Improvement the Bag of Words Image Representation Using Spatial Information

Farhangi, M. Mehdi; Soryani, Mohsen

doi:10.1007/978-3-642-31552-7_69

Cited by 9 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The five methods are i. BoW [30]: the popular local feature classification algorithm that uses a visual word to represent a local feature. ii.…”

Section: Methodsmentioning

confidence: 99%

“…In the experiments, we implemented and evaluated the proposed method as well as four other well‐known algorithms on the HSRSI data set. The five methods are BoW [ 30 ]: the popular local feature classification algorithm that uses a visual word to represent a local feature. Traditional LLC algorithm [ 9 ]: the locality‐constrained linear coding algorithm that uses nearest‐neighbour words for the spatial domain to represent a local feature. SSIP algorithm [ 29 ]: a parallel framework of HSI classification based on spatial spectral interest point. VGGNet algorithm [ 31 ]: a deep learning algorithm for convolution networks that inherits some frameworks of Lenet and Alexnet algorithms. Our algorithm: the representation method that uses nearest‐neighbour words for the spatial–spectral domain to represent a local feature and spatial–spectral pyramid matching mode. …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Robust multi‐view representation for spatial–spectral domain in application of hyperspectral image classification

Li¹,

Wang²,

Huang

et al. 2018

IET Computer Vision

View full text Add to dashboard Cite

Spatial-spectral representation plays an important role in hyperspectral images (HSIs) classification. However, many of the existing local feature algorithms for HSIs are based on the two-dimensional image and do not take full advantage of the information hidden in HSI, such as spatial-spectral locality correlation information, thereby reducing the robustness of these algorithms. In response to these problems, this study presents a robust multi-view spatial-spectral representation method with the characteristics of HSIs. There are two key techniques in this representation method, called spatial-spectral locality constrained linear coding (SSLLC) and spatial-spectral pyramid matching model (SSPM). Firstly, SSLLC applies the locality information of the feature points and visual words and uses the discriminant information provided by the nearest-neighbouring spatial-spectral feature points in HSIs. Secondly, SSPM works by partitioning the image into increasingly fine sub-cubes and uses the cubes to match the local features of the HSIs. The multi-view representation is tolerant to illumination change, image rotation, affine distortion etc. To assess the validity of authors' algorithm, the authors compared their results with several existing approaches, including a deep learning method. The experimental results show that this representation method can effectively improve the accuracy of HSIs classification.

show abstract

“…The five methods are i. BoW [30]: the popular local feature classification algorithm that uses a visual word to represent a local feature. ii.…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Robust multi‐view representation for spatial–spectral domain in application of hyperspectral image classification

Li¹,

Wang²,

Huang

et al. 2018

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…In this case, counting all the words combinations, even for small vocabularies, is very time‐consuming. To deal with this problem, we propose a new approach, based on extending our preliminary work [27] with a method to construct informative words, producing results on a new dataset and comparison with other image representations. The informative nodes are obtained from the nodes of an ontology structure and are appropriate for words relation modelling.…”

Section: Related Workmentioning

confidence: 99%

Informative visual words construction to improve bag of words image representation

Farhangi

Soryani

2014

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Bag of visual words model has recently attracted much attention from computer vision society because of its notable success in analysing images and exploring their content. This study improves this model by utilising the adjacency information between words. To explore this information, a binary tree structure is constructed from the visual words in order to model the isa relationships in the vocabulary. Informative nodes of this tree are extracted by using the χ 2 criterion and are used to capture the adjacency information of visual words. This approach is a simple and computationally effective way for modelling the spatial relations of visual words, which improves the image classification performance. The authors evaluated our method for visual classification of three known datasets: 15 natural scenes, Caltech-101 and Graz-01.

show abstract

Fuzzy bag of words for social image description

Liu

Huang

et al. 2014

Multimed Tools Appl

View full text Add to dashboard Cite

Improvement the Bag of Words Image Representation Using Spatial Information

Cited by 9 publications

References 9 publications

Robust multi‐view representation for spatial–spectral domain in application of hyperspectral image classification

Robust multi‐view representation for spatial–spectral domain in application of hyperspectral image classification

Informative visual words construction to improve bag of words image representation

Fuzzy bag of words for social image description

Contact Info

Product

Resources

About