Feature Coding for Image Representation and Recognition

Feature Coding for Image Representation and Recognition

Author: Yongzhen Huang

Publisher: Springer

Published: 2015-01-05

Total Pages: 80

ISBN-13: 3662450003

DOWNLOAD EBOOK

This brief presents a comprehensive introduction to feature coding, which serves as a key module for the typical object recognition pipeline. The text offers a rich blend of theory and practice while reflects the recent developments on feature coding, covering the following five aspects: (1) Review the state-of-the-art, analyzing the motivations and mathematical representations of various feature coding methods; (2) Explore how various feature coding algorithms evolve along years; (3) Summarize the main characteristics of typical feature coding algorithms and categorize them accordingly; (4) Discuss the applications of feature coding in different visual tasks, analyze the influence of some key factors in feature coding with intensive experimental studies; (5) Provide the suggestions of how to apply different feature coding methods and forecast the potential directions for future work on the topic. It is suitable for students, researchers, practitioners interested in object recognition.


Book Synopsis Feature Coding for Image Representation and Recognition by : Yongzhen Huang

Download or read book Feature Coding for Image Representation and Recognition written by Yongzhen Huang and published by Springer. This book was released on 2015-01-05 with total page 80 pages. Available in PDF, EPUB and Kindle. Book excerpt: This brief presents a comprehensive introduction to feature coding, which serves as a key module for the typical object recognition pipeline. The text offers a rich blend of theory and practice while reflects the recent developments on feature coding, covering the following five aspects: (1) Review the state-of-the-art, analyzing the motivations and mathematical representations of various feature coding methods; (2) Explore how various feature coding algorithms evolve along years; (3) Summarize the main characteristics of typical feature coding algorithms and categorize them accordingly; (4) Discuss the applications of feature coding in different visual tasks, analyze the influence of some key factors in feature coding with intensive experimental studies; (5) Provide the suggestions of how to apply different feature coding methods and forecast the potential directions for future work on the topic. It is suitable for students, researchers, practitioners interested in object recognition.

Computer Vision -- ECCV 2010

Computer Vision -- ECCV 2010

Author: Kostas Daniilidis

Publisher: Springer Science & Business Media

Published: 2010-08-30

Total Pages: 836

ISBN-13: 364215560X

DOWNLOAD EBOOK

The six-volume set comprising LNCS volumes 6311 until 6313 constitutes the refereed proceedings of the 11th European Conference on Computer Vision, ECCV 2010, held in Heraklion, Crete, Greece, in September 2010. The 325 revised papers presented were carefully reviewed and selected from 1174 submissions. The papers are organized in topical sections on object and scene recognition; segmentation and grouping; face, gesture, biometrics; motion and tracking; statistical models and visual learning; matching, registration, alignment; computational imaging; multi-view geometry; image features; video and event characterization; shape representation and recognition; stereo; reflectance, illumination, color; medical image analysis.


Book Synopsis Computer Vision -- ECCV 2010 by : Kostas Daniilidis

Download or read book Computer Vision -- ECCV 2010 written by Kostas Daniilidis and published by Springer Science & Business Media. This book was released on 2010-08-30 with total page 836 pages. Available in PDF, EPUB and Kindle. Book excerpt: The six-volume set comprising LNCS volumes 6311 until 6313 constitutes the refereed proceedings of the 11th European Conference on Computer Vision, ECCV 2010, held in Heraklion, Crete, Greece, in September 2010. The 325 revised papers presented were carefully reviewed and selected from 1174 submissions. The papers are organized in topical sections on object and scene recognition; segmentation and grouping; face, gesture, biometrics; motion and tracking; statistical models and visual learning; matching, registration, alignment; computational imaging; multi-view geometry; image features; video and event characterization; shape representation and recognition; stereo; reflectance, illumination, color; medical image analysis.

