Discovery of Collocation Patterns: from Visual Words to Visual Phrases

Yuan, Junsong; Wu, Ying; Yang, Ming

doi:10.1109/cvpr.2007.383222

Cited by 212 publications

(152 citation statements)

References 20 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…Frequent pattern mining techniques have been used in computer vision problems, including image classification [2,13,14], object recognition and object-part recognition [12]. These methods used different image representation, the way they convert image representation into transactional description which is suitable for pattern mining techniques and selects relevant and discriminative patterns.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Image Classification using Frequent Itemset Mining

Patel¹,

Sahani²

2015

IJCA

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

“…For applying FIM technique to image classification these bags (histogram) need to be converted into sets of items known as transactions using Bag-to-set (B2S) [2] method. This is done by considering each visual word as an item [13].…”

Section: Introductionmentioning

confidence: 99%

Image Classification using Frequent Itemset Mining

Patel¹,

Sahani²

2015

IJCA

View full text Add to dashboard Cite

“…Yuan et al [36] have proposed another higher-level lexicon, i.e. visual phrase lexicon, where a visual phrase is a spatially co-occurrent pattern of visual words.…”

Section: Analogy Between Information Retrieval and Cbirmentioning

confidence: 99%

Toward a higher-level visual representation for content-based image retrieval

Sayad

Martinet

Urruty

et al. 2010

Multimed Tools Appl

View full text Add to dashboard Cite

Having effective methods to access the desired images is essential nowadays with the availability of a huge amount of digital images. The proposed approach is based on an analogy between content-based image retrieval and text retrieval. The aim of the approach is to build a meaningful mid-level representation of images to be used later on for matching between a query image and other images in the desired database. The approach is based firstly on constructing different visual words using local patch extraction and fusion of descriptors. Secondly, we introduce a new method using multilayer pLSA to eliminate the noisiest words generated by the vocabulary building process. Thirdly, a new spatial weighting scheme is introduced that consists of weighting visual words according to the probability of each visual word to belong to each of the n Gaussian. Finally, we construct visual phrases from groups of visual words that are involved in strong association rules. Experimental results show that our approach outperforms the results of traditional image retrieval techniques.

show abstract

“…The alternative to the costly RANSAC verification is to inject geometric information directly into the retrieval procedure, by either spatially aggregating the local descriptors in a predefined [6] or adaptively selected [13] set of regions, or by capturing word cooccurrences into visual phrases, which correspond to higher-level visual information, either at the level of an entire image [14], or on local neighbourhoods [15,16]. By attaching additional geometric information to the visual words, schemes that deal with similarity transformations (translation, scale) in the image space have been designed [17,18]; addressing more complex transformations (e.g.…”

Section: Introductionmentioning

confidence: 99%

Affine invariant visual phrases for object instance recognition

Pătrăucean

Ovsjanikov

2015

2015 14th IAPR International Conference on Machine Vision Applications (MVA)

View full text Add to dashboard Cite

Object instance recognition approaches based on the bag-of-words model are severely affected by the loss of spatial consistency during retrieval. As a result, costly RANSAC verification is needed to ensure geometric consistency between the query and the retrieved images. A common alternative is to inject geometric information directly into the retrieval procedure, by endowing the visual words with additional information. Most of the existing approaches in this category can efficiently handle only restricted classes of geometric transformations, including scale and translation. In this paper, we propose a simple and efficient scheme that can cover the more complex class of full affine transformations. We demonstrate the usefulness of our approach in the case of planar object instance recognition, such as recognition of books, logos, traffic signs, etc.

show abstract

Discovery of Collocation Patterns: from Visual Words to Visual Phrases

Abstract: Abstract

Cited by 212 publications

References 20 publications

Image Classification using Frequent Itemset Mining

Image Classification using Frequent Itemset Mining

Toward a higher-level visual representation for content-based image retrieval

Affine invariant visual phrases for object instance recognition

Contact Info

Product

Resources

About