Color matching for image retrieval

Mehtre, Babu M.; Kankanhalli, Mohan; Narasimhalu, Arcot Desai; Man, Guo Chang

doi:10.1016/0167-8655(94)00096-l

Cited by 155 publications

(57 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…effectiveness, to evaluate the compared approaches. This measure was proposed by Mehtre et al [10], and adopted to quantify the utility of relevance feedback mechanisms recently [4]. The definition is shown in Eq.…”

Section: Methodsmentioning

confidence: 99%

Exploiting Unlabeled Data in Content-Based Image Retrieval

Zhou

Chen

Jiang

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, the Ssair (Semi-Supervised Active Image Retrieval) approach, which attempts to exploit unlabeled data to improve the performance of content-based image retrieval (Cbir), is proposed. This approach combines the merits of semi-supervised learning and active learning. In detail, in each round of relevance feedback, two simple learners are trained from the labeled data, i.e. images from user query and user feedback. Each learner then classifies the unlabeled images in the database and passes the most relevant/irrelevant images to the other learner. After re-training with the additional labeled data, the learners classify the images in the database again and then their classifications are merged. Images judged to be relevant with high confidence are returned as the retrieval result, while these judged with low confidence are put into the pool which is used in the next round of relevance feedback. Experiments show that semi-supervised learning and active learning mechanisms are both beneficial to Cbir.

show abstract

Section: Methodsmentioning

confidence: 99%

Exploiting Unlabeled Data in Content-Based Image Retrieval

Zhou

Chen

Jiang

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In this sense, we propose a preliminary segmentation of images for obtaining homogeneous regions supported in a hierarchical structure of clustering, and then, we use the colour and shape attributes for establishing similarity between scenes. Our scheme, as contrasted with other works (Gevers and Smeulders, 1999a;Jacobs et al, 1995;Jain and Vailaya, 1998;Kankanhalli et al, 1999;Mehtre et al, 1995), allows us to recover images based on queries formulated in terms of complete scenes or homogeneous colour regions contained in them.…”

Section: Introductionmentioning

confidence: 98%

“…However, traditionally, colour data have been avoided on many occasions either to simplify the computations or to reduce the storage space required to contain the studied image. Recent works reveal increasing interest in the use of colour as an attribute for image segmentation (Chapron, 1992;Healey, 1992;Schettini, 1993;Lambert and Carron, 1999;Borsotti et al, 1998;Zugaj and Lattuati, 1998;Yung and Lai, 1998) as well as for image retrieval from large databases (Swain and Ballard, 1991;Swain, 1993;Mehtre et al, 1995Mehtre et al, , 1998Kankanhalli et al, 1996;Smeulders, 1999a,b,c, 2000;Del Bimbo et al, 1998;Chang, 1997;Chang et al, 1997;Ma and Manjunath, 1997;Pentland et al, 1996;Smith and Chang, 1996;Flickner et al, 1995).…”

Section: Introductionmentioning

confidence: 99%

A scheme of colour image retrieval from databases

Fuertes

Lucena

Blanca

et al. 2001

Pattern Recognition Letters

View full text Add to dashboard Cite

This paper presents a scheme of image retrieval from a database using queries prompted by the colour and the shape of the objects present in di erent scenes. Of the whole scheme of image retrieval, we will focus attention on the modules that allow feature extraction of the component objects from the scenes and the matching of the objects among the di erent images. The de®ned scheme enables the indexing of images by measuring the similarity between the integral objects. Ó

show abstract

“…Importantly, users ®nd colour-based queries an intuitive and effective mechanism for navigating in an image database [6,7]. Colour distribution information can be represented in a number of ways: mean RGB co-variant RGB [8], colour clusters [9±11]), and colour names [12,13]). However, the most general (and arguably the simplest) representation for colour distributions is the colour histogram.…”

Section: Introductionmentioning

confidence: 99%

Image indexing using compressed colour histograms

Berens

Finlayson

Qiu

2000

IEE Proc., Vis. Image Process.

View full text Add to dashboard Cite

The distribution of colours in an image has proven to be very useful for object recognition. Building on Swain's colour indexing, colour distributions are now an integral part of many recognition schemes. This is not to say that colour alone suf®ces but rather that colour is one important cue that aids recognition. Colour indexing is performed on colour distribution histograms, and as such, the speed of the system is directly related to the size of the histogram to be indexed. It is shown how colour histograms can be effectively compressed and how compressed colour histograms can be compared for indexing. The authors make two important contributions. First, they show that an opponent colour histogram can be compressed more readily than can conventional colour space. Secondly, they use the standard transform encoding methods (the Karhunen±Loe Ãve transform, the discrete cosine transform, the Hadamard transform and hybrid transforms) to compress colour histograms. Experiments show that compression rates of up to 250:1 are possible without affecting indexing performance. This means that a database can be searched that is 250 times larger in the same time as that searched by conventional indexing.

show abstract

Color matching for image retrieval

Cited by 155 publications

References 5 publications

Exploiting Unlabeled Data in Content-Based Image Retrieval

Exploiting Unlabeled Data in Content-Based Image Retrieval

A scheme of colour image retrieval from databases

Image indexing using compressed colour histograms

Contact Info

Product

Resources

About