Sparse Coding and Its Applications in Computer Vision

Sparse Coding and Its Applications in Computer Vision

Author: Zhaowen E. T. Al WANG

Publisher: World Scientific

Published: 2015-10-28

Total Pages: 239

ISBN-13: 9814725056

DOWNLOAD EBOOK

"This book provides a broader introduction to the theories and applications of sparse coding techniques in computer vision research. It introduces sparse coding in the context of representation learning, illustrates the fundamental concepts, and summarizes the most active research directions. A variety of applications of sparse coding are discussed, ranging from low-level image processing tasks such as super-resolution and de-blurring to high-level semantic understanding tasks such as image recognition, clustering and fusion. The book is suitable to be used as an introductory overview to this field, with its theoretical part being both easy and precious enough for quick understanding. It is also of great value to experienced researchers as it offers new perspective to the underlying mechanism of sparse coding, and points out potential future directions for different applications."--


Book Synopsis Sparse Coding and Its Applications in Computer Vision by : Zhaowen E. T. Al WANG

Download or read book Sparse Coding and Its Applications in Computer Vision written by Zhaowen E. T. Al WANG and published by World Scientific. This book was released on 2015-10-28 with total page 239 pages. Available in PDF, EPUB and Kindle. Book excerpt: "This book provides a broader introduction to the theories and applications of sparse coding techniques in computer vision research. It introduces sparse coding in the context of representation learning, illustrates the fundamental concepts, and summarizes the most active research directions. A variety of applications of sparse coding are discussed, ranging from low-level image processing tasks such as super-resolution and de-blurring to high-level semantic understanding tasks such as image recognition, clustering and fusion. The book is suitable to be used as an introductory overview to this field, with its theoretical part being both easy and precious enough for quick understanding. It is also of great value to experienced researchers as it offers new perspective to the underlying mechanism of sparse coding, and points out potential future directions for different applications."--

Feature Extraction and Image Processing for Computer Vision

Feature Extraction and Image Processing for Computer Vision

Author: Mark Nixon

Publisher: Academic Press

Published: 2012-12-18

Total Pages: 629

ISBN-13: 0123978246

DOWNLOAD EBOOK

Feature Extraction and Image Processing for Computer Vision is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in Matlab. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated. As one reviewer noted, "The main strength of the proposed book is the exemplar code of the algorithms." Fully updated with the latest developments in feature extraction, including expanded tutorials and new techniques, this new edition contains extensive new material on Haar wavelets, Viola-Jones, bilateral filtering, SURF, PCA-SIFT, moving object detection and tracking, development of symmetry operators, LBP texture analysis, Adaboost, and a new appendix on color models. Coverage of distance measures, feature detectors, wavelets, level sets and texture tutorials has been extended. Named a 2012 Notable Computer Book for Computing Methodologies by Computing Reviews Essential reading for engineers and students working in this cutting-edge field Ideal module text and background reference for courses in image processing and computer vision The only currently available text to concentrate on feature extraction with working implementation and worked through derivation


Book Synopsis Feature Extraction and Image Processing for Computer Vision by : Mark Nixon

Download or read book Feature Extraction and Image Processing for Computer Vision written by Mark Nixon and published by Academic Press. This book was released on 2012-12-18 with total page 629 pages. Available in PDF, EPUB and Kindle. Book excerpt: Feature Extraction and Image Processing for Computer Vision is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in Matlab. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated. As one reviewer noted, "The main strength of the proposed book is the exemplar code of the algorithms." Fully updated with the latest developments in feature extraction, including expanded tutorials and new techniques, this new edition contains extensive new material on Haar wavelets, Viola-Jones, bilateral filtering, SURF, PCA-SIFT, moving object detection and tracking, development of symmetry operators, LBP texture analysis, Adaboost, and a new appendix on color models. Coverage of distance measures, feature detectors, wavelets, level sets and texture tutorials has been extended. Named a 2012 Notable Computer Book for Computing Methodologies by Computing Reviews Essential reading for engineers and students working in this cutting-edge field Ideal module text and background reference for courses in image processing and computer vision The only currently available text to concentrate on feature extraction with working implementation and worked through derivation

