Semantically similar visual words discovery to facilitate visual invariance

Chimlek, Sutasinee; Kesorn, Kraisak; Piamsa-nga, Punpiti; Poslad, Stefan

doi:10.1109/icme.2010.5582604

Cited by 3 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most recent techniques, K-means [Sheng et al 2010;Kandasamy and Rodrigo 2010;Hotta 2009;Chimlek et al 2010] is preferred for clustering data because it is unsupervised and easily implemented. However, K-means has obvious sensitivity in initialization and local searching abilities.…”

Section: Bag Of Words With Multithresholdingmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of archaeological pottery sherds

Makridis

Daras

2012

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

This article presents a novel technique for automatic archaeological sherd classification. Sherds that are found in the field usually have little to no visible textual information such as symbols, graphs, or marks on them. This makes manual classification an extremely difficult and time-consuming task for conservators and archaeologists. For a bunch of sherds found in the field, an expert identifies different classes and indicates at least one representative sherd for each class (training sample). The proposed technique uses the representative sherds in order to correctly classify the remaining sherds. For each sherd, local features based on color and texture information are extracted and are then transformed into a global vector that describes the whole sherd image, using a new bag of words technique. Finally, a feature selection algorithm is applied that locates features with high discriminative power. Extensive experiments were performed in order to verify the effectiveness of the proposed technique and show very promising results.

show abstract

Section: Bag Of Words With Multithresholdingmentioning

confidence: 99%

“…Feature selection techniques have been widely used in 2D image classification problems [Chimlek et al 2010;Kerroum et al 2009]. In our case, a plethora of features has to be integrated in order to deal with both textured and nontextured databases.…”

Section: Feature Selection and Sherd Classificationmentioning

confidence: 99%

Automatic classification of archaeological pottery sherds

Makridis

Daras

2012

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

show abstract

“…In [5] the author uses Olympic game ontology by fusing both textual and visual information but for ontology the author uses only the anthropological structure of the Olympic game event, where in our work we also interpolate the image feature in those Ontology creations.…”

Section: Related Workmentioning

confidence: 99%

Semantically Effective Visual Concept Illustration for Images

Thyagharajan¹,

Nagarajan²

2014

IJET

View full text Add to dashboard Cite

Abstract-The field of analyzing and understanding high-dimension real world data in a knowledgeable form is known as computer vision. Image is such a high dimension real world data which is enormously available in meaningless way. Using Ontologies in this computer vision field will enable a high end Ontology knowledge based image analysis and understanding. The main objective of this paper is to develop a frame work that creates a Bag of Visual Words for sports events using low level features of images and to develop ontology to provide semantic meaning to the images. Such semantically available images can be easily retrieved using a semantic image retrieval system. We used the concepts of enhanced Scale Invariant Feature Transform (SIFT) for feature extraction and Support Vector Machine based classification model to provide semantic to the images for action classification of images Index Terms-Computer vision, ontology, bag of visual words, SIFT, SVM and knowledge-based component.

show abstract

“…Subsequently, histograms of the estimated words, that are computed using the constructed vocabulary of visual words and the original descriptors, are used for representing the image content. Typical techniques of this category employ the K-means algorithm for clustering (Chimlek et al 2010;Hotta 2009;Kandasamy and Rodrigo 2010;Sheng et al 2010), mainly due to its ease of implementation. However, K-means has increased sensitivity to its initialisation and local search strategy.…”

Section: Visual Features Extraction Approachmentioning

confidence: 99%