PicSOM – content-based image retrieval with self-organizing maps

Laaksonen, Jorma; Koskela, Markus; Laakso, Sami; Oja, Erkki

doi:10.1016/s0167-8655(00)00082-9

Cited by 173 publications

(80 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We briefly summarise the qualitative representation schema for describing a hierarchy of spatial ontologies and Self-organizing maps (SOM) as the method for design comparison. For more detail see [17] and [18,40].…”

Section: Computational Analysismentioning

confidence: 99%

“…In text and image-based research, RF is an established approach that enables contextualdependencies to be integrated for document and image retrieval. Recently this approach has been adopted by researchers using SOMs to retrieve information from large databases [38,39,40].…”

Section: Relevant Stylesmentioning

confidence: 99%

“…For this reason, the labels (architects) identified from training are maintained so as to assign categories. The "micro-averaged" precision matrix method [50] was first used to evaluate each network and the well-established JAC and FM methods were then used to evaluate cluster quality; see [40] for further details of these evaluation methods.…”

Section: Testingmentioning

confidence: 99%

See 2 more Smart Citations

Let’s Look at Style: Visual and Spatial Representation and Reasoning in Design

Jupp

Gero

2010

The Structure of Style

View full text Add to dashboard Cite

Abstract. This chapter explores the perception and modeling of style in design relating to visuo-spatial representation and reasoning. We approach this subject via cognitive and contextual considerations significant to the role of style during designing. A designer's ability to represent and reason about design artifacts visually and spatially allows meaningful 'chunks' of design information to be utilized relative to the designer's task and context. Central to cognitive and contextual notions of style are two issues, namely the level of semantic interpretation, and the comparative method's degree of contextual sensitivity. This compound problem requires some explicit and cognitively plausible ordering principle and adaptive measure capable of allowing for dependencies in reasoning about similarities. This chapter first investigates the perception of style in relation to these modeling requirements before demonstrating and testing their implementation. We then discuss style in relation to design tasks and how they can be supported via the classification and retrieval of designs from large databases of visuo-spatial information.

show abstract

Section: Computational Analysismentioning

confidence: 99%

Section: Relevant Stylesmentioning

confidence: 99%

See 1 more Smart Citation

Let’s Look at Style: Visual and Spatial Representation and Reasoning in Design

Jupp

Gero

2010

The Structure of Style

View full text Add to dashboard Cite

show abstract

“…The PicSOM system [5] is a framework for research on algorithms and methods for content-based image retrieval. PicSOM implements relevance feedback by using Tree Structured Self-Organizing Map (TS-SOM) [6] in storing the user responses and in selecting the images.…”

Section: Picsommentioning

confidence: 99%

Self-Organizing Maps of Web Link Information

Laakso

Laaksonen

Koskela

et al. 2001

Advances in Self-Organising Maps

Self Cite

View full text Add to dashboard Cite

Summary. We have developed a method that utilizes hypertext link information in image retrieval from the World Wide Web. The basis of the method consists of a set of basic relations that can take place between two images in the Web. Our method uses the SHA-1 message digest algorithm for dimension reduction by random mapping. The Web link features have then been used in creating a SelfOrganizing Map of images in the Web. The method has been effectively tested with our PicSOM content-based image retrieval system using a Web image database containing over a million images. The method can as such be used also in other Web applications not related to content-based image retrieval.

show abstract

“…The system is implemented inside the PicSOM 1 CBIR software framework [27,28,29]. As an input, the system takes two sets of images: a set of images annotated with a certain keyword (positive examples), and a set of auxiliary background images (negative examples) As the result of the processing the system produces a segmentation of the positive example images and ranks the segments according to their relevance to the keyword, i.e.…”

Section: System Implementationmentioning

confidence: 99%

PicSOM – content-based image retrieval with self-organizing maps

Cited by 173 publications

References 11 publications

Let’s Look at Style: Visual and Spatial Representation and Reasoning in Design

Let’s Look at Style: Visual and Spatial Representation and Reasoning in Design

Self-Organizing Maps of Web Link Information

Focusing Keywords to Automatically Extracted Image Segments Using Self-Organising Maps

Contact Info

Product

Resources

About