Image Processing and Pattern Recognition

Image Processing and Pattern Recognition

Author: Frank Y. Shih

Publisher: John Wiley & Sons

Published: 2010-07-16

Total Pages: 551

ISBN-13: 0470590408

DOWNLOAD EBOOK

A comprehensive guide to the essential principles of image processing and pattern recognition Techniques and applications in the areas of image processing and pattern recognition are growing at an unprecedented rate. Containing the latest state-of-the-art developments in the field, Image Processing and Pattern Recognition presents clear explanations of the fundamentals as well as the most recent applications. It explains the essential principles so readers will not only be able to easily implement the algorithms and techniques, but also lead themselves to discover new problems and applications. Unlike other books on the subject, this volume presents numerous fundamental and advanced image processing algorithms and pattern recognition techniques to illustrate the framework. Scores of graphs and examples, technical assistance, and practical tools illustrate the basic principles and help simplify the problems, allowing students as well as professionals to easily grasp even complicated theories. It also features unique coverage of the most interesting developments and updated techniques, such as image watermarking, digital steganography, document processing and classification, solar image processing and event classification, 3-D Euclidean distance transformation, shortest path planning, soft morphology, recursive morphology, regulated morphology, and sweep morphology. Additional topics include enhancement and segmentation techniques, active learning, feature extraction, neural networks, and fuzzy logic. Featuring supplemental materials for instructors and students, Image Processing and Pattern Recognition is designed for undergraduate seniors and graduate students, engineering and scientific researchers, and professionals who work in signal processing, image processing, pattern recognition, information security, document processing, multimedia systems, and solar physics.


Book Synopsis Image Processing and Pattern Recognition by : Frank Y. Shih

Download or read book Image Processing and Pattern Recognition written by Frank Y. Shih and published by John Wiley & Sons. This book was released on 2010-07-16 with total page 551 pages. Available in PDF, EPUB and Kindle. Book excerpt: A comprehensive guide to the essential principles of image processing and pattern recognition Techniques and applications in the areas of image processing and pattern recognition are growing at an unprecedented rate. Containing the latest state-of-the-art developments in the field, Image Processing and Pattern Recognition presents clear explanations of the fundamentals as well as the most recent applications. It explains the essential principles so readers will not only be able to easily implement the algorithms and techniques, but also lead themselves to discover new problems and applications. Unlike other books on the subject, this volume presents numerous fundamental and advanced image processing algorithms and pattern recognition techniques to illustrate the framework. Scores of graphs and examples, technical assistance, and practical tools illustrate the basic principles and help simplify the problems, allowing students as well as professionals to easily grasp even complicated theories. It also features unique coverage of the most interesting developments and updated techniques, such as image watermarking, digital steganography, document processing and classification, solar image processing and event classification, 3-D Euclidean distance transformation, shortest path planning, soft morphology, recursive morphology, regulated morphology, and sweep morphology. Additional topics include enhancement and segmentation techniques, active learning, feature extraction, neural networks, and fuzzy logic. Featuring supplemental materials for instructors and students, Image Processing and Pattern Recognition is designed for undergraduate seniors and graduate students, engineering and scientific researchers, and professionals who work in signal processing, image processing, pattern recognition, information security, document processing, multimedia systems, and solar physics.

Recent Advances in Intelligent Image Search and Video Retrieval

Recent Advances in Intelligent Image Search and Video Retrieval

Author: Chengjun Liu

Publisher: Springer

Published: 2017-04-18

Total Pages: 246

ISBN-13: 3319520814

DOWNLOAD EBOOK

This book initially reviews the major feature representation and extraction methods and effective learning and recognition approaches, which have broad applications in the context of intelligent image search and video retrieval. It subsequently presents novel methods, such as improved soft assignment coding, Inheritable Color Space (InCS) and the Generalized InCS framework, the sparse kernel manifold learner method, the efficient Support Vector Machine (eSVM), and the Scale-Invariant Feature Transform (SIFT) features in multiple color spaces. Lastly, the book presents clothing analysis for subject identification and retrieval, and performance evaluation methods of video analytics for traffic monitoring. Digital images and videos are proliferating at an amazing speed in the fields of science, engineering and technology, media and entertainment. With the huge accumulation of such data, keyword searches and manual annotation schemes may no longer be able to meet the practical demand for retrieving relevant content from images and videos, a challenge this book addresses.This book initially reviews the major feature representation and extraction methods and effective learning and recognition approaches, which have broad applications in the context of intelligent image search and video retrieval. It subsequently presents novel methods, such as improved soft assignment coding, Inheritable Color Space (InCS) and the Generalized InCS framework, the sparse kernel manifold learner method, the efficient Support Vector Machine (eSVM), and the Scale-Invariant Feature Transform (SIFT) features in multiple color spaces. Lastly, the book presents clothing analysis for subject identification and retrieval, and performance evaluation methods of video analytics for traffic monitoring. Digital images and videos are proliferating at an amazing speed in the fields of science, engineering and technology, media and entertainment. With the huge accumulation of such data, keyword searches and manual annotation schemes may no longer be able to meet the practical demand for retrieving relevant content from images and videos, a challenge this book addresses.


Book Synopsis Recent Advances in Intelligent Image Search and Video Retrieval by : Chengjun Liu

Download or read book Recent Advances in Intelligent Image Search and Video Retrieval written by Chengjun Liu and published by Springer. This book was released on 2017-04-18 with total page 246 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book initially reviews the major feature representation and extraction methods and effective learning and recognition approaches, which have broad applications in the context of intelligent image search and video retrieval. It subsequently presents novel methods, such as improved soft assignment coding, Inheritable Color Space (InCS) and the Generalized InCS framework, the sparse kernel manifold learner method, the efficient Support Vector Machine (eSVM), and the Scale-Invariant Feature Transform (SIFT) features in multiple color spaces. Lastly, the book presents clothing analysis for subject identification and retrieval, and performance evaluation methods of video analytics for traffic monitoring. Digital images and videos are proliferating at an amazing speed in the fields of science, engineering and technology, media and entertainment. With the huge accumulation of such data, keyword searches and manual annotation schemes may no longer be able to meet the practical demand for retrieving relevant content from images and videos, a challenge this book addresses.This book initially reviews the major feature representation and extraction methods and effective learning and recognition approaches, which have broad applications in the context of intelligent image search and video retrieval. It subsequently presents novel methods, such as improved soft assignment coding, Inheritable Color Space (InCS) and the Generalized InCS framework, the sparse kernel manifold learner method, the efficient Support Vector Machine (eSVM), and the Scale-Invariant Feature Transform (SIFT) features in multiple color spaces. Lastly, the book presents clothing analysis for subject identification and retrieval, and performance evaluation methods of video analytics for traffic monitoring. Digital images and videos are proliferating at an amazing speed in the fields of science, engineering and technology, media and entertainment. With the huge accumulation of such data, keyword searches and manual annotation schemes may no longer be able to meet the practical demand for retrieving relevant content from images and videos, a challenge this book addresses.

Pattern Recognition and Image Processing in C++

Pattern Recognition and Image Processing in C++

Author: Dietrich Paulus

Publisher: Vieweg+Teubner Verlag

Published: 2012-12-06

Total Pages: 370

ISBN-13: 3322878678

DOWNLOAD EBOOK

Parts of this text were used for several years by students in a one~term under graduate course in computer science. The students had to prepare projects in small groups (2~4 students).1 This book emphasizes practical experience with image processing. It offers a comprehensive study of • image processing and image analysis, • basics of speech processing, • object~oriented programming, • software design, • and programming in C++. The book is divided into four parts. In the first part we introduce image processing, image analysis, programming tools, and the basics of C++. In the second part we describe object~oriented programming in general and the possible applications of object~oriented concepts in C++. Several appli cations of object~oriented programming for image processing are discussed as well. The new features of C++ are introduced entirely through the use of examples. We cover the proper representation of the data that is a result of pattern analysis as well. The third part describes a complete system for image segmentation. Some of the material covered refers to the exercises found in the first and second parts: this verifies our belief that an image segmentation system of programs can be developed while simultaneously acquainting others to C++. We combine the data representation described in the second part with the algorithms that use and manipulate them here in the third part.


Book Synopsis Pattern Recognition and Image Processing in C++ by : Dietrich Paulus

Download or read book Pattern Recognition and Image Processing in C++ written by Dietrich Paulus and published by Vieweg+Teubner Verlag. This book was released on 2012-12-06 with total page 370 pages. Available in PDF, EPUB and Kindle. Book excerpt: Parts of this text were used for several years by students in a one~term under graduate course in computer science. The students had to prepare projects in small groups (2~4 students).1 This book emphasizes practical experience with image processing. It offers a comprehensive study of • image processing and image analysis, • basics of speech processing, • object~oriented programming, • software design, • and programming in C++. The book is divided into four parts. In the first part we introduce image processing, image analysis, programming tools, and the basics of C++. In the second part we describe object~oriented programming in general and the possible applications of object~oriented concepts in C++. Several appli cations of object~oriented programming for image processing are discussed as well. The new features of C++ are introduced entirely through the use of examples. We cover the proper representation of the data that is a result of pattern analysis as well. The third part describes a complete system for image segmentation. Some of the material covered refers to the exercises found in the first and second parts: this verifies our belief that an image segmentation system of programs can be developed while simultaneously acquainting others to C++. We combine the data representation described in the second part with the algorithms that use and manipulate them here in the third part.

