Efficient Image Retrieval through Vantage Objects

Vleugels, Jules; Veltkamp, Remco C.

doi:10.1007/3-540-48762-x_71

Cited by 33 publications

(30 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these approaches, anchor space is built by selecting a subset of objects from database as global reference axes. The selected objects are named as foci [33], anchor [34] or vantage points [35]. The main challenges of anchor-based selection are which and how many objects should be selected as anchors.…”

Section: Anchor-based Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Selection of Concept Detectors for Video Search by Ontology-Enriched Semantic Spaces

Wei

Ngo

Jiang

2008

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

Section: Anchor-based Selectionmentioning

confidence: 99%

“…The recent work in [33], for instance, proposes HF (Hull-ofFoci) algorithm for the selection of anchor objects. The idea of using anchors to build anchor-space has actually been used in various applications including database indexing [33], music classification [34], image retrieval [35], and animal sound classification [36].…”

Section: Anchor-based Selectionmentioning

confidence: 99%

Selection of Concept Detectors for Video Search by Ontology-Enriched Semantic Spaces

Wei

Ngo

Jiang

2008

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…The final set of experiments we present compares our "clustering" approach of choosing pivots to ones existing in the literature [19][20][21][22]. Previous methods of utilizing the concept of pivots have been proposed in the context of search in metric spaces.…”

Section: Comparison With Other Methods Of Choosing Pivotsmentioning

confidence: 99%

“…Various studies [19][20][21][22] use notions of pivots or anchors or foci for efficient indexing and query processing. Our approach is related in principle, but our objectives and methodologies are different.…”

Section: Related Workmentioning

confidence: 99%

NNH: Improving Performance of Nearest-Neighbor Searches Using Histograms

Jin

Koudas

2004

Advances in Database Technology - EDBT 2004

View full text Add to dashboard Cite

Abstract. Efficient search for nearest neighbors (NN) is a fundamental problem arising in a large variety of applications of vast practical interest. In this paper we propose a novel technique, called NNH ("Nearest Neighbor Histograms"), which uses specific histogram structures to improve the performance of NN search algorithms. A primary feature of our proposal is that such histogram structures can co-exist in conjunction with a plethora of NN search algorithms without the need to substantially modify them. The main idea behind our proposal is to choose a small number of pivot objects in the space, and pre-calculate the distances to their nearest neighbors. We provide a complete specification of such histogram structures and show how to make use of the information they provide towards more effective searching. In particular, we show how to construct them, how to decide the number of pivots, how to choose pivot objects, how to incrementally maintain them under dynamic updates, and how to utilize them in conjunction with a variety of NN search algorithms to improve the performance of NN searches. Our intensive experiments show that nearest neighbor histograms can be efficiently constructed and maintained, and when used in conjunction with a variety of algorithms for NN search, they can improve the performance dramatically.

show abstract

“…The difference here is that only the nearest centroid matters in clustering whereas these methods store and use the similarities from data items to all vantage points. Studies on using vantage points in image indexing include Vleugels and Veltkamp (2002) and Natsev and Smith (2002).…”

Section: Vantage Pointsmentioning

confidence: 99%

Content-Based Image Retrieval Using Self-Organizing Maps

Laaksonen

Koskela

Oja

1999

Visual Information and Information Systems

View full text Add to dashboard Cite

Digital image libraries are becoming more common and widely used as visual information is produced at a rapidly growing rate. Creating and storing digital images is nowadays easy and getting more affordable all the time as the needed technologies are maturing and becoming eligible for general use. As a result, the amount of data in visual form is increasing and there is a strong need for effective ways to manage and process it. In many settings, the existing and widely adopted methods for text-based indexing and information retrieval are inadequate for these new purposes.Content-based image retrieval addresses the problem of finding images relevant to the users' information needs from image databases, based principally on low-level visual features for which automatic extraction methods are available. Due to the inherently weak connection between the high-level semantic concepts that humans naturally associate with images and the low-level visual features that the computer is relying upon, the task of developing this kind of systems is very challenging. A popular method to improve retrieval performance is to shift from single-round queries to navigational queries where a single retrieval instance consists of multiple rounds of user-system interaction and query reformulation. This kind of operation is commonly referred to as relevance feedback and can be considered as supervised learning to adjust the subsequent retrieval process by using information gathered from the user's feedback.In this thesis, an image retrieval system named PicSOM is presented, including detailed descriptions of using multiple parallel Self-Organizing Maps (SOMs) for image indexing and a novel relevance feedback technique. The proposed relevance feedback technique is based on spreading the user responses to local SOM neighborhoods by a convolution with a kernel function. A broad set of evaluations with different image features, retrieval tasks, and parameter settings demonstrating the validity of the retrieval method is described. In particular, the results establish that relevance feedback with the proposed method is able to adapt to different retrieval tasks and scenarios.Furthermore, a method for using the relevance assessments of previous retrieval sessions or potentially available keyword annotations as sources of semantic information is presented. With performed experiments, it is confirmed that the efficiency of semantic image retrieval can be substantially increased by using these features in parallel with the standard low-level visual features.

show abstract

Efficient Image Retrieval through Vantage Objects

Cited by 33 publications

References 21 publications

Selection of Concept Detectors for Video Search by Ontology-Enriched Semantic Spaces

Selection of Concept Detectors for Video Search by Ontology-Enriched Semantic Spaces

NNH: Improving Performance of Nearest-Neighbor Searches Using Histograms

Content-Based Image Retrieval Using Self-Organizing Maps

Contact Info

Product

Resources

About