Distance browsing in distributed multimedia databases

Proceedings of the 1st international workshop on Computer vision meets databases - CVDB '04, 2004

Multimedia databases get larger and larger in our days, and this trend is expected to continue in the future. There are various aspects that affect the demand for efficient database techniques to manage the flood of multimedia data, namely the increasing number of objects, the increasing complexity of objects, and the emergence of new query types. Whereas traditional indexing structures cope with large numbers of simple objects, complex multimedia objects require more sophisticated indexing techniques. In the tutorial, we discuss characteristics of multimedia data and multimedia queries including similarity range queries and k-nearest neighbor queries. The main focus is on efficient processing of k-nearest neighbor queries in various settings and includes direct k-NN search on indexes, multi-step k-NN query processing for complex distance functions and methods for high-dimensional spaces.

2014 IEEE International Congress on Big Data, 2014

The past decade has seen the rapid proliferation of low-priced devices for recording image, audio and video data in nearly unlimited quantity. Multimedia is Big Data, not only in terms of their volume, but also with respect to their heterogeneous nature. This also includes the variety of the queries to be executed. Current approaches for searching in big multimedia collections mainly rely on keywords. However, manually annotating every single object in a large collection is not feasible. Therefore, content-based multimedia retrieval-using sample objects as query input-is increasingly becoming an important requirement for dealing with the data deluge. In image databases, for instance, effective methods exploit the use of exemplary images or hand-drawn sketches as query input. In this paper, we introduce ADAM, a novel multimedia retrieval system that is tailored to large collections and that is able to support both Boolean retrieval for structured data and similarity-based retrieval for feature vectors extracted from the multimedia objects. For efficient query processing in such big multimedia data, ADAM allows the distribution of the indexed collection to multiple shards and performs queries in a MapReduce style. Furthermore, it supports a signature-based indexing strategy for similarity search that heavily reduces the query time. The efficiency of ADAM has been successfully evaluated in a content-based image retrieval application on the basis of 14 million images from the ImageNet collection.

ADBIS (Local Proceedings), 2004

In this paper we introduce the Pivoting M-tree (PM-tree), a metric access method combining M-tree with the pivot-based approach. While in M-tree a metric region is represented by a hyper-sphere, in PM-tree the shape of a metric region is determined by intersection of the hyper-sphere and a set of hyper-rings. The set of hyper-rings for each metric region is related to a fixed set of pivot objects. As a consequence, the shape of a metric region bounds the indexed objects more tightly which, in turn, significantly improves the overall efficiency of similarity search. We present basic algorithms on PM-tree and two cost models for range query processing. Finally, the PM-tree efficiency is experimentally evaluated on large synthetic as well as real-world datasets.

2009

As the volume of multimedia data available on internet is tremendously increasing, the content-based similarity search becomes a popular approach to multimedia retrieval. The most popular retrieval concept is the k nearest neighbor (kNN) search. For a long time, the kNN queries provided an effective retrieval in multimedia databases. However, as today's multimedia databases available on the web grow to massive volumes, the classic kNN query quickly loses its descriptive power. In this paper, we introduce a new similarity query type, the k distinct nearest neighbors (kDNN), which aims to generalize the classic kNN query to be more robust with respect to the database size. In addition to retrieving just objects similar to the query example, the kDNN further ensures the objects within the result have to be distinct enough, i.e. excluding near duplicates.

—Searching for digital images in large-scale multi-media database is a hard problem due to the rapid increase of the digital assets. Metric Permutation Table is an efficient data structure for large-scale multimedia indexing. This data structure is based on the Permutation-based indexing, that aims to predict the proximity between elements encoding their location with respect to their surrounding. The main constraint of the Metric Permutation Table is the indexing time. With the exponential increase of multimedia data, parallel computation is needed. Opening the GPUs to general purpose computation allows to perform parallel computation on a powerful platform. In this paper, we propose efficient indexing and searching algorithms for the Metric Permutation Table using GPU and multi-core CPU. We study the performance and efficiency of our algorithms on large-scale datasets of millions of images. Experimental results show a decrease of the indexing time while preserving the quality of the results.

2008

A main problem with the handling of multimedia databases is the navigation through and the search within the content of a database. The problem arises from the difference between the possible textual description (annotation) of the database content and its visual appearance. Overcoming the so called-semantic gap-has been in the focus of research for some time. This paper presents a new system for similarity-based browsing of multimedia databases.

