Corpus ID: 17835851

Performance evaluation of wavelet scattering network in image texture classification in various color spaces

@article{Wu2014PerformanceEO,
  title={Performance evaluation of wavelet scattering network in image texture classification in various color spaces},
  author={Jiasong Wu and Longyu Jiang and Xu Han and Lotfi Senhadji and Huazhong Shu},
  journal={ArXiv},
  year={2014},
  volume={abs/1407.6423}
}
Texture plays an important role in many image analysis applications. In this paper, we give a performance evaluation of color texture classification by performing wavelet scattering network in various color spaces. Experimental results on the KTH_TIPS_COL database show that opponent RGB based wavelet scattering network outperforms other color spaces. Therefore, when dealing with the problem of color texture classification, opponent RGB based wavelet scattering network is recommended. 
PCANet for Color Image Classification in Various Color Spaces
TLDR
Experimental results on CURet texture database, UC Merced land use database, and Georgia Tech face database show that Luminance and Chrominance based principal component analysis network outperforms other color spaces in the vast majority of cases. Expand
Deep learning for texture classification via multi-wavelet fusion of scattering transforms
TLDR
A multi-wavelet fusion-based architecture to improve the error of classification by using scattering transforms that achieves better classification results compared to the original scattering transform, and thus can be used as an effective method for texture classification problems. Expand
Target Classification in Synthetic Aperture Radar Images Using Quantized Wavelet Scattering Networks
TLDR
The WSN-based quantization studies performed in this investigation provide a good benchmark and important guidance for the design of quantized neural networks architectures for target classification and investigate their robustness to low signal-to-noise ratio (SNR) levels. Expand
A Compressed Sensing Algorithm Based on Multi-scale Residual Reconstruction Network
In recent years, a small number of measurements and iterative optimization algorithms were exploited in compressed sensing to reconstruct images. In the process of reconstruction, most algorithmsExpand

References

SHOWING 1-10 OF 16 REFERENCES
Experiments in colour texture analysis
TLDR
Experimental results indicate that the incorporation of colour information enhances the performance of the texture analysis techniques examined, and the classification accuracy is determined using a neural network classifier based on Learning Vector Quantization. Expand
Classification with color and texture: jointly or separately?
TLDR
It is argued that color and texture are separate phenomena that can, or even should, be treated individually. Expand
Invariant Scattering Convolution Networks.
  • Joan Bruna, S. Mallat
  • Medicine
  • IEEE transactions on pattern analysis and machine intelligence
  • 2012
TLDR
The mathematical analysis of wavelet scattering networks explain important properties of deep convolution networks for classification. Expand
Invariant Scattering Convolution Networks
  • Joan Bruna, S. Mallat
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
TLDR
The mathematical analysis of wavelet scattering networks explains important properties of deep convolution networks for classification. Expand
Generic Deep Networks with Wavelet Scattering
TLDR
A two-layer wavelet scattering network, which involves no learning and no max pooling, performs efficiently on complex image data sets such as CalTech, with structural objects variability and clutter. Expand
A New Biologically Inspired Color Image Descriptor
TLDR
A hierarchical non-linear spatio-chromatic operator yields spatial and chromatic opponent channels, which mimics processing in the primate visual cortex, which is shown to outperform standard grayscale/shape-based descriptors as well as alternative color processing schemes on several datasets. Expand
Evaluating Color Descriptors for Object and Scene Recognition
TLDR
From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition and the usefulness of invariance is category-specific. Expand
Color Based Object Recognition
TLDR
It is shown that l1l2l3 is also invariant to highlights, and a change in spectral power distribution of the illumination is considered to propose a new photometric color invariant m1m2m3 for matte objects. Expand
Distinctive Image Features from Scale-Invariant Keypoints
The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used toExpand
DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo
  • E. Tola, V. Lepetit, P. Fua
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2010
TLDR
An EM-based algorithm to compute dense depth and occlusion maps from wide-baseline image pairs using a local image descriptor, DAISY, which is very efficient to compute densely and robust against many photometric and geometric transformations. Expand
...
1
2
...