&lt;title&gt;Efficient content-based P2P image retrieval using peer content descriptions&lt;/title&gt;

Müller, Wolfgang; Eisenhardt, Martin; Henrich, Andreas

doi:10.1117/12.531184

Cited by 16 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note that this contradicts previous results reported in [15]. The surprising results in that experiments proved to be artifacts due to interaction between the replication and the data-to-peer assignment method used in [15].…”

Section: Sensitivity To Replicationcontrasting

confidence: 56%

See 1 more Smart Citation

Fast retrieval of high-dimensional feature vectors in P2P networks using compact peer data summaries

2005

Self Cite

View full text Add to dashboard Cite

The retrieval facilities of most peer-to-peer (P2P) systems are limited to queries based on a unique identifier or a small set of keywords. The techniques used for this purpose are hardly applicable for content based image retrieval (CBIR) in a P2P network. Furthermore, we will argue that the curse of dimensionality and the high communication overhead prevent the adaptation of multidimensional search trees or fast sequential scan techniques for P2P CBIR. In the present paper we will propose two compact data representations that can be distributed in a P2P network and used as the basis for a source selection. This allows for communicating with only a small fraction of all peers during query processing without deteriorating the result quality significantly. We will also present experimental results confirming our approach.

show abstract

Section: Sensitivity To Replicationcontrasting

confidence: 56%

“…The surprising results in that experiments proved to be artifacts due to interaction between the replication and the data-to-peer assignment method used in [15]. There, replication meant more images, but also much sharper clusters of interest.…”

Section: Sensitivity To Replicationmentioning

confidence: 94%

Fast retrieval of high-dimensional feature vectors in P2P networks using compact peer data summaries

2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…We feel that the Distributed IR approach is not only promising in terms of performance, but also in terms of costs that have to be paid for maintaining such a network. This new work is based on our previously published research about peer summaries for CBIR [8,6]. The paper adds more performant peer selection methods, and most importantly a strategy to progressively change the data distribution within the network such that the peers focus more concisely on areas of interest, thus enabling dramatically improved source selection.…”

Section: Introductionmentioning

confidence: 98%

Clustering-Based Source Selection for Efficient Image Retrieval in Peer-to-Peer Networks

Eisenhardt

Müller

Henrich

et al. 2006

Eighth IEEE International Symposium on Multimedia (ISM'06)

Self Cite

View full text Add to dashboard Cite

In peer-to-peer (P2P) networks, computers with equal rights form a logical (overlay) network in order to provide a common service that lies beyond the capacity of every single participant. Efficient similarity search is generally recognized as a frontier in research about P2P systems. One way to address it is using data source selection based approaches where peers summarize the data they contribute to the network, generating typically one summary per peer. When processing queries, these summaries are used to choose the peers (data sources) that are most likely to contribute to the query result. Only those data sources are contacted. There are two main contributions of this paper. We extend earlier work, adding a data source selection method for high-dimensional vector data, comparing different peer ranking schemes. More importantly, we present a method that uses progressive stepwise data exchange between peers to better each peer's summary and therefore improve the system's performance. 1

show abstract

“…Muller et al [8] have presented experiments with efficient Content Based Image Retrieval in a P2P environment, thus a P2P-CBIR system. Although according to the work, peer data summaries can be used within the retrieval process for increasing efficiency, but security aspects are ignored.…”

Section: Introductionmentioning

confidence: 99%

Optimization of encryption technique using evolutionary algorithm for protecting multimedia contents in P2P system

Shahabadkar

Pujeri

2013

2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT)

View full text Add to dashboard Cite

With the growth of usage of file sharing applications over internet, Peer-to-Peer (P2P) networking system has recently drawn attentions of the researchers for various causes right from QoS issues to Security flaws. Due to absence of any centralized administrative management in P2P system, the network becomes highly vulnerable for various types of attacks. Therefore, the current paper discusses about a novel technique that uses recurrence relation to generate number of encryption version of the multimedia content, which is further more strengthened using optimization technique. Evolutionary Algorithm is considered for optimizing the encryption process. The accomplished results are finally evaluated with respect to correlation coefficient among the adjacent pixels, key analysis, and highest entropy of frames.

show abstract

<title>Efficient content-based P2P image retrieval using peer content descriptions</title>

Cited by 16 publications

References 0 publications

Fast retrieval of high-dimensional feature vectors in P2P networks using compact peer data summaries

Fast retrieval of high-dimensional feature vectors in P2P networks using compact peer data summaries

Clustering-Based Source Selection for Efficient Image Retrieval in Peer-to-Peer Networks

Optimization of encryption technique using evolutionary algorithm for protecting multimedia contents in P2P system

Contact Info

Product

Resources

About