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

We present a methodology for naturally grouping the estimation of Twitter messages. Miniaturized scale websites are a testing new wellspring of data for information mining methods. The aim of this paper is to focus the careful feeling of the information from the microblogging site Twitter. Tweets regularly likewise contain URLs to different sites. Tweets additionally contain a certain measure of OOV (Out-Of-Vocabulary) words, for example, Hash tags, a labeling framework for points permitting Tweets in a comparative vein of discussion to be found. Other OOV words incorporate notice which is a system to direct a Tweet to one or more users. The KH coder tool gives a conventional precision result where the content is POS labeled and MySQL is utilized for putting away points of interest as a part of the database. The R tool is utilized to view the factual examination of information. Further, machine learning calculation has likewise been performed. A preprocessing and highlight choice system in blend with a Maximum Entropy, Naive Bayes and Decision Tree classifiers has been exhibited and sensible results has been delivered. Accuracy of the machine adapting methods for sentiment has been thought about and statistical representation of the classes has been depicted through KH Coder.

Simulated and Self-Sustained Classification of Twitter Data based on its Sentiment

The remotely sensed high-dimensional hyperspectral imagery is a single capture of a scene at different spectral wavelengths. Since it contains an enormous amount of information, it has multiple areas of application in the field of remote sensing, forensic, biomedical, etc. Hyperspectral images are very prone to noise due to atmospheric effects and instrumental errors. In the past, the bands which were affected by noise were discarded before further processing such as classification. Therefore, along with the noise the relevant features present in the hyperspectral image are lost. To avoid this, researchers developed many denoising techniques. The goal of denoising technique is to remove the noise effectively while preserving the important features. Recently, the convolutional neural network (CNN) serves as a benchmark on vision-related task. Hence, hyperspectral images can be classified using CNN. The data is fed to the network as pixel vectors thus called Vectorized Convolutional Neural Network (VCNN). The objective of this work is to analyze the effect of denoising on VCNN. Here, VCNN functions as the classifier. For the purpose of comparison and to analyze the effect of denoising on VCNN, the network is trained with raw data (without denoising) and denoised data using techniques such as Total Variation (TV), Wavelet, and Least Square. The performance of the classifier is evaluated by analyzing its precision, recall, and F1-score. Also, comparison based on classwise accuracies and average accuracies for all the methods has been performed. From the comparative classification result, it is observed that Least Square denoising performs well on VCNN.

Effect of Denoising on Vectorized Convolutional Neural Network for Hyperspectral Image Classification

Malicious uniform resource locator (URL) host unsolicited content and are a serious threat and are used to commit cyber crime. Malicious URL’s are responsible for various cyber attacks like spamming, identity theft, financial fraud, etc. The internet growth has also resulted in increase of fraudulent activities in the web. The classical methods like blacklisting is ineffective in detecting newly generated malicious URL’s. So there arises a need to develop an effective algorithm to detect and classify the malicious URL’s. At the same time the recent advancement in the field of machine learning had shown promising results in areas like image processing, Natural language processing (NLP) and other domains. This motivates us to move in the direction of machine learning based techniques for detecting and classifying URL’s. However, there are significant challenges in detecting malicious URL’s that needs to be answered. First and foremost any available data used in detecting malicious URL’s is outdated. This makes the model difficult to be deployed in real time scenario. Secondly the inability to capture semantic and sequential information affects the generalization to the test data. In order to overcome these shortcomings we introduce the concept of time split and random split on the training data. Random split will randomly split the data for training and testing. Whereas time split will split the data based on time information of the URL’s. This in turn is followed by different representation of the data. These representation are passed to the classical machine learning and deep learning techniques to evaluate the performance. The analysis for data set from Sophos Machine Learning building blocks tutorial shows better performance for time split based grouping of data with decision tree classifier and an accuracy of 88.5%. Additionally, highly scalable framework is designed to collect data from various data sources in a passive way inside an Ethernet LAN. The proposed framework can collect data in real time and process in a distributed way to provide situational awareness. The proposed framework can be easily extended to handle vary large amount of cyber events by adding additional resources to the existing system.

Time Split Based Pre-processing with a Data-Driven Approach for Malicious URL Detection

/pdf/g-lets-a-new-signal-processing-algorithm-35ykl5i3oq.pdf

G-Lets: A New Signal Processing Algorithm

An efficient and reliable method for implementing Morphological Analyzer for Malayalam using Machine Learning approach has been presented here. A Morphological Analyzer segments words into morphemes and analyze word formation. Morphemes are smallest meaning bearing units in a language. Morphological Analysis is one of the techniques used in formal reading and writing. Rule based approaches are generally used for building Morphological Analyzer. The disadvantage of using rule based approaches are that if one rule fails it will affect the entire rule that follows, that is each rule works on the output of previous rule. The significance of using machine learning approach arises from the fact that rules are learned automatically from data, uses learning and classification algorithms to learn models and make predictions. The result shows that the system is very effective and after learning it predicts correct grammatical features even forwords which are not in the training set.

K. P. Soman

Papers

Simulated and Self-Sustained Classification of Twitter Data based on its Sentiment

Effect of Denoising on Vectorized Convolutional Neural Network for Hyperspectral Image Classification

Time Split Based Pre-processing with a Data-Driven Approach for Malicious URL Detection

G-Lets: A New Signal Processing Algorithm

Morphological analyzer for Malayalam using machine learning