Content-Based Information Retrieval (CBIR)

Image features play a vital role in image retrieval. This chapter presents the use of Zernike moment features for retrieving the binary and gray level images from established image databases. To retrieve a set of similar category of images from an image database, up to 25 Zernike moment features from order zero to order 8 were utilized and exp erimented in this chapter. A total of 1400 binary images from MPEG-7 dataset and 1440 images from a COIL-20 dataset were used to evaluate the capability of Zernike moments features for image retrieval. The exp erimental results show that Zernike moments implementation is suitable for image retrieval due to rotation invariance and fast computation.

On-line keyword searching from documents in Chinese tends to use inverted indexing as the main technique, which has its difficulties. Suffix Array is widely used for processing text in Western languages. However, it fails to get widely used in Chinese processing because of the speciality of Chinese. Suffix Array is a powerful tool. However it costs too much space. That is the major bottleneck of suffix Array. A data
structure called Keyword-driven Suffix Array is proposed in this paper for on-line keyword searching from documents in Chinese, based on observation of on-line search pattern and traits of Chinese. Space efficiency is improved a lot using this data structure. When the document database is large enough, space efficiency is improved by about 5/6 using this data structure without sacrificing its time efficiency.

Abstract:-A fuzzy approach to color quantization and its application in content-based image indexing and retrieval is presented in this paper. There are some drawbacks associated with traditional color histogram such as color quantization. The goal in this paper is to develop an effective method to overcome several limitations, which are related to traditional color histogram. In the proposed method, fuzzy logic is used to quantize color space and apply it in color histogram construction.

Deep learning and image processing are two areas of great interest to academics and industry professionals alike. The areas of application of these two disciplines range widely, encompassing fields such as medicine, robotics, and security and surveillance. The aim of this book, 'Deep Learning for Image Processing Applications', is to offer concepts from these two areas in the same platform, and the book brings together the shared ideas of professionals from academia and research about problems and solutions relating to the multifaceted aspects of the two disciplines. The first chapter provides an introduction to deep learning, and serves as the basis for much of what follows in the subsequent chapters, which cover subjects including: the application of deep neural networks for image classification; hand gesture recognition in robotics; deep learning techniques for image retrieval; disease detection using deep learning techniques; and the comparative analysis of deep data and big data. The book will be of interest to all those whose work involves the use of deep learning and image processing techniques

Scope of the book:
This book focusses on the technical concepts of deep learning and its associated branch Neural Networks for the various dimensions of image processing applications. The proposed volume intends to bring together researchers to report the latest results or progress in the development of the above-mentioned areas. Since there is a deficit of books on this specific subject matter, the editors aim to provide a common platform for researchers working in this area to exhibit their novel findings.
Topics of Interest:
This book solicits contributions, which include the fundamentals in the field of Deep Artificial Neural Networks and Image Processing supported by case studies and practical examples. Each chapter is expected to be self-contained and to cover an in-depth analysis of real life applications of neural networks to image analysis.

The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide variability, and video input is of low quality. At the centre of focus are face appearance manifolds: this thesis presents a significant advance of their understanding and application in the sphere of face recognition. The two main contributions are the Generic Shape-Illumination Manifold recognition algorithm and the Anisotropic Manifold Space clustering.

The Generic Shape-Illumination Manifold algorithm shows how video sequences of unconstrained head motion can be reliably compared in the presence of greatly changing imaging conditions. Our approach consists of combining a priori domain-specific knowledge in the form of a photometric model of image formation, with a statistical model of generic face appearance variation. One of the key ideas is the reillumination algorithm which takes two sequences of faces and produces a third, synthetic one, that contains the same poses as the first in the illumination of the second.

The Anisotropic Manifold Space clustering algorithm is proposed to automatically determine the cast of a feature-length film, without any dataset-specific training information. The method is based on modelling coherence of dissimilarities between appearance manifolds: it is shown how inter- and intra-personal similarities can be exploited by mapping each manifold into a single point in the manifold space. This concept allows for a useful interpretation of classical clustering approaches, which highlights their limitations. A superior method is proposed that uses a mixture-based generative model to hierarchically grow class boundaries corresponding to different individuals.