Experimental Robotics

Experimental Robotics

Author: Jaydev P. Desai

Publisher: Springer

Published: 2013-07-09

Total Pages: 966

ISBN-13: 3319000659

DOWNLOAD EBOOK

The International Symposium on Experimental Robotics (ISER) is a series of bi-annual meetings, which are organized, in a rotating fashion around North America, Europe and Asia/Oceania. The goal of ISER is to provide a forum for research in robotics that focuses on novelty of theoretical contributions validated by experimental results. The meetings are conceived to bring together, in a small group setting, researchers from around the world who are in the forefront of experimental robotics research. This unique reference presents the latest advances across the various fields of robotics, with ideas that are not only conceived conceptually but also explored experimentally. It collects robotics contributions on the current developments and new directions in the field of experimental robotics, which are based on the papers presented at the 13the ISER held in Québec City, Canada, at the Fairmont Le Château Frontenac, on June 18-21, 2012. This present thirteenth edition of Experimental Robotics edited by Jaydev P. Desai, Gregory Dudek, Oussama Khatib, and Vijay Kumar offers a collection of a broad range of topics in field and human-centered robotics.


Book Synopsis Experimental Robotics by : Jaydev P. Desai

Download or read book Experimental Robotics written by Jaydev P. Desai and published by Springer. This book was released on 2013-07-09 with total page 966 pages. Available in PDF, EPUB and Kindle. Book excerpt: The International Symposium on Experimental Robotics (ISER) is a series of bi-annual meetings, which are organized, in a rotating fashion around North America, Europe and Asia/Oceania. The goal of ISER is to provide a forum for research in robotics that focuses on novelty of theoretical contributions validated by experimental results. The meetings are conceived to bring together, in a small group setting, researchers from around the world who are in the forefront of experimental robotics research. This unique reference presents the latest advances across the various fields of robotics, with ideas that are not only conceived conceptually but also explored experimentally. It collects robotics contributions on the current developments and new directions in the field of experimental robotics, which are based on the papers presented at the 13the ISER held in Québec City, Canada, at the Fairmont Le Château Frontenac, on June 18-21, 2012. This present thirteenth edition of Experimental Robotics edited by Jaydev P. Desai, Gregory Dudek, Oussama Khatib, and Vijay Kumar offers a collection of a broad range of topics in field and human-centered robotics.

Advances in Reasoning-Based Image Processing Intelligent Systems

Advances in Reasoning-Based Image Processing Intelligent Systems

Author: Roumen Kountchev

Publisher: Springer Science & Business Media

Published: 2012-01-13

Total Pages: 460

ISBN-13: 3642246931

DOWNLOAD EBOOK

The book puts special stress on the contemporary techniques for reasoning-based image processing and analysis: learning based image representation and advanced video coding; intelligent image processing and analysis in medical vision systems; similarity learning models for image reconstruction; visual perception for mobile robot motion control, simulation of human brain activity in the analysis of video sequences; shape-based invariant features extraction; essential of paraconsistent neural networks, creativity and intelligent representation in computational systems. The book comprises 14 chapters. Each chapter is a small monograph, representing resent investigations of authors in the area. The topics of the chapters cover wide scientific and application areas and complement each-other very well. The chapters’ content is based on fundamental theoretical presentations, followed by experimental results and comparison with similar techniques. The size of the chapters is well-ballanced which permits a thorough presentation of the investigated problems. The authors are from universities and R&D institutions all over the world; some of the chapters are prepared by international teams. The book will be of use for university and PhD students, researchers and software developers working in the area of digital image and video processing and analysis.


