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

Viitaniemi, Ville; Laaksonen, Jorma

doi:10.1007/978-3-540-38233-1_5

Cited by 2 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result is naturally dependent on the database at hand. If the database is sufficiently comprehensive, the significance of context in the images may become lesser, and the actual target object in the image becomes the most important contributor in image classification, as in [12].…”

Section: Discussionmentioning

confidence: 99%

“…The flexibility might be needed, for example if the framework is used for image analysis on the level of image segments. This is the case in [13] where the framework is discriminatively used to locate an object in the images an basis of examples, in [12] where image-level keywords are focused on specific image segments, and in the next section of this paper. 7.…”

Section: Quantitative Validationmentioning

confidence: 99%

See 1 more Smart Citation

Use of Image Regions in Context-Adaptive Image Classification

Viitaniemi¹,

Laaksonen²

2006

Semantic Multimedia

Self Cite

View full text Add to dashboard Cite

In this paper we describe and discuss our existing PicSOM software framework from the point of view of context-adaptive analysis of image contents, especially its method for using automatic image segmentation. We describe and experimentally validate a modification to the segment-using procedure that both essentially reduces the computational cost and slightly improves classification accuracy. Finally, we apply the segment-using methodology in qualitatively investigating the roles of primary objects and their context in classifying the images of the Pascal VOC Challenge 2006 database.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Quantitative Validationmentioning

confidence: 99%