The Generic Shape-Illumination Manifold is evaluated on a large data corpus acquired in real-world conditions and its performance is shown to greatly exceed that of state-of-the-art methods in the literature and the best performing commercial software. Empirical evaluation of the Anisotropic Manifold Space clustering on a popular situation comedy is also described with excellent preliminary results.

This article summarizes the research on computational methods to detect academic plagiarism by systematically reviewing 239 research papers published between 2013 and 2018. To structure the presentation of the research contributions, we propose novel technically oriented typologies for plagiarism prevention and detection efforts, the forms of academic plagiarism, and computational plagiarism detection methods. We show that academic plagiarism detection is a highly active research field. Over the period we review, the field has seen major advances regarding the automated detection of strongly obfuscated and thus hard-to-identify forms of academic plagiarism. These improvements mainly originate from better semantic text analysis methods , the investigation of non-textual content features, and the application of machine learning. We identify a research gap in the lack of methodologically thorough performance evaluations of plagiarism detection systems. Concluding from our analysis, we see the integration of heterogeneous analysis methods for tex-tual and non-textual content features using machine learning as the most promising area for future research contributions to improve the detection of academic plagiarism further.

With the increasingly growing size of digital image collections, known image search is gaining more and more importance. Especially when the objects in such collections do not possess appropriate metadata (e.g., tags, annotations), content-based image retrieval (CBIR) is a promising approach. However, the application of CBIR to known item search usually suffers from the unavailability of query images that are good enough to express the user's information need. In order to improve this situation, we propose the QbS system which provides an approach to content-based search in large image collections based on user-drawn sketches. By exploiting novel devices for human-computer interaction like interactive paper, tablet PCs, or graphic tablets, users are able to draw a sketch that reflects their information need and start a content-based search using this sketch. The QbS system provides query support and offers several invariances that allow the user-generated sketch to slightly deviate from the searched image in terms of rotation, translation, relative size, and/or unknown objects in the background. To illustrate the benefits of the approach, we show search results from the evaluation of QbS on the basis of the MIRFLICKR collection with 25'000 objects.

Существует широкий круг задач, где требуется анализ, аудио-визуальных моделей реальности. В частности, для многих военных и гражданских приложений, необходимо наличие поиска нечетких дубликатов видео. Для мирного применения, — это группировка подсказок в выдаче поисковиков, поиск неправомерных публикаций видеофайлов, сокращение объема хранимой и передаваемой информации. Для военного применения можно тоже перечислить несколько вариантов.

This article summarizes the research on computational methods to detect academic plagiarism by systematically reviewing 239 research papers published between 2013 and 2018. To structure the presentation of the research contributions, we propose novel technically oriented typologies for plagiarism prevention and detection efforts, the forms of academic plagiarism, and computational plagiarism detection methods. We show that academic plagiarism detection is a highly active research field. Over the period we review, the field has seen major advances regarding the automated detection of strongly obfuscated and thus hard-to-identify forms of academic plagiarism. These improvements mainly originate from better semantic text analysis methods, the investigation of non-textual content features, and the application of machine learning. We identify a research gap in the lack of methodologically thorough performance evaluations of plagiarism detection systems. Concluding from our analysis, we s...

Most news organizations provide immediate access to topical news broadcasts through RSS streams or podcasts. Until recently, applications have not permitted a user to perform content based search within a longer spoken broadcast to find the segment that might interest them. Recent progress in both automatic speech recognition (ASR) and natural language processing (NLP) has produced robust tools that allow us to now provide users with quicker and more focused access to relevant segments of news broadcast videos. Our public online demonstrator of the Voxalead application currently indexes daily broadcast news content from 50 sources in English, French, Chinese, Arabic, Spanish, Dutch, Italian and Russian.

