Semantic Content-Based Retrieval for Video Documents

2011 ◽  
pp. 165-200 ◽  
Author(s):  
Lilac Al-Safadi ◽  
Janusz Getta
Keyword(s):  
Video Retrieval ◽  
Semantic Content ◽  
Research Area ◽  
Query Languages ◽  
Video Data ◽  
Digital Television ◽  
Video Information ◽  
Standard Text ◽  
Multimedia Technologies ◽  
Video Documents

The advancement of multimedia technologies has enabled electronic processing of information to be recorded in formats that are different from the standard text format. These include image, audio and video formats. The video format is a rich and expressive form of media used in many areas of our everyday life, such as in education, medicine and engineering. The expressiveness of video documents is the main reason for their domination in future information systems. Therefore, effective and efficient access to video information that supports video-based applications has become a critical research area. This has led to the development of, for example, new digitizing and compression tools and technology, video data models and query languages, video data management systems and video analyzers. With applications of a vast amount of stored video data, such as news archives and digital television, video retrieval became, and still is, an active area of research.

Semantic Content-Based Retrieval for Video Documents

2011 ◽  
pp. 89-135
Author(s):  
Lilac Al-Safadi ◽  
Janusz Getta
Keyword(s):  
Video Retrieval ◽  
Semantic Content ◽  
Research Area ◽  
Query Languages ◽  
Video Data ◽  
Digital Television ◽  
Video Information ◽  
Standard Text ◽  
Multimedia Technologies ◽  
Video Documents

The advancement of multimedia technologies has enabled electronic processing of information to be recorded in formats that are different from the standard text format. These include image, audio and video formats. The video format is a rich and expressive form of media used in many areas of our everyday life, such as in education, medicine and engineering. The expressiveness of video documents is the main reason for their domination in future information systems. Therefore, effective and efficient access to video information that supports video-based applications has become a critical research area. This has led to the development of, for example, new digitizing and compression tools and technology, video data models and query languages, video data management systems and video analyzers. With applications of a vast amount of stored video data, such as news archives and digital television, video retrieval became, and still is, an active area of research.

A Content-Driven System Architecture for Tackling Automatic Cataloging of Animated Movie Databases

2012 ◽  
pp. 101-123
Author(s):  
Bogdan Ionescu ◽  
Alexandru Marin ◽  
Patrick Lambert ◽  
Didier Coquin ◽  
Constantin Vertan
Keyword(s):  
Interactive Video ◽  
Video Retrieval ◽  
Semantic Content ◽  
Detection Methods ◽  
Temporal Segmentation ◽  
Video Information ◽  
Driven System ◽  
Linguistic Approach ◽  
Content Annotation ◽  
Fuzzy Linguistic

This article discusses content-based access to video information in large video databases and particularly, to retrieve animated movies. The authors examine temporal segmentation, and propose cut, fade and dissolve detection methods adapted to the constraints of this domain. Further, the authors discuss a fuzzy linguistic approach for deriving automatic symbolic/semantic content annotation in terms of color techniques and action content. The proposed content descriptions are then used with several data mining techniques (SVM, k-means) to automatically retrieve the animation genre and to classify animated movies according to some color techniques. The authors integrate all the previous techniques to constitute a prototype client-server architecture for a 3D virtual environment for interactive video retrieval.

Constructing and Utilizing Video Ontology for Accurate and Fast Retrieval

2011 ◽  
Vol 2 (4) ◽  
pp. 59-75 ◽  
Author(s):  
Kimiaki Shirahama ◽  
Kuniaki Uehara
Keyword(s):  
Knowledge Base ◽  
Large Scale ◽  
Video Retrieval ◽  
Computational Cost ◽  
Semantic Content ◽  
Video Data ◽  
Experimental Results ◽  
Huge Number ◽  
Dempster Shafer Theory ◽  
Shafer Theory

