A pooled Object Bank descriptor for image scene classification

Zang, Mujun; Wen, Dunwei; Liu, Tong; Zhang, Hailin; Liu, Chan-juan

doi:10.1016/j.eswa.2017.10.057

Cited by 11 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object Bank (OB) is a high-level image representation that encodes the spatial and semantic information [19]. However OB approach suffers from drawback of high-dimensionality and various approaches have been proposed in literature to reduce the dimensions and enhance the performance of OB [19,34]. To boost the performance of OB representation Zang et al [34] proposed a threshold value filter method.…”

Section: Related Workmentioning

confidence: 99%

“…However OB approach suffers from drawback of high-dimensionality and various approaches have been proposed in literature to reduce the dimensions and enhance the performance of OB [19,34]. To boost the performance of OB representation Zang et al [34] proposed a threshold value filter method. They used Matthew effect normalization method to simplify OB representation and constructed more compact descriptors and showed improved performance on three real-world datasets, with substantial dimensionality reduction of image descriptors.…”

Section: Related Workmentioning

confidence: 99%

“…Feature Dimensionality Accuracy PIWAH [16] 1800 76% SPM [18] 4200 81.1% Zang et al [34] 3717 81.5% SPSad+ [17] 13200 83.7% Karmakar et al [15] 4200 84.20% LGF [39] X 85.8% CWCH 2400 88.04%…”

Section: Algorithmsmentioning

confidence: 99%

“…6.94% higer accuracy compared to SPM [18], which is the pioneering work to incorporate spatial information into the BoVW model. In another recent paper [34], Zang et al reduce the dimensions of Object Bank (OB) achieving an accuracy 81.5%, CWCH produced a low-dimensional histogram representation with a 6.54% higher accuracy. Compared with the approach of rectangular rings [15] our method achieves 3.84% more accuracy with fewer dimensions reported in their work.…”

Section: Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

Intelligent image classification-based on spatial weighted histograms of concentric circles

Zafar

Ashraf

Ali

et al. 2018

ComSIS

View full text Add to dashboard Cite

As digital images play a vital role in multimedia content, the automatic classification of images is an open research problem. The Bag of Visual Words (BoVW) model is used for image classification, retrieval and object recognition problems. In the BoVW model, a histogram of visual words is computed without considering the spatial layout of the 2-D image space. The performance of BoVW suffers due to a lack of information about spatial details of an image. Spatial Pyramid Matching (SPM) is a popular technique that computes the spatial layout of the 2-D image space. However, SPM is not rotation-invariant and does not allow a change in pose and view point, and it represents the image in a very high dimensional space. In this paper, the spatial contents of an image are added and the rotations are dealt with efficiently, as compared to approaches that incorporate spatial contents. The spatial information is added by constructing the histogram of circles, while rotations are dealt with by using concentric circles. A weighed scheme is applied to represent the image in the form of a histogram of visual words. Extensive evaluation of benchmark datasets and the comparison with recent classification models demonstrate the effectiveness of the proposed approach. The proposed representation outperforms the state-of-the-art methods in terms of classification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent image classification-based on spatial weighted histograms of concentric circles

Zafar

Ashraf

Ali

et al. 2018

ComSIS

View full text Add to dashboard Cite

show abstract

“…Compared with generative models, SPM can achieve higher accuracy [12]. The SPM method [9] mines the spatial information through partitioning the image into increasingly finer spatial subregions and employs pyramid Match Kernel [1] to compare corresponding subregions.…”

Section: Introductionmentioning

confidence: 99%

A Fast Sparse Coding Method for Image Classification

et al. 2019

Self Cite

View full text Add to dashboard Cite

Image classification is an important problem in computer vision. The sparse coding spatial pyramid matching (ScSPM) framework is widely used in this field. However, the sparse coding cannot effectively handle very large training sets because of its high computational complexity, and ignoring the mutual dependence among local features results in highly variable sparse codes even for similar features. To overcome the shortcomings of previous sparse coding algorithm, we present an image classification method, which replaces the sparse dictionary with a stable dictionary learned via low computational complexity clustering, more specifically, a k-medoids cluster method optimized by k-means++. The proposed method can reduce the learning complexity and improve the feature’s stability. In the experiments, we compared the effectiveness of our method with the existing ScSPM method and its improved versions. We evaluated our approach on two diverse datasets: Caltech-101 and UIUC-Sports. The results show that our method can increase the accuracy of spatial pyramid matching, which suggests that our method is capable of improving performance of sparse coding features.

show abstract