Data available on the web is growing at an exponential rate, creating Knowledge or extracting information is of paramount importance. Information Retrieval (IR) plays a crucial role in Knowledge management as it helps us to find the relevant information from the existing data. This paper compares the performance of keyword-based retrieval and other architectural styles in information retrieval system with ontology-based retrieval on documents in regional language

The purpose of this report is to describe research and solution to the problem of designing a Content Based Image Retrieval, CBIR system. It outlines the problem, the proposed solution, the final solution and the accomplishments achieved. Due to the enormous increase in image database sizes, as well as its vast deployment in various applications, the need for CBIR development arose. Firstly, this report outlines a description of the primitive features of an image; texture, colour, and shape. These features are extracted and used as the basis for a similarity check between images. The algorithms used to calculate the similarity between extracted features, are then explained. Our final result was a MatLab built software application, with an image database, that utilized texture and colour features of the images in the database as the basis of comparison and retrieval. The structure of the final software application is illustrated. Furthermore, the results of its performance are illustrated by a detailed example.
Keywords: Content Based Image Retrieval(CBIR), Similarity, Features and Image Database.

The development of content based retrieval mechanisms is a very active
research area. Present studies are mainly focused on automating the information
extraction and indexing processes. Usually for the development and evaluation of such
mechanisms there is always a need for a ground-truth database. In this paper we present a
software tool named qp that is able to semi-automatically produce a collection of random
3D vessels, with morphological characteristics similar to those found in ancient Greek
pottery, a ceramic group exhibited worldwide with great impact to scholars as well as
general public. A 3D vessel collection has been produced by qp and can be used as a test
bed dataset for the development of shape-based 3D descriptors applicable to pottery.
Additionally, qp can be considered as a 3D vessel modelling software tool which can be
used by people not related to computer graphics technology and particularly to 3D
modelling.

The paper focuses on an approach to a near-duplicate videos search. The search is based on the comparison of scene relative lengths in the space L2. The comparison is made with Gale-Church hypothesis. The concept "shot descriptor" was introduced. To speed up the performance of this method, semantic hashing was suggested, i.e. a generalization of locally sensitive hashing. 

В работе рассмотрен подход для поиска нечетких дубликатов видео. Поиск основан на сравнении относительных длин сцен в пространстве L2. Сравнение проводится с учетом гипотезы Гейла-Черча. Вводится понятие «дескриптора сцены». Для ускорения работы метода предложено использовать семантическое хеширование, обобщение локально чувствительного хеширования.

This Master project aimed at studying, analyzing and developing relevance feedback (RF) techniques to enhance similarity queries that employ the content-based image retrieval (CBIR) approach. The motivation to  develop this project came from the iRIS (internet Retrieval of Images System), which is a Web server prototype to process similarity queries. The iRIS can be integrated to a PACS (Picture and Archiving and Communication System) adding the functionality of retrieval images comparing their inherent alikeliness. The main reservation about using CBIR techniques is the semantic gap, because the general use of low level features to describe the images. The low level features, such as color, texture and shape, mostly cannot bridge the gap between what the users expect/want to what they get, generating disappointment and refusal of employing the system. However, if the user is allowed to interact with the system, classifying the query results and using such information on refinement steps, the queries can be reprocessed and the results tend to comply with the users’ expectation. This is just the core of the relevance feedback techniques. Looking at this scenario, this project developed two relevance feedback (RF) techniques: the RF Projection and the RF Multiple Point Projection. The improvements on the similarity queries were expressive going to up 29% with only one interaction, and to 42% on the fifth interaction, when compared to the original query. Experiments performed with users, have shown us that in average they run 3 iterations before get satisfactory results. By the results given by the experiment, one can claim that RF is a powerful approach to improve the use of CBIR systems and enhance similarity queries.

The rapid growth of the worldwide web poses unprecedented scaling challenges for general-purpose crawlers and search engines. In this paper we describe a new hypertext information management system called a Focused Crawler. The goal of a focused crawler is to selectively seek out pages that are relevant to a pre-defined set of topics. The topics are specified not using keywords, but using exemplary documents. Rather than collecting and indexing all accessible hypertext documents to be able to answer all possible ad-hoc queries, a focused crawler analyzes its crawl boundary to find the links that are likely to be most relevant for the crawl. It avoids irrelevant regions of the web. This leads to significant savings in hardware and network resources, and helps keep the crawl more up-to-date. We describe a prototype implementation that is comprised of three programs integrated via a re-lational database: a crawler that stores metadata for documents and links in relational tables and is guided by various attributes in these tables, a hypertext classifier that updates the metadata with topic information from a large taxonomy (such as Yahoo!), and a rating system that updates metadata fields signifying the value of a page as a access point for a large number of relevant pages. The two " mining " modules guide the crawler away from unnecessary exploration and focus its efforts on web regions of interest. We report on extensive focused-crawling experiments using several topics at different levels of speci-ficity. Focused crawling acquires relevant pages steadily while standard crawling quickly loses its way, even though they are started from the same root set. Focused crawling is robust against large perturbations in the starting set of URLs. It discovers largely overlapping sets of resources in spite of these perturbations. It is also capable of exploring out and discovering valuable resources that are dozens of links away from the start set, while carefully pruning the millions of pages that may lie within this same radius. Our anecdotes suggest that focused crawling is very effective for building high-quality collections of web documents on specific topics, using modest desktop hardware.

