Structural difference histogram representation for texture image classification

Feng, Jinwang; Liu, Xinliang; Dong, Yongsheng; Liang, Lin-Mei; Pu, Jiexin

doi:10.1049/iet-ipr.2016.0495

Cited by 16 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Texture is an important image property for image analysis and understanding [1, 2]. Dynamic texture (DT) is the texture with motion, which is the extension of image texture to the temporal domain.…”

Section: Introductionmentioning

confidence: 99%

Dynamic texture classification using Gumbel mixtures in the complex wavelet domain

Qiao

Liu

2019

IET Image Processing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Dynamic texture classification using Gumbel mixtures in the complex wavelet domain

Qiao

Liu

2019

IET Image Processing

View full text Add to dashboard Cite

“…For example, in the first stage, the system performs a preprocessing operation on the input image such as lightning correction, histogram normalisation, and colour segmentation. In the second stage, it extracts features such as edges, local binary patterns (LBPs) [3], histogram of gradients (HOGs), histogram of optical flow, bag‐of‐features (BoFs), scale‐invariant feature transform (SIFT), and dense trajectory features. The resultant of these steps is used to carry out the classification task through a matching or machine learning algorithm, namely artificial neural networks or support vector machines (SVMs).…”

Section: Introductionmentioning

confidence: 99%

Effect of fusing features from multiple DCNN architectures in image classification

Akilan

Zhang

2018

IET image process

View full text Add to dashboard Cite

Automatic image classification has become a necessary task to handle the rapidly growing digital image usage. It has branched out many algorithms and adopted new techniques. Among them, feature fusion-based image classification methods rely on hand-crafted features traditionally. However, it has been proven that the bottleneck features extracted through pretrained convolutional neural networks (CNNs) can improve the classification accuracy. Thence, this study analyses the effect of fusing such cues from multiple architectures without being tied to any hand-crafted features. First, the CNN features are extracted from three different pre-trained models, namely AlexNet, VGG-16, and Inception-V3. Then, a generalised feature space is formed by employing principal component reconstruction and energy-level normalisation, where the features from individual CNN are mapped into a common subspace and embedded using arithmetic rules to construct fused feature vectors (FFVs). This transformation play a vital role in creating a representation that is appearance invariant by capturing complementary information of different high-level features. Finally, a multi-class linear support vector machine is trained. The experimental results demonstrate that such multi-modal CNN feature fusion is well suited for image/object classification tasks, but surprisingly it has not been explored so far by the computer vision research community extensively.

show abstract

“…The statistical texture features provide the essential information about the properties of the intensity level in an image [24]. The LBP is a powerful texture descriptor [25,26] and it warrants less computation cost [13]. The above-mentioned methods have their own specialities in classifying texture images; hence, we adopt these methods and propose two new improved approaches to discriminate texture images effectively.…”

Section: Introductionmentioning

confidence: 99%

Two improved extension of local binary pattern descriptors using wavelet transform for texture classification

Ramakrishnan¹,

Nithya²

2018

IET Image Processing

View full text Add to dashboard Cite

Structural difference histogram representation for texture image classification

Cited by 16 publications

References 36 publications

Dynamic texture classification using Gumbel mixtures in the complex wavelet domain

Dynamic texture classification using Gumbel mixtures in the complex wavelet domain

Effect of fusing features from multiple DCNN architectures in image classification

Two improved extension of local binary pattern descriptors using wavelet transform for texture classification

Contact Info

Product

Resources

About