Optimizing color information processing inside an SVM network

Today, with the higher computing power of CPUs and GPUs, many different neural network architectures have been proposed for object detection in images. However, these networks are often not optimized to process color information. In this paper, we propose a new method based on an SVM network, that efficiently extracts this color information. We describe different network archi-tectures and compare them with several color models (CIELAB, HSV, RGB...). The results obtained on real data show that our network is more efficient and robust than a single SVM network, with an average precision gain ranging from 1.5% to 6% with respect to the complexity of the test image database. We have optimized the network architecture in order to gain information from color data, thus increasing the average precision by up to 10%.

[1]  Minho Lee,et al.  Deep Network with Support Vector Machines , 2013, ICONIP.

[2]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[4]  Dumitru Erhan,et al.  Scalable Object Detection Using Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Gwanggil Jeon,et al.  Measuring and Comparison of Edge Detectors in Color Spaces , 2013 .

[7]  Marc Chaumont,et al.  An efficient multi-resolution SVM network approach for object detection in aerial images , 2015, 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP).

[8]  Matthew Anderson,et al.  Proposal for a Standard Default Color Space for the Internet - sRGB , 1996, CIC.

[9]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  John Shawe-Taylor,et al.  Generic object recognition by combining distinct features in machine learning , 2005, IS&T/SPIE Electronic Imaging.

[11]  P Ganesan,et al.  Segmentation and edge detection of color images using CIELAB color space and edge detectors , 2010, INTERACT-2010.

[12]  Daniel A. Lavigne,et al.  Robust vehicle detection in low-resolution aerial imagery , 2010, Defense + Commercial Sensing.

[13]  Marc Chaumont,et al.  Detection of Manhole Covers in High-Resolution Aerial Images of Urban Areas by Combining Two Methods , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Ian H. Witten,et al.  Stacked generalization: when does it work? , 1997, IJCAI 1997.

[15]  Dumitru Erhan,et al.  Deep Neural Networks for Object Detection , 2013, NIPS.

[16]  Ramón López de Mántaras,et al.  Real-Time Object Segmentation Using a Bag of Features Approach , 2010, CCIA.

[17]  Jing Gao,et al.  Converting Output Scores from Outlier Detection Algorithms into Probability Estimates , 2006, Sixth International Conference on Data Mining (ICDM'06).

[18]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Marc Chaumont,et al.  Automatic localization of tombs in aerial imagery: Application to the digital archiving of cemetery heritage , 2013, 2013 Digital Heritage International Congress (DigitalHeritage).