This paper presents an alternative approach for Content Based Image Retrieval (CBIR) using Scale Invariant Feature Transform (SIFT) algorithm for binary and gray scale images. The motivation to use SIFT algorithm for CBIR is due to the fact that SIFT is invariant to scale, rotation and translation as well as partially invariant to affine distortion and illumination changes. Inspired by these facts, this paper investigates the fundamental properties of SIFT for robust CBIR by using MPEG-7, COIL-20 and ZuBuD image databases. Our approach uses detected keypoints and its descriptors to match between the query images and images from the database. Our experimental results show that the proposed CBIR using SIFT algorithm producing excellent retrieval result for images with many corners as compared to retrieving image with less corners.

Searching Test Image from Image databases using features extraction from the content is currently an active research area. In this work we present novel feature extraction approaches for content-based image retrieval when the query image is color image. To facilitate robust man-machine interfaces, we accept query images with color attributes. Special attention is given to the similarity measure with different distance matrices properties since the Test Image and Object Image from database finding the distance measuring. Several applicable techniques within the literature are studied for these conditions. The goal is to present the user with a subset of images that are more similar to the Object Image. One of the most important aspects of the proposed methods is that the accuracy measurement of the different database images. This significantly improves the feature extraction process and enables the methods to be used for other computer vision applications.

https://sites.google.com/site/ijcsis/

CBIR is a very important domain, especially in the
last decade due to the increased need for image retrieval
from the multimedia database. In general, we extract low
level (color, texture, and shape) or high-level features (when
we include machine learning techniques) from the images. In
our work, we proposed a new CBIR system using Local
Neighbor Pattern (LNP) with supervised machine learning
techniques. We evaluated the performance of this system by
comparing the system with Local Tetra Pattern (LTrP) using
Corel 1k, Vistex and TDF face databases. We used three
types of the database (i.e color, texture and face databases) to
improve the effectiveness of our system. Performance
analysis shows that LNP gives better performance regarding
the average recall than LBP, LDP, and LTrP. To increase
the accuracy of this system we used the LNP method with
machine learning techniques and performance analysis
shows that local pattern with machine learning techniques
improves the average accuracy from 36.23% to 85.60% when
we use LNP with cubic SVM on DB1 (Corel1K), and from
82.51% to 99.50 % when we use LNP with fine KNN on DB2
(Vistex DB), and from 56.63% to 95% when we use LNP with
ensemble subspace discriminant on DB3 (face DB).

Image content on the Web is increasing exponentially. As a result, there is a need for image retrieval systems. Historically, there have been two methodologies, text-based and content-based. In the text-based approach, query systems retrieve images that have been manually annotated using key words. This approach can be problematic: it is labor-intensive and maybe biased according to the subjectivity of the observer. Content based image retrieval (CBIR) searches and retrieves digital images in large databases by analysis of derived-image features. CBIR systems typically use the characteristics of color, texture, shape and their combination for definition of features. Similarity measures that originated in the preceding text-based era are commonly used. However, CBIR struggles with bridging the semantic gap, defined as the division between high-level complexity of CBIR and human perception and the low-level implementation features and techniques. In this paper, CBIR is reviewed in a broad context. Newer approaches is feature generation and similarity measures are detailed with representative studies addressing their efficacy. Color-texture moments, columns-of-interest, harmonysymmetry-geometry, SIFT (Scale Invariant Feature Transform), and SURF (Speeded Up Robust Features) are presented as alternative feature generation modalities. Graph
matching, Earth Mover’s Distance, and relevance feedback are discussed with the realm of similarity. We conclude that while CBIR is evolving and continues to slowly close the semantic gap, addressing the complexity of human perception remains a challenge.

