Embedding class information into local invariant features by low-dimensional retinotopic mapping

作者：Raytchev Bisser^*; Kikutsugi Yuta; Tamaki Toru; Kaneda Kazufumi

来源：Machine Vision and Applications, 2013, 24(2): 407-418.

DOI：10.1007/s00138-012-0415-7

• Local invariant features
• Multidimensional scaling
• Dimensionality reduction
• SIFT
• PCA-SIFT
• View-invariant object recognition
• Retinotopic mapping

In this paper, we propose a new general framework to obtain more distinctive local invariant features by projecting the original feature descriptors into low-dimensional feature space, while simultaneously incorporating also class information. In the resulting feature space, the features from different objects project to separate areas, while locally the metric relations between features corresponding to the same object are preserved. The low-dimensional feature embedding is obtained by a modified version of classical Multidimensional Scaling, