Semantic and Interactive Content-based Image Retrieval

Semantic and Interactive Content-based Image Retrieval PDF

Author: Björn Barz

Publisher: Cuvillier Verlag

Published: 2020-12-23

Total Pages: 322

ISBN-13: 3736963467

DOWNLOAD EBOOK →

Content-based Image Retrieval (CBIR) ist ein Verfahren zum Auffinden von Bildern in großen Datenbanken wie z. B. dem Internet anhand ihres Inhalts. Ausgehend von einem vom Nutzer bereitgestellten Anfragebild, gibt das System eine sortierte Liste ähnlicher Bilder zurück. Der Großteil moderner CBIR-Systeme vergleicht Bilder ausschließlich anhand ihrer visuellen Ähnlichkeit, d.h. dem Vorhandensein ähnlicher Texturen, Farbkompositionen etc. Jedoch impliziert visuelle Ähnlichkeit nicht zwangsläufig auch semantische Ähnlichkeit. Zum Beispiel können Bilder von Schmetterlingen und Raupen als ähnlich betrachtet werden, weil sich die Raupe irgendwann in einen Schmetterling verwandelt. Optisch haben sie jedoch nicht viel gemeinsam. Die vorliegende Arbeit stellt eine Methode vor, welche solch menschliches Vorwissen über die Semantik der Welt in Deep-Learning-Verfahren integriert. Als Quelle für dieses Wissen dienen Taxonomien, die für eine Vielzahl von Domänen verfügbar sind und hierarchische Beziehungen zwischen Konzepten kodieren (z.B., ein Pudel ist ein Hund ist ein Tier etc.). Diese hierarchiebasierten semantischen Bildmerkmale verbessern die semantische Konsistenz der CBIR-Ergebnisse im Vergleich zu herkömmlichen Repräsentationen und Merkmalen erheblich. Darüber hinaus werden drei verschiedene Mechanismen für interaktives Image Retrieval präsentiert, welche die den Anfragebildern inhärente semantische Ambiguität durch Einbezug von Benutzerfeedback auflösen. Eine der vorgeschlagenen Methoden reduziert das erforderliche Feedback mithilfe von Clustering auf einen einzigen Klick, während eine andere den Nutzer kontinuierlich involviert, indem das System aktiv nach Feedback zu denjenigen Bildern fragt, von denen der größte Erkenntnisgewinn bezüglich des Relevanzmodells erwartet wird. Die dritte Methode ermöglicht dem Benutzer die Auswahl besonders interessanter Bildbereiche zur Fokussierung der Ergebnisse. Diese Techniken liefern bereits nach wenigen Feedbackrunden deutlich relevantere Ergebnisse, was die Gesamtmenge der abgerufenen Bilder reduziert, die der Benutzer überprüfen muss, um relevante Bilder zu finden. Content-based image retrieval (CBIR) aims for finding images in large databases such as the internet based on their content. Given an exemplary query image provided by the user, the retrieval system provides a ranked list of similar images. Most contemporary CBIR systems compare images solely by means of their visual similarity, i.e., the occurrence of similar textures and the composition of colors. However, visual similarity does not necessarily coincide with semantic similarity. For example, images of butterflies and caterpillars can be considered as similar, because the caterpillar turns into a butterfly at some point in time. Visually, however, they do not have much in common. In this work, we propose to integrate such human prior knowledge about the semantics of the world into deep learning techniques. Class hierarchies serve as a source for this knowledge, which are readily available for a plethora of domains and encode is-a relationships (e.g., a poodle is a dog is an animal etc.). Our hierarchy-based semantic embeddings improve the semantic consistency of CBIR results substantially compared to conventional image representations and features. We furthermore present three different mechanisms for interactive image retrieval by incorporating user feedback to resolve the inherent semantic ambiguity present in the query image. One of the proposed methods reduces the required user feedback to a single click using clustering, while another keeps the human in the loop by actively asking for feedback regarding those images which are expected to improve the relevance model the most. The third method allows the user to select particularly interesting regions in images. These techniques yield more relevant results after a few rounds of feedback, which reduces the total amount of retrieved images the user needs to inspect to find relevant ones.

Handbook on Neural Information Processing

Handbook on Neural Information Processing PDF

Author: Monica Bianchini

Publisher: Springer Science & Business Media

Published: 2013-04-12

Total Pages: 547

ISBN-13: 3642366570

DOWNLOAD EBOOK →

This handbook presents some of the most recent topics in neural information processing, covering both theoretical concepts and practical applications. The contributions include: Deep architectures Recurrent, recursive, and graph neural networks Cellular neural networks Bayesian networks Approximation capabilities of neural networks Semi-supervised learning Statistical relational learning Kernel methods for structured data Multiple classifier systems Self organisation and modal learning Applications to content-based image retrieval, text mining in large document collections, and bioinformatics This book is thought particularly for graduate students, researchers and practitioners, willing to deepen their knowledge on more advanced connectionist models and related learning paradigms.

Content-Based Image and Video Retrieval

Content-Based Image and Video Retrieval PDF

Author: Oge Marques

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 189

ISBN-13: 1461509874

DOWNLOAD EBOOK →

Content-Based Image And Video Retrieval addresses the basic concepts and techniques for designing content-based image and video retrieval systems. It also discusses a variety of design choices for the key components of these systems. This book gives a comprehensive survey of the content-based image retrieval systems, including several content-based video retrieval systems. The survey includes both research and commercial content-based retrieval systems. Content-Based Image And Video Retrieval includes pointers to two hundred representative bibliographic references on this field, ranging from survey papers to descriptions of recent work in the area, entire books and more than seventy websites. Finally, the book presents a detailed case study of designing MUSE–a content-based image retrieval system developed at Florida Atlantic University in Boca Raton, Florida.

Proceedings of the International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2013

Proceedings of the International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2013 PDF

Author: Suresh Chandra Satapathy

Publisher: Springer Science & Business Media

Published: 2013-10-05

Total Pages: 553

ISBN-13: 3319029312

DOWNLOAD EBOOK →

This volume contains the papers presented at the Second International Conference on Frontiers in Intelligent Computing: Theory and Applications (FICTA-2013) held during 14-16 November 2013 organized by Bhubaneswar Engineering College (BEC), Bhubaneswar, Odisha, India. It contains 63 papers focusing on application of intelligent techniques which includes evolutionary computation techniques like genetic algorithm, particle swarm optimization techniques, teaching-learning based optimization etc for various engineering applications such as data mining, Fuzzy systems, Machine Intelligence and ANN, Web technologies and Multimedia applications and Intelligent computing and Networking etc.

Content-Based Image Retrieval

Content-Based Image Retrieval PDF

Author: Vipin Tyagi

Publisher: Springer

Published: 2018-01-15

Total Pages: 378

ISBN-13: 9811067597

DOWNLOAD EBOOK →

The book describes several techniques used to bridge the semantic gap and reflects on recent advancements in content-based image retrieval (CBIR). It presents insights into and the theoretical foundation of various essential concepts related to image searches, together with examples of natural and texture image types. The book discusses key challenges and research topics in the context of image retrieval, and provides descriptions of various image databases used in research studies. The area of image retrieval, and especially content-based image retrieval (CBIR), is a very exciting one, both for research and for commercial applications. The book explains the low-level features that can be extracted from an image (such as color, texture, shape) and several techniques used to successfully bridge the semantic gap in image retrieval, making it a valuable resource for students and researchers interested in the area of CBIR alike.

Content Based Image Retrieval with Bag of Visual Words

Content Based Image Retrieval with Bag of Visual Words PDF

Author: Anindita Mukherjee

Publisher: Mohammed Abdul Sattar

Published: 2024-01-23

Total Pages: 0

ISBN-13:

DOWNLOAD EBOOK →

Content based image retrieval (CBIR) has become a popular area of research for both computer vision and multimedia communities. It aims at organizing digital picture archives by analyzing their visual contents. CBIR techniques make use of these visual contents to retrieve in response to any particular query. Note that this differs from traditional retrieval systems based on keywords to search images. Due to widespread variations in the images of standard image databases, achieving high precision and recall for retrieval remains a challenging task. In the recent past, many CBIR algorithms have applied Bag of Visual Words (BoVW) for modeling the visual contents of images. Though BoVW has emerged as a popular image content descriptor, it has some important limitations which can in turn adversely affect the retrieval performance. Image retrieval has many applications in diverse fields including healthcare, biometrics, digital libraries, historical research and many more (da Silva Torres and Falcao, 2006). In the retrieval system, two kinds of approaches are mainly followed, namely, Text-Based Image Retrieval (TBIR) and Content-Based Image Retrieval (CBIR). The former approach requires a lot of hu- man effort, and time and perception. Content based image retrieval is a technique that enables an user to extract similar images based on a query from a database containing large number of images.The basic issue in designing a CBIR system is to select the image features that best represent the image content in a database. As a part of a CBIR system, one has to apply appropriate visual content descriptors to represent these images. A query image should be represented similarly. Then, based on some measures of similarity, a set of images would be retrieved from the avail- able image database. The relevance feedback part, which incorporates inputs from a user, can be an optional block in a CBIR system. The fundamental problem in CBIR is how to transform the visual contents into distinctive features for dissimilar images, and into similar features for images that look alike. BoVW has emerged as a popular model for representing the visual content of an image in the recent past. It tries to bridge the gap between low level visual features and high-level semantic features to some extent.

Image Retrieval and Analysis Using Text and Fuzzy Shape Features: Emerging Research and Opportunities

Image Retrieval and Analysis Using Text and Fuzzy Shape Features: Emerging Research and Opportunities PDF

Author: Sumathy, P.

Publisher: IGI Global

Published: 2018-01-05

Total Pages: 183

ISBN-13: 152253797X

DOWNLOAD EBOOK →

Multimedia information retrieval focuses on the tools of processing and searching that are applicable to the content-based management of new multimedia documents. It has recently expanded to encompass newly devised techniques that will further its performance and growing importance. Image Retrieval and Analysis Using Text and Fuzzy Shape Features: Emerging Research and Opportunities is a critical scholarly resource that explores methods and strategies related to multimedia information retrieval systems. Featuring coverage on a broad range of topics including content-based image retrieval, text-based image retrieval, fuzzy object shape features, encoding, and indexing, this book is geared towards library science specialists, information technology specialists, and researchers seeking current information on the integration of new information retrieval technologies.

Color Image Processing

Color Image Processing PDF

Author: Rastislav Lukac

Publisher: CRC Press

Published: 2018-10-03

Total Pages: 622

ISBN-13: 1420009788

DOWNLOAD EBOOK →

Color Image Processing: Methods and Applications embraces two decades of extraordinary growth in the technologies and applications for color image processing. The book offers comprehensive coverage of state-of-the-art systems, processing techniques, and emerging applications of digital color imaging. To elucidate the significant progress in specialized areas, the editors invited renowned authorities to address specific research challenges and recent trends in their area of expertise. The book begins by focusing on color fundamentals, including color management, gamut mapping, and color constancy. The remaining chapters detail the latest techniques and approaches to contemporary and traditional color image processing and analysis for a broad spectrum of sophisticated applications, including: Vector and semantic processing Secure imaging Object recognition and feature detection Facial and retinal image analysis Digital camera image processing Spectral and superresolution imaging Image and video colorization Virtual restoration of artwork Video shot segmentation and surveillance Color Image Processing: Methods and Applications is a versatile resource that can be used as a graduate textbook or as stand-alone reference for the design and the implementation of various image and video processing tasks for cutting-edge applications. This book is part of the Digital Imaging and Computer Vision series.

Case-Based Reasoning on Images and Signals

Case-Based Reasoning on Images and Signals PDF

Author: Petra Perner

Publisher: Springer Science & Business Media

Published: 2008

Total Pages: 442

ISBN-13: 3540731784

DOWNLOAD EBOOK →

This book is the ?rst edited book that deals with the special topic of signals and images within case-based reasoning (CBR). Signal-interpreting systems are becoming increasingly popular in medical, industrial, ecological, biotechnological and many other applications. Existing statisticalandknowledge-basedtechniqueslackrobustness,accuracy,and?- ibility. New strategies are needed that can adapt to changing environmental conditions, signal variation, user needs and process requirements. Introducing CBRstrategiesintosignal-interpretingsystemscansatisfytheserequirements. CBR can be used to control the signal-processing process in all phases of a signal-interpreting system to derive information of the highest possible qu- ity. Beyond this CBR o?ers di?erent learning capabilities, for all phases of a signal-interpretingsystem,thatsatisfydi?erentneedsduringthedevelopment process of a signal-interpreting system. In the outline of this book we summarize under the term “signal” signals of 1-dimensional, 2-dimensional or 3-dimensional nature. The unique data and the necessary computation techniques require ext- ordinary case representations, similarity measures and CBR strategies to be utilised. Signalinterpretation(1D,2D,or3Dsignalinterpretation)istheprocessof mapping the numerical representation of a signal into logical representations suitable for signal descriptions. A signal-interpreting system must be able to extract symbolic features from the raw data e.g., the image (e.g., irregular structure inside the nodule, area of calci?cation, and sharp margin). This is a complex process; the signal passes through several general processing steps before the ?nal symbolic description is obtained. The structure of the book is divided into a theoretical part and into an application-oriented part.