On Building a Universal and Compact Visual Vocabulary

Hou, Jian; Liu, Weixue; E, Xu; Karimi, Hamid Reza

doi:10.1155/2013/163976

Cited by 3 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hou et al [5] proposed a similarity threshold based clustering method to calculate the optimal vocabulary size for a given visual object classes dataset. The similarity threshold based clustering is used to determine the size of a compact vocabulary, and the vector quantization with the vocabulary size is then performed with K-means clustering method.…”

Section: Previous Workmentioning

confidence: 99%

Creating Compact and Discriminative Visual Vocabularies Using Visual Bits

Kirishanthy

Ramanan

2015

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

In a patch-based object recognition system the key role of a visual vocabulary is to provide a way to map the low-level features into a fixed-length vector in histogram space to which standard classifiers can be directly applied. The discriminative power of such a visual vocabulary determines the quality of the vocabulary model, whereas the size of the vocabulary controls the complexity of the model. A compact visual vocabulary provides a lower-dimensional representation whereas a large-sized vocabulary may overfit to the distribution of visual words in an image and lead to heavy computational load. The generic framework of a bag-of-features approach follows a standard routine extracting local image descriptors and clustering with a user-designated number of clusters. The problem with this routine lies in that constructing a vocabulary for each single dataset is not efficient. Usually the construction of a vocabulary is achieved by cluster analysis using K-means algorithm. However, one of its drawbacks is the choice of a suitable value for K which determines the size of a visual vocabulary. The choice of the size of a vocabulary should be balanced between the recognition rate and computational needs. In this paper we propose a two-staged approach to map an initial high-dimensional vocabulary into a compact vocabulary while maintaining its discriminative power. Using an initial larger vocabulary we first represent the training images using a coding scheme that maps the importance of each visual word within an image as visual bits. These set of visual bits of images then form a sparse representation of every visual word with respect to the set of category-specific training images that is used for the compression. We have tested our vocabulary compression technique on four computer vision tasks: (i) Xerox7 (ii) PASCAL VOC Challenge 2007 (iii) UIUC texture and (iv) MPEG7 CE Shape-1 Part B Silhouette image datasets. Testing results show that the proposed method slightly outperforms vocabularies learnt by K-means by achieving just half the size of initial vocabulary. Our compression technique could help to optimize larger vocabularies to fewer visual words with stable performance.

show abstract

Section: Previous Workmentioning

confidence: 99%

Creating Compact and Discriminative Visual Vocabularies Using Visual Bits

Kirishanthy

Ramanan

2015

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

show abstract

“…They build a codebook for a given database, and the codebook is not used in other image databases. The literatures [26][27][28][29] have explored the possibility of building the universal codebook, which can be used in various image databases.…”

Section: Related Workmentioning

confidence: 99%

Research on Vocabulary Sizes and Codebook Universality

Liu

Hou

Karimi

2014

Abstract and Applied Analysis

Self Cite

View full text Add to dashboard Cite

Codebook is an effective image representation method. By clustering in local image descriptors, a codebook is shown to be a distinctive image feature and widely applied in object classification. In almost all existing works on codebooks, the building of the visual vocabulary follows a basic routine, that is, extracting local image descriptors and clustering with a user-designated number of clusters. The problem with this routine lies in that building a codebook for each single dataset is not efficient. In order to deal with this problem, we investigate the influence of vocabulary sizes on classification performance and vocabulary universality with the kNN classifier. Experimental results indicate that, under the condition that the vocabulary size is large enough, the vocabularies built from different datasets are exchangeable and universal.

show abstract