Performance analysis of texture classification techniques using shearlet transform

Krishnan, K. Gopala; Vanathi, P. T.; Abinaya, R.

doi:10.1109/wispnet.2016.7566368

Cited by 10 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the model with 4-level decomposition achieved the best accuracy in the previous experiment, we used this network in this experiment as well. We compared our model with a spectral approach using shearlet transform [24], a VGG network [5], T-CNN [2], and FV-CNN [8] with a fully connected layer (FC).…”

Section: Resultsmentioning

confidence: 99%

Wavelet Convolutional Neural Networks for Texture Classification

Fujieda,

Takayama,

Hachisuka

2017

Preprint

View full text Add to dashboard Cite

Texture classification is an important and challenging problem in many image processing applications. While convolutional neural networks (CNNs) achieved significant successes for image classification, texture classification remains a difficult problem since textures usually do not contain enough information regarding the shape of object. In image processing, texture classification has been traditionally studied well with spectral analyses which exploit repeated structures in many textures. Since CNNs process images asis in the spatial domain whereas spectral analyses process images in the frequency domain, these models have different characteristics in terms of performance. We propose a novel CNN architecture, wavelet CNNs, which integrates a spectral analysis into CNNs. Our insight is that the pooling layer and the convolution layer can be viewed as a limited form of a spectral analysis. Based on this insight, we generalize both layers to perform a spectral analysis with wavelet transform. Wavelet CNNs allow us to utilize spectral information which is lost in conventional CNNs but useful in texture classification. The experiments demonstrate that our model achieves better accuracy in texture classification than existing models. We also show that our model has significantly fewer parameters than CNNs, making our model easier to train with less memory.

show abstract

Section: Resultsmentioning

confidence: 99%

Wavelet Convolutional Neural Networks for Texture Classification

Fujieda,

Takayama,

Hachisuka

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Training with fine-tuning: Figure 4 and Table 3 show the classification rates using the networks pre-trained with the ImageNet 2012 dataset [35]. We compared our model with a spectral approach using shearlet transform [25], VGG-M [4], T-CNN [1], and VGG-M using compact bilinear pooling [9]. For compact bilinear pooling, we compared our model only with Tensor Sketch (TS) since it worked the best in practice.…”

Section: Texture Classificationmentioning

confidence: 99%

Wavelet Convolutional Neural Networks

Fujieda¹,

Takayama²,

Hachisuka³

2018

Preprint

View full text Add to dashboard Cite

Spatial and spectral approaches are two major approaches for image processing tasks such as image classification and object recognition. Among many such algorithms, convolutional neural networks (CNNs) have recently achieved significant performance improvement in many challenging tasks. Since CNNs process images directly in the spatial domain, they are essentially spatial approaches. Given that spatial and spectral approaches are known to have different characteristics, it will be interesting to incorporate a spectral approach into CNNs. We propose a novel CNN architecture, wavelet CNNs, which combines a multiresolution analysis and CNNs into one model. Our insight is that a CNN can be viewed as a limited form of a multiresolution analysis. Based on this insight, we supplement missing parts of the multiresolution analysis via wavelet transform and integrate them as additional components in the entire architecture. Wavelet CNNs allow us to utilize spectral information which is mostly lost in conventional CNNs but useful in most image processing tasks. We evaluate the practical performance of wavelet CNNs on texture classification and image annotation. The experiments show that wavelet CNNs can achieve better accuracy in both tasks than existing models while having significantly fewer parameters than conventional CNNs.

show abstract

“…ere are some enhancements which are implemented such as GLDM and GLRLM [29,30]. e latest work is from GLCM that extracted different features of the face based on GLCM [31,32]. However, in the existing methods, there are some drawbacks.…”

Section: Introductionmentioning

confidence: 99%

A Novel Statistical Feature Analysis-Based Global and Local Method for Face Recognition

Talab

Awang

Ansari³

2020

International Journal of Optics

View full text Add to dashboard Cite

Face recognition from an image/video has been a fast-growing area in research community, and a sizeable number of face recognition techniques based on texture analysis have been developed in the past few years. Further, these techniques work well on gray-scale and colored images, but very few techniques deal with binary and low-resolution images. As the binary image is becoming the preferred format for low face resolution analysis, there is a need for further studies to provide a complete solution for the image-based face recognition system with a higher accuracy rate. To overcome the limitation of the existing methods in extracting distinctive features in low-resolution images due to the contrast between the face and background, we propose a statistical feature analysis technique to fill the gaps. To achieve this, the proposed technique integrates the binary-level occurrence matrix (BLCM) and the fuzzy local binary pattern (FLBP) named FBLCM to extract global and local features of the face from binary and low-resolution images. The purpose of FBLCM is to distinctively improve performance of edge sharpness between black and white pixels in the binary image and to extract significant data relating to the features of the face pattern. Experimental results on Yale and FEI datasets validate the superiority of the proposed technique over the other top-performing feature analysis methods. The developed technique has achieved the accuracy of 94.54% when a random forest classifier is used, hence outperforming other techniques such as the gray-level co-occurrence matrix (GLCM), bag of word (BOW), and fuzzy local binary pattern (FLBP), respectively.

show abstract

Performance analysis of texture classification techniques using shearlet transform

Cited by 10 publications

References 17 publications

Wavelet Convolutional Neural Networks for Texture Classification

Wavelet Convolutional Neural Networks for Texture Classification

Wavelet Convolutional Neural Networks

A Novel Statistical Feature Analysis-Based Global and Local Method for Face Recognition

Contact Info

Product

Resources

About