Object Classification via PCANet and Color Constancy Model

De Kun Hu; Li Zhang; Wei Dong Zhao; Tao Yan

doi:10.4028/www.scientific.net/AMM.635-637.997

Paper Titles

A New Edge Detection Algorithm Applied in Obstacle Identification of Unmanned Vehicle
p.981

Based on the Adaboost Algorithm of Face Detection Research
p.985

Defect Inspection for SMD Inductors
p.989

Image Adaptive Denoising Method Based on Compressive Sensing
p.993

Object Classification via PCANet and Color Constancy Model
p.997

Research Object Rotational Motion Estimation Based on Digital Video Analysis Technique
p.1001

Determining Intrinsic Parameters and Pose of Cameras from Single View with Variable Focal Length
p.1011

A Retrieval Strategy for Texture Image
p.1018

An Efficient Concealment Algorithm for Inter Frames Based on Block-Level and Pixel-Level Motion Vector Extrapolation
p.1026

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 635-637Object Classification via PCANet and Color...

Object Classification via PCANet and Color Constancy Model

Abstract:

In order to classify the objects in nature images, a model with color constancy and principle component analysis network (PCANet) is proposed. The new color constancy model imitates the functional properties of the HVS from the retina to the double-opponent cells in V1. PCANet can be designed and learned extremely, which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms. At last, a SVM is trained to classify the object in the image. The results of experiments demonstrate the potential of the model for object classification in wild color images.

You might also be interested in these eBooks

Advanced Design and Manufacturing Technology IV

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 635-637)

Pages:

997-1000

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.635-637.997

Citation:

Cite this paper

Online since:

September 2014

Authors:

De Kun Hu, Li Zhang*, Wei Dong Zhao, Tao Yan

Keywords:

Color Constancy, Deep Learning, Object Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] K. E. A. van de Sande, T. Gevers, and C. G. M. Snoek. Evaluating color descriptors for object and scene recognition. TPAMI, 32(9): 1582–1596, 2010. 1, 7.

DOI: 10.1109/tpami.2009.154

Google Scholar

[2] J. Wang, J. Yang, K. Yu, F. Lv, T. S. Huang, and Y. Gong. Locality constrained linear coding for image classification. In CVPR, pages 3360–3367, 2010. 1, 2, 5.

Google Scholar

[3] X. Zhou, K. Yu, T. Zhang, and T. S. Huang. Image classification using super-vector coding of local image descriptors. In ECCV 2010, pages 141–154. 2010. 1, 2.

DOI: 10.1007/978-3-642-15555-0_11

Google Scholar

[4] O. Duchenne, A. Joulin, and J. Ponce. A graph-matching kernel for object categorization. In ICCV 2011, pages 1792–1799, 2011. 1.

DOI: 10.1109/iccv.2011.6126445

Google Scholar

[5] B. Hakan, P. Marco, P. V. Namboodiriz, T. Tinne, Object Classification with Adaptable Regions, 2014CVPR.

Google Scholar

[6] Y. Sun, X. Wang and X. Tang, Deep Convolutional Network Cascade for Facial Point Detection, CVPR (2013).

Google Scholar

[7] T. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, Y. Ma: PCANet: A Simple Deep Learning Baseline for Image Classification, CoRR abs/1404. 3606 (2014).

DOI: 10.1109/tip.2015.2475625

Google Scholar

[8] S. Gao, K. Yang, C Li, Y Li, A Color Constancy Model with Double-Opponency Mechanisms, ICCV2013.

Google Scholar

[9] A. Vedaldi and B. Fulkerson. VLFeatQ. Wang, Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models, arXiv: 1207. 3538v2 [cs. CV] 23 Apr (2014).

Google Scholar