This paper examines video retrieval based on Query-By-Example (QBE) approach, where shots relevant to a query are retrieved from large-scale video data based on their similarity to example shots. This involves two crucial problems: The first is that similarity in features does not necessarily imply similarity in semantic content. The second problem is an expensive computational cost to compute the similarity of a huge number of shots to example shots. The authors have developed a method that can filter a large number of shots irrelevant to a query, based on a video ontology that is knowledge base about concepts displayed in a shot. The method utilizes various concept relationships (e.g., generalization/specialization, sibling, part-of, and co-occurrence) defined in the video ontology. In addition, although the video ontology assumes that shots are accurately annotated with concepts, accurate annotation is difficult due to the diversity of forms and appearances of the concepts. Dempster-Shafer theory is used to account the uncertainty in determining the relevance of a shot based on inaccurate annotation of this shot. Experimental results on TRECVID 2009 video data validate the effectiveness of the method.

scholarly journals Retrieval of Video Contents based on Deep Parameter Analysis using Machine Learning

2019 ◽  
Vol 8 (2S10) ◽  
pp. 772-779
Keyword(s):  
Moving Objects ◽  
Video Retrieval ◽  
Motion Vector ◽  
Content Management ◽  
Video Data ◽  
Parameter Analysis ◽  
Video Content ◽  
Video Information ◽  
Content Retrieval ◽  
Video Frames

In the recent past, video content-based communication hasincreases with a significant consumption of space and time complexity.The introduction of the data is exceedingly improved in video information as the video information incorporates visual and sound data. The mix of these two kinds of information for a single data portrayal is exceedingly compelling as the broad media substance can make an ever-increasing number of effects on the human cerebrum. Thus, most of the substance for training or business or restorative area are video-based substances. This development in video information have impacted a significant number of the professional to fabricate and populate video content library for their use. Hence, retrieval of the accurate video data is the prime task for all video content management frameworks. A good number of researches are been carried out in the field of video retrieval using various methods. Most of the parallel research outcomes have focused on content retrieval based on object classification for the video frames and further matching the object information with other video contents based on the similar information. This method is highly criticised and continuously improving as the method solely relies on fundamental object detection and classification using the preliminary characteristics. These characteristics are primarily depending on shape or colour or area of the objects and cannot be accurate for detection of similarities. Hence, this work proposes, a novel method for similarity-based retrieval of video contents using deep characteristics. The work majorly focuses on extraction of moving objects, static objects separation, motion vector analysis of the moving objects and the traditional parameters as area from the video contents and further perform matching for retrieval or extraction of the video data. The proposed novel algorithm for content retrieval demonstrates 98% accuracy with 90% reduction in time complexity.

Constructing and Utilizing Video Ontology for Accurate and Fast Retrieval

2013 ◽  
pp. 226-242
Author(s):  
Kimiaki Shirahama ◽  
Kuniaki Uehara
Keyword(s):  
Knowledge Base ◽  
Large Scale ◽  
Video Retrieval ◽  
Computational Cost ◽  
Semantic Content ◽  
Video Data ◽  
Experimental Results ◽  
Query By Example ◽  
Dempster Shafer Theory ◽  
Shafer Theory

This paper examines video retrieval based on Query-By-Example (QBE) approach, where shots relevant to a query are retrieved from large-scale video data based on their similarity to example shots. This involves two crucial problems: The first is that similarity in features does not necessarily imply similarity in semantic content. The second problem is an expensive computational cost to compute the similarity of a huge number of shots to example shots. The authors have developed a method that can filter a large number of shots irrelevant to a query, based on a video ontology that is knowledge base about concepts displayed in a shot. The method utilizes various concept relationships (e.g., generalization/specialization, sibling, part-of, and co-occurrence) defined in the video ontology. In addition, although the video ontology assumes that shots are accurately annotated with concepts, accurate annotation is difficult due to the diversity of forms and appearances of the concepts. Dempster-Shafer theory is used to account the uncertainty in determining the relevance of a shot based on inaccurate annotation of this shot. Experimental results on TRECVID 2009 video data validate the effectiveness of the method.