Grey Level Co-occurrence Matrices (GLCM) are one of the earliest techniques used for image texture analysis. In this paper we defined a new feature called trace extracted from the GLCM and its implications in texture analysis are discussed in the context of Content Based Image Retrieval (CBIR). The theoretical extension of GLCM to n-dimensional gray scale images are also discussed. The results indicate that trace features outperform Haralick features when applied to CBIR.

This paper provides a mining approach to the research area of relevance feedback (RF) in content-based image retrieval (CBIR). Relevance feedback is a powerful technique in CBIR systems, in order to improve the performance of CBIR effectively. The drawbacks in CBIR are the features of the query image and the semantic gap between low-level features and high level concepts. Especially, Mining Image data is the one of the essential features in this present scenario since image data plays vital role in every aspect of the system such as business for marketing, hospital for surgery, engineering for construction, Web for publication and so on. In this paper, we are proposed an adaptive approach for relevance feedback in CBIR using mining techniques. Where in the processes of feedback we are using a new technique called Image retrieval based on optimum clusters is proposed for improving user interaction with image retrieval systems by fully exploiting the similarity information. The index is created by describing the images according to their color characteristics, with compact feature vectors, that represent typical color distributions.

Abstract. Metadata vocabularies provide various semantic relations between concepts. For content-based recommender systems, these relations enable a wide range of concepts to be recommended. However, not all semantically related concepts are interesting for end users. In this paper, we identified a number of semantic relations, which are within one vocabulary (eg a concept has a broader/narrower concept) and across multiple vocabularies (eg an artist is associated to an art style). Our goal is to investigate which semantic relations are ...

Social media have become a major source of health information for lay people. It has the power to influence the public's adoption of health policies and to determine the response to the current COVID-19 pandemic. The aim of this paper is to enhance understanding of personality characteristics of users who spread information about controversial COVID-19 medical treatments on Twitter.

The paper focuses on the algorithms of the event detection in content-based video retrieval. Video has a complex structure and can express the same idea in different ways. This makes the task of searching for video more complicated. Video titles and text descriptions cannot give the whole information about objects and events in the video. This creates a need for content-based video retrieval. There is a semantic gap between low-level video features, that can be extracted, and the users’ perception. The task of event detection is reduced to the task of video segmentation. Complex content-based video retrieval can be regarded as the bridge between traditional retrieval and semantic-based video retrieval. The properties of video as a time series are described. Introduced the concept of anomalies in the video. A method for event detection based on comparing moving averages with windows of different sizes is proposed. According to the classification given at the beginning of this article, our method refers to statistical methods. It differs from other methods with low computational complexity and simplicity. The video stream processing language is proposed for function-based description of video handling algorithms. So, our method is formulated in the form of a declarative description on an interpreted programming language. Unfortunately, most of the existing video processing methods use exclusively imperative approach, which often makes understanding more difficult. Examples of the use of this language are given. Its grammar is described too. As shown by experiments, the implementation of the proposed video events retrieval method, unlike their counterparts, can work for video streams too with a real-time and potentially infinite frame sequences. Such advantages within low computational requirements make implementation of the method helpful in aviation and space technology. The algorithm has some disadvantages due to necessity parameter selection for particular task classes. The theorem on near-duplicates of video is formulated at the end of the article. It asserts the near-duplicate videos express the same sequence of phenomena.

