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

Part of speech (POS) tagging is the process of annotating syntactic categories for each word in a corpus. This paper presents an SVM methodology based on Linear Programming for implementing automatic Tamil POS tagger. We have designed our own tagset consisting of 32 tags for preparing the annotated corpus for Tamil. The features are extracted from a corpus of twenty five thousand sentences and trained with linear programming based SVM. This method, when tested with 10,000 sentences, gave an overall accuracy of 95.63%. Index Terms— Annotated corpus, tokenization, tagging, machine learning.

Tamil POS Tagging using Linear Programming

Data mining: theory and practice

Automated sleep apnea detection and severity identification has largely focused on multivariate sensor data in the past two decades. Clinically too, sleep apnea is identified using a combination of markers including blood oxygen saturation, respiration rate etc. More recently, scientists have begun to investigate the use of instantaneous heart rates for detection and severity measurement of sleep apnea. However, the best-known techniques that use heart rate and its derivatives have been able to achieve less than 85% accuracy in classifying minute-to-minute apnea data. In our research reported in this paper, we apply a deep learning technique called LSTM-RNN (long short-term memory recurrent neural network) for identification of sleep apnea and its severity based only on instantaneous heart rates. We have tested this model on multiple sleep apnea datasets and obtained perfect accuracy. Furthermore, we have also tested its robustness on an arrhythmia dataset (that is highly probable in mimicking sleep apnea heart rate variability) and found that the model is highly accurate in distinguishing between the two.

Instantaneous heart rate as a robust feature for sleep apnea severity detection using deep learning

DeepMalNet: Evaluating shallow and deep networks for static PE malware detection

In this modern world many communication devices are highly intelligent and interconnected between each other. Any up-gradation of the hardware in the existing communication devices is not easier one. Compatibility of the new hardware with existing hardware is highly essential. But the new protocols may or may not support the older one. The solution for these problems can be provided by using the reconfigurable hardware design. The hardware can be reprogrammed according to the new change in technology up-gradation. The cost of commercially available hardware and software requirements for setting up such a module is very high. This can be solved by using Open source hardware and software such as Universal Software Radio Peripheral (USRP) and GNU Radio. This work demonstrates how the modern analog communication system like Community Radio Schemes and Radio Data System (RDS) and digital communication systems such as Simple Digital Video Broadcasting (DVB) and OFDM based data communication can be developed using the Open source hardware USRP1. This work will be helpful even for first year level of engineering students to easily implement any communication and control applications with cheaper cost.

K. P. Soman

Papers

Tamil POS Tagging using Linear Programming

Data mining: theory and practice

Instantaneous heart rate as a robust feature for sleep apnea severity detection using deep learning

DeepMalNet: Evaluating shallow and deep networks for static PE malware detection

Modern analog and digital communication systems development using GNU Radio with USRP