNs, and recently interesting deep CNN architectures have been reported. Several inspiring ideas to bring advancements in CNNs have been explored, such as the use of different activation and loss functions, parameter optimization, regularization, and architectural innovations. However, the significant improvement in the representational capacity of the deep CNN is achieved through architectural innovations. Notably, the ideas of exploiting spatial and channel information, depth and width of architecture, and multi-path information processing have gained substantial attention. Similarly, the idea of using a block of layers as a structural unit is also gaining popularity. This survey thus focuses on the intrinsic taxonomy present in the recently reported deep CNN architectures and, consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature-map exploitation, channel boosting, and attention. Additionally, the elementary understanding of CNN components, current challenges, and applications of CNN are also provided.

https://link.springer.com/content/pdf/10.1007/s10462-020-09825-6.pdf

A survey of the recent architectures of deep convolutional neural networks

The enormous number of user activity on online social networks results in a considerable amount of data which expresses the opinion from millions of people with diversity in their social aspects. The freedom of language usage shared through social media paves the way for the existence of code-mixed data that turns out to be more complex for mining the information out of it. Considering this, we created Kannada-English code mixed corpus by crawling Facebook comments. As of now, there is no relevant corpus as well as literature available for code-mixed Kannada-English sentiment analysis. In addition to the crawled corpus, we also used sentiment analysis code-mixed corpus provided by Sentiment Analysis for Indian Languages (SAIL)-2017 which includes Bengali-English and Hindi-English languages. This paper also addresses the performance of distributed representation methods in sentiment analysis task. We have reported comparisons among different machine learning and deep learning techniques.

Sentiment Analysis for Code-Mixed Indian Social Media Text With Distributed Representation

Atrial fibrillation (AF) is the predominant type of cardiac arrhythmia affecting more than 45 Million individuals globally. It is one of the leading contributors of strokes and hence detecting them in real-time is of paramount importance for early intervention. Traditional methods require long ECG traces and tedious preprocessing for accurate diagnosis. In this paper, we explore and employ deep learning methods such as RNN, LSTM and GRU to detect the Atrial Fibrillation (AF) faster in the given electrocardiogram traces. For this study, we used one of the well-known publicly available MIT-BIH Physionet dataset. To the best of our knowledge this is the first time Deep learning has been employed to detect the Atrial Fibrillation in real-time. Based on our experiments RNN, LSTM and GRU offer the accuracy of 0.950, 1.000 and 1.000 respectively. Our methodology does not require any de-noising, other filtering and preprocessing methods. Results are encouraging enough to begin clinical trials for the real-time detection of AF that will be highly beneficial in the scenarios of ambulatory, intensive care units and for real-time detection of AF for life saving implantable defibrillators.

Real-Time Detection of Atrial Fibrillation from Short Time Single Lead ECG Traces Using Recurrent Neural Networks

Entity Extraction for Malayalam Social Media Text Using Structured Skip-gram Based Embedding Features from Unlabeled Data

Real-time prediction of domain names that are generated using the Domain Generation Algorithms (DGAs) is a challenging cyber security task. Scope to collect the vast amount of data for training favored data-driven techniques and deep learning architectures have the potential to address this challenge. This paper proposes a deep learning framework using long short-term memory (LSTM) architecture for prediction of the domain names that are generated using the DGAs. Binary classification had benign and DGA domain names and multiclass classification was performed using 20 different DGAs. For the binary classification, LSTM model gave accuracy of 98.7% and 71.3% on two different test data sets and for the multi-class classification, it gave accuracy of 68.3% and 67.0% respectively. Two diversified data sets were used to analyze the robustness of the LSTM architecture.

Deep Learning Framework for Domain Generation Algorithms Prediction Using Long Short-term Memory

Kernel based methods have emerged as one of the most promising techniques for Hyper Spectral Image classification and has attracted extensive research efforts in recent years. This paper introduces a new kernel based framework for Hyper Spectral Image (HSI) classification using Grand Unified Regularized Least Squares (GURLS) library. The proposed work compares the performance of different kernel methods available in GURLS package with the library for Support Vector Machines namely, LIBSVM. The assessment is based on HSI classification accuracy measures and computation time. The experiment is performed on two standard Hyper Spectral datasets namely, Salinas A and Indian Pines subset captured by AVIRIS (Airborne Visible Infrared Imaging Spectrometer) sensor. From the analysis, it is observed that GURLS library is competitive to LIBSVM in terms of its prediction accuracy whereas computation time seems to favor LIBSVM. The major advantage of GURLS toolbox over LIBSVM is its simplicity, ease of use, automatic parameter selection and fast training and tuning of multi-class classifier. Moreover, GURLS package is provided with an implementation of Random Kitchen Sink algorithm, which can easily handle high dimensional Hyper Spectral Images at much lower computational cost than LIBSVM.

K. P. Soman

Papers

Sentiment Analysis for Code-Mixed Indian Social Media Text With Distributed Representation

Real-Time Detection of Atrial Fibrillation from Short Time Single Lead ECG Traces Using Recurrent Neural Networks

Entity Extraction for Malayalam Social Media Text Using Structured Skip-gram Based Embedding Features from Unlabeled Data

Deep Learning Framework for Domain Generation Algorithms Prediction Using Long Short-term Memory

GURLS vs LIBSVM: Performance Comparison of Kernel Methods for Hyperspectral Image Classification