scholarly journals Large-Scale Video Retrieval via Deep Local Convolutional Features

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Chen Zhang ◽  
Bin Hu ◽  
Yucong Suo ◽  
Zhiqiang Zou ◽  
Yimu Ji
Keyword(s):  
Large Scale ◽  
Video Retrieval ◽  
Video Data ◽  
Query Image ◽  
Key Frame Extraction ◽  
Key Frame ◽  
Storage Cost ◽  
Extraction Algorithm ◽  
Feature Aggregation ◽  
And Storage

In this paper, we study the challenge of image-to-video retrieval, which uses the query image to search relevant frames from a large collection of videos. A novel framework based on convolutional neural networks (CNNs) is proposed to perform large-scale video retrieval with low storage cost and high search efficiency. Our framework consists of the key-frame extraction algorithm and the feature aggregation strategy. Specifically, the key-frame extraction algorithm takes advantage of the clustering idea so that redundant information is removed in video data and storage cost is greatly reduced. The feature aggregation strategy adopts average pooling to encode deep local convolutional features followed by coarse-to-fine retrieval, which allows rapid retrieval in the large-scale video database. The results from extensive experiments on two publicly available datasets demonstrate that the proposed method achieves superior efficiency as well as accuracy over other state-of-the-art visual search methods.

Reader service experience system of intelligent library based on artificial intelligence and machine learning

2021 ◽  
pp. 1-11
Author(s):  
Wang Songyun
Keyword(s):  
Digital Library ◽  
Clustering Algorithm ◽  
Service System ◽  
Video Retrieval ◽  
Social Economy ◽  
Video Data ◽  
Software Requirements ◽  
Library Service ◽  
The Times ◽  
Video Recovery

With the development of social economy and the improvement of science and technology, digital video on the Internet is increasing rapidly, and it has become a new force to promote the development of the times. Most of these videos are stored in the memory, which poses a great challenge to the research and development of the system. The reader service system is an important part of library service. The library uses it to collect information resources, not just for service and work. The document combines the video of library service, the analysis of video recovery and video software requirements of digital library, puts forward the design goal and conception of video search, and puts forward a foundation. From the video data of digital library, video retrieval experiments are gradually carried out. These experimental results show that the number of enhanced dynamic clustering algorithm increases to ensure the complexity of the image.

scholarly journals Devising a conceptual method for generating cryptocompression codograms of images without loss of information quality

2021 ◽  
Vol 4 (2(112)) ◽  
pp. 6-17
Author(s):  
Vladimir Barannik ◽  
Serhii Sidchenko ◽  
Dmitriy Barannik ◽  
Sergii Shulgin ◽  
Valeriy Barannik ◽  
...  
Keyword(s):  
Information Quality ◽  
Dynamic Range ◽  
Video Data ◽  
Service Component ◽  
Loss Of Information ◽  
Video Information ◽  
Information Components ◽  
Service Data ◽  
Processing Steps ◽  
Better Than

Along with the widespread use of digital images, an urgent scientific and applied issue arose regarding the need to reduce the volume of video information provided it is confidential and reliable. To resolve this issue, cryptocompression coding methods could be used. However, there is no method that summarizes all processing steps. This paper reports the development of a conceptual method for the cryptocompression coding of images on a differentiated basis without loss of information quality. It involves a three-stage technology for the generation of cryptocompression codograms. The first two cascades provide for the generation of code structures for information components while ensuring their confidentiality and key elements as a service component. On the third cascade of processing, it is proposed to manage the confidentiality of the service component. The code values for the information components of nondeterministic length are derived out on the basis of a non-deterministic number of elements of the source video data in a reduced dynamic range. The generation of service data is proposed to be organized in blocks of initial images with a dimension of 16×16 elements. The method ensures a decrease in the volume of source images during the generation of cryptocompression codograms, by 1.14–1.58 times (12–37 %), depending on the degree of their saturation. This is 12.7‒23.4 % better than TIFF technology and is 9.6‒17.9 % better than PNG technology. The volume of the service component of cryptocompression codograms is 1.563 % of the volume of the source video data or no more than 2.5 % of the total code stream. That reduces the amount of data for encryption by up to 40 times compared to TIFF and PNG technologies. The devised method does not introduce errors into the data in the coding process and refers to methods without loss of information quality.