Book Synopsis Advances in Reasoning-Based Image Processing Intelligent Systems by : Roumen Kountchev

Download or read book Advances in Reasoning-Based Image Processing Intelligent Systems written by Roumen Kountchev and published by Springer Science & Business Media. This book was released on 2012-01-13 with total page 460 pages. Available in PDF, EPUB and Kindle. Book excerpt: The book puts special stress on the contemporary techniques for reasoning-based image processing and analysis: learning based image representation and advanced video coding; intelligent image processing and analysis in medical vision systems; similarity learning models for image reconstruction; visual perception for mobile robot motion control, simulation of human brain activity in the analysis of video sequences; shape-based invariant features extraction; essential of paraconsistent neural networks, creativity and intelligent representation in computational systems. The book comprises 14 chapters. Each chapter is a small monograph, representing resent investigations of authors in the area. The topics of the chapters cover wide scientific and application areas and complement each-other very well. The chapters’ content is based on fundamental theoretical presentations, followed by experimental results and comparison with similar techniques. The size of the chapters is well-ballanced which permits a thorough presentation of the investigated problems. The authors are from universities and R&D institutions all over the world; some of the chapters are prepared by international teams. The book will be of use for university and PhD students, researchers and software developers working in the area of digital image and video processing and analysis.

Unsupervised Feature Learning Via Sparse Hierarchical Representations

Unsupervised Feature Learning Via Sparse Hierarchical Representations

Author: Honglak Lee

Publisher: Stanford University

Published: 2010

Total Pages: 133

ISBN-13:

DOWNLOAD EBOOK

Machine learning has proved a powerful tool for artificial intelligence and data mining problems. However, its success has usually relied on having a good feature representation of the data, and having a poor representation can severely limit the performance of learning algorithms. These feature representations are often hand-designed, require significant amounts of domain knowledge and human labor, and do not generalize well to new domains. To address these issues, I will present machine learning algorithms that can automatically learn good feature representations from unlabeled data in various domains, such as images, audio, text, and robotic sensors. Specifically, I will first describe how efficient sparse coding algorithms --- which represent each input example using a small number of basis vectors --- can be used to learn good low-level representations from unlabeled data. I also show that this gives feature representations that yield improved performance in many machine learning tasks. In addition, building on the deep learning framework, I will present two new algorithms, sparse deep belief networks and convolutional deep belief networks, for building more complex, hierarchical representations, in which more complex features are automatically learned as a composition of simpler ones. When applied to images, this method automatically learns features that correspond to objects and decompositions of objects into object-parts. These features often lead to performance competitive with or better than highly hand-engineered computer vision algorithms in object recognition and segmentation tasks. Further, the same algorithm can be used to learn feature representations from audio data. In particular, the learned features yield improved performance over state-of-the-art methods in several speech recognition tasks.


Book Synopsis Unsupervised Feature Learning Via Sparse Hierarchical Representations by : Honglak Lee

Download or read book Unsupervised Feature Learning Via Sparse Hierarchical Representations written by Honglak Lee and published by Stanford University. This book was released on 2010 with total page 133 pages. Available in PDF, EPUB and Kindle. Book excerpt: Machine learning has proved a powerful tool for artificial intelligence and data mining problems. However, its success has usually relied on having a good feature representation of the data, and having a poor representation can severely limit the performance of learning algorithms. These feature representations are often hand-designed, require significant amounts of domain knowledge and human labor, and do not generalize well to new domains. To address these issues, I will present machine learning algorithms that can automatically learn good feature representations from unlabeled data in various domains, such as images, audio, text, and robotic sensors. Specifically, I will first describe how efficient sparse coding algorithms --- which represent each input example using a small number of basis vectors --- can be used to learn good low-level representations from unlabeled data. I also show that this gives feature representations that yield improved performance in many machine learning tasks. In addition, building on the deep learning framework, I will present two new algorithms, sparse deep belief networks and convolutional deep belief networks, for building more complex, hierarchical representations, in which more complex features are automatically learned as a composition of simpler ones. When applied to images, this method automatically learns features that correspond to objects and decompositions of objects into object-parts. These features often lead to performance competitive with or better than highly hand-engineered computer vision algorithms in object recognition and segmentation tasks. Further, the same algorithm can be used to learn feature representations from audio data. In particular, the learned features yield improved performance over state-of-the-art methods in several speech recognition tasks.