The problem of object recognition is of immense practical importance and potential, and the last decade has witnessed a number of breakthroughs in the state of the art. Most of the past object recognition work focuses on textured objects and local appearance descriptors extracted around salient points in an image. These methods fail in the matching of smooth, untextured objects for which salient point detection does not produce robust results. The recently proposed bag of boundaries (BoB) method is the first to directly address this problem. Since the texture of smooth objects is largely uninformative, BoB focuses on describing and matching objects based on their post-segmentation boundaries. Herein we address three major weaknesses of this work. The first of these is the uniform treatment of all boundary segments. Instead, we describe a method for detecting the locations and scales of salient boundary segments. Secondly, while the BoB method uses an image based elementary descriptor (HoGs + occupancy matrix), we propose a more compact descriptor based on the local profile of boundary normals' directions. Lastly, we conduct a far more systematic evaluation, both of the bag of boundaries method and the method proposed here. Using a large public database, we demonstrate that our method exhibits greater robustness while at the same time achieving a major computational saving -- object representation is extracted from an image in only 6%  of the time needed to extract a bag of boundaries, and the storage requirement is similarly reduced to less than 8%.

the World Wide Web (WWW) is very difficult because web contains a huge number of images. To solve this problem we need a system
that can retrieve the required images needed by the user. Image Crawler is a web based tool that collects and indexes group of web
images available on the internet. This tool collects the keyword or phrase from the user to retrieve the images from the web. Then
these collected keyword is applied to the different general search tools like Google, Yahoo, Bind etc,. The collected web page
information is stored in the temporary file till 200KB file size from the server. Then this file content will be scanned and extract the
image URL’s and it is compared the URL which is present in the database to avoid the duplicate downloads. The extracted URL’s
images are downloaded and finally stores unique image and corresponding metadata like filename, url, size etc. in the database. In
this paper we present the designing of an Image crawler tool. We build a search tool which is flexible, general-purpose image search
framework and explore a directed result aggregating and removing of duplicates to achieve top results compared to other existing
search tools. Finally this resulted images are used in the Content Based Image Retrieval (CBIR) system for extracting the relevant
images need by the client using the content of the images rather than the text based information.

Content-Based Image Retrieval (CBIR) locates, retrieves and displays images alike to one given as a query, using a set of features. It demands accessible data in medical archives and from medical equipment, to infer meaning after some processing. A problem similar in some sense to the target image can aid clinicians. CBIR complements text-based retrieval and improves evidence-based diagnosis, administration, teaching, and research in healthcare. It facilitates visual/automatic diagnosis and decision-making in real-time remote consultation/screening, store-and-forward tests, home care assistance and overall patient surveillance. Metrics help comparing visual data and improve diagnostic. Specially designed architectures can benefit from the application scenario. CBIR use calls for file storage standardization, querying procedures, efficient image transmission, realistic databases, global availability, access simplicity, and Internet-based structures. This chapter recommends important and complex aspects required to handle visual content in healthcare.

Recent advances in text detection allow for finding text regions in natural scenes rather accurately. Global features in content based image retrieval, however, typically do not cover such a high level information. While haracteristics of text regions may be reflected by texture or color properties, the respective pixels are not treated in a different way. In this contribution we investigate the impact of text detection on content based image retrieval using global features. Detected text regions are preprocessed to allow for different treatment by feature extraction algorithms, and we show that for certain domains this leads to a much higher precision in content based retrieval.

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we propose a novel, general recognition framework for efficient matching of individual face images, sets or sequences. The framework is based on simple image processing filters that compete with unprocessed greyscale input to yield a single matching score between individuals. It is shown how the discrepancy between illumination conditions between novel input and the training data set can be estimated and used to weigh the contribution of two competing representations. We describe an extensive empirical evaluation of the proposed method on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our algorithm consistently demonstrated a dramatic performance improvement over traditional filtering approaches. We demonstrate a reduction of 50-75% in recognition error rates, the best performing method-filter combination correctly recognizing 96% of the individuals.

This paper presents a novel compact shape descriptor designed specifically for content-based retrieval
of complete or nearly complete 3D vessel replicas. The descriptor consists of two vectors that carry
morphological features of the vessel’s main body and appendages. The extraction of the descriptor is
based on a pose normalisation preprocessing phase which is designed for axially symmetric objects. In
order to evaluate the efficiency of the descriptor, we created a calibrated ground-truth database of 1012
3D digitised and manually modelled vessels and performed multiple query-by-example experiments.
We present the performance of our descriptor in relation to the performance of the MPEG-7 3D shape
spectrum descriptor. Additionally, a web-based 3D content-based retrieval prototype system has been
developed based on open source technologies.