… of the 2006 International Conference on …, 2006

UPnP™ (Universal Plug'n'Play) specifies standards for interaction between user interface / control devices, called Control Points, and embedded application devices, called UPnP Devices, on an IP network. UPnP includes a six layer generic protocol for IP address establishment, UPnP Device discovery, Device and Service Description retrieval, Device Control in the form of interpreted XML procedure invocation from a Control Point to a Service, Service Eventing that notifies subscribers of changes in a Service's advertised state, and Presentation for vendor-specific extensions. UPnP AV (audio-visual) specifications extend these protocols for multimedia by defining Media Server and Media Renderer Device types, along with the Content Directory Service of metadata that describe and locate available video, audio and image content. This paper examines the standard operations available for metadata creation, maintenance, browse and search, and discusses deficiencies in UPnP's SQLlike search capability. We propose a keyword-based alternative to search whose benefits include ease of use familiar to users of Web search engines, incremental refinement of query results when browsing a large database, structuring of results in a classification hierarchy, and applicability to graphical manipulation and display of results. We have built a reference implementation of this query interface that uses only established database structures such as B-trees. Our results fit readily into the distributed UPnP AV framework.

Big Data and Cognitive Computing

The indexing and retrieval of multimedia content is generally implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results, but also leads to more complex graph structures. However, graph traversal-based algorithms for similarity are quite inefficient and computationally expensive, especially for large data structures. To deliver fast and effective retrieval especially for large multimedia collections and multimedia big data, an efficient similarity algorithm for large graphs in particular is desirable. Hence, in this paper, we define a graph projection into a 2D space (Graph Code) and the corresponding algorithms for indexing and retrieval. We show that calculations in this space can be performed more efficiently than graph traversals due to the simpler processing model and the high level of parallelization. As a...

2008

Similarity search for content-based retrieval (where content can be any combination of text, image, audio/video, etc.) has gained importance in recent years, also because of the advantage of ranking the retrieved results according to their proximity to a query. However, to use similarity search in real world applications, we need to tackle the problem of huge volumes of such mixed multimedia data (e.g., coming from Web sites) and the problem of their distribution on multiple cooperating nodes. The proposed approach is being used in two running projects: SAPIR and NeP4B.In this paper we approach this problem by considering a scenario of a network of autonomous peers maintaining a local collection of metric objects (i.e., mixed mode multimedia content). This network forms a distributed Peer-to-Peer (P2P) search engine for similarity search based on the paradigm of Routing Index. Each peer in the network thus maintains both an index of its local resources and a table for every neighbor, summarizing the objects that are reachable from it. The paper presents techniques that aim to make our P2P similarity-based search system viable, trading approximate results for scalable solutions. Results of simulations that use real collections of images are discussed.

Data Engineering, 2006. ICDE' …, 2006

2001

The many successful research results in the domain of computer vision have made similarity based data retrieval techniques a promising approach. As a result, the integration of similarity based retrieval techniques of multimedia data into DBMSs is currently an active research issue. We first illustrate the importance of similarity based operations. Then, we present our image data repository model that supports similarity based operations conveniently under an object-relational database paradigm. Furthermore, we present novel similarity based operators on image tables and study their properties. Finally, based on the properties of the operators identified, we derive algebraic rules that are useful for similarity based query optimization and we introduce a cost model for an implementation of one of the major similarity based operators

Lecture Notes in Computer Science, 1998

E cient evaluation of similarity queries is one of the basic requirements for advanced multimedia applications. In this paper, we consider the relevant case where complex similarity queries are de ned through a generic language L and whose predicates refer to a single feature F. Contrary to the language level which deals only with similarity scores, the proposed evaluation process is based on distances between feature values-known spatial or metric indexes use distances to evaluate predicates. The proposed solution suggests that the index should process complex queries as a whole, thus evaluating multiple similarity predicates at a time. The exibility of our approach is demonstrated by considering three di erent similarity languages, and showing how the M-tree access method has been extended to this purpose. Experimental results clearly show that performance of the extended M-tree version is consistently better than that of state-of-the-art search algorithms.

In this paper the architecture of a distributed and scalable multimedia information retrieval system (Dsmily) is described. The system consists of hierarchically organized networked nodes and is designed to integrate existing dynamic multimedia databases. The document ranking process as well as the preselection of databases to be searched, both tasks are based on a probabilistic model for distributed retrieval.

2007

Many multimedia applications require the storage and retrieval of non-traditional data types such as audio, video and images. One important functionality required by these applications is the capability to find objects in a database that are similarto a given object. The comparison algorithms for multimedia data types are typically computationally expensive. Therefore, the performance of similarity queries can be improved significantly by reducing the number of invocations of these comparison algorithms. In this paper, we ...

ArXiv, 2013

Similarity search is critical for many database applications, including the increasingly popular online services for Content-Based Multimedia Retrieval (CBMR). These services, which include image search engines, must handle an overwhelming volume of data, while keeping low response times. Thus, scalability is imperative for similarity search in Web-scale applications, but most existing methods are sequential and target shared-memory machines. Here we address these issues with a distributed, efficient, and scalable index based on Locality-Sensitive Hashing (LSH). LSH is one of the most efficient and popular techniques for similarity search, but its poor referential locality properties has made its implementation a challenging problem. Our solution is based on a widely asynchronous dataflow parallelization with a number of optimizations that include a hierarchical parallelization to decouple indexing and data storage, locality-aware data partition strategies to reduce message passing,...