The Pascal Visual Object Classes Challenge 2008 submission

After a plurality of grooves are formed in an insulating film and in an anti-reflection film on the insulating film, a barrier metal film and a conductive film are deposited on the anti-reflection film such that each of the grooves is filled therewith. Subsequently, the portions of the conductive film outside the grooves are removed by polishing and then the portions of the barrier metal film outside the grooves are removed by polishing. Thereafter, respective foreign matters adhered to a polishing pad and to a surface to be polished during polishing are removed and then a surface of the anti-reflection film is polished.

[1]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[2]  Lixin Fan,et al.  Categorizing Nine Visual Classes using Local Appearance Descriptors , 2004 .

[3]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[4]  Cordelia Schmid,et al.  Learning Object Representations for Visual Object Class Recognition , 2007, ICCV 2007.

[5]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[6]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.