scholarly journals A Distributed Content-Based Video Retrieval System for Large Data-sets

2021 ◽  
Author(s):  
ElMehdi SAOUDI ◽  
Said Jai Andaloussi
Keyword(s):  
Real Time ◽  
Retrieval System ◽  
Video Retrieval ◽  
Multimedia Databases ◽  
Video Data ◽  
Multimedia Data ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Data Set ◽  
Content Based Video Retrieval

Abstract With the rapid growth of the volume of video data and the development of multimedia technologies, it has become necessary to have the ability to accurately and quickly browse and search through information stored in large multimedia databases. For this purpose, content-based video retrieval ( CBVR ) has become an active area of research over the last decade. In this paper, We propose a content-based video retrieval system providing similar videos from a large multimedia data-set based on a query video. The approach uses vector motion-based signatures to describe the visual content and uses machine learning techniques to extract key-frames for rapid browsing and efficient video indexing. We have implemented the proposed approach on both, single machine and real-time distributed cluster to evaluate the real-time performance aspect, especially when the number and size of videos are large. Experiments are performed using various benchmark action and activity recognition data-sets and the results reveal the effectiveness of the proposed method in both accuracy and processing time compared to state-of-the-art methods.

scholarly journals A method for reducing information redundancy of digital images for cloud storage

Connectivity ◽  
2020 ◽  
Vol 148 (6) ◽  
Author(s):  
Yu. I. Katkov ◽  
◽  
O. S. Zvenigorodsky ◽  
O. V. Zinchenko ◽  
V. V. Onyshchenko ◽  
...  
Keyword(s):  
Image Compression ◽  
Video Compression ◽  
Cloud Storage ◽  
Video Data ◽  
Information Redundancy ◽  
High Quality ◽  
Video Information ◽  
Quality Video ◽  
High Quality Video

The article is devoted to the topical issue of finding new effective and improving existing widespread compression methods in order to reduce computational complexity and improve the quality of image-renewable image compression images, is important for the introduction of cloud technologies. The article presents a problem To increase the efficiency of cloud storage, it is necessary to determine methods for reducing the information redundancy of digital images by fractal compression of video content, to make recommendations on the possibilities of applying these methods to solve various practical problems. The necessity of storing high-quality video information in new HDTV formats 2k, 4k, 8k in cloud storage to meet the existing needs of users has been substantiated. It is shown that when processing and transmitting high quality video information there is a problem of reducing the redundancy of video data (image compression) provided that the desired image quality is preserved, restored by the user. It has been shown that in cloud storage the emergence of such a problem is historically due to the contradiction between consumer requirements for image quality and the necessary volumes and ways to reduce redundancy of video data, which are transmitted over communication channels and processed in data center servers. The solution to this problem is traditionally rooted in the search for effective technologies for compressing, archiving and compressing video information. An analysis of video compression methods and digital video compression technology has been performed, which reduces the amount of data used to represent the video stream. Approaches to image compression in cloud storage under conditions of preservation or a slight reduction in the amount of data that provide the user with the specified quality of the restored image are shown. Classification of special compression methods without loss and with information loss is provided. Based on the analysis, it is concluded that it is advisable to use special methods of compression with loss of information to store high quality video information in the new formats HDTV 2k, 4k, 8k in cloud storage. The application of video image processing and their encoding and compression on the basis of fractal image compression is substantiated. Recommendations for the implementation of these methods are given.

Sign in / Sign up

Export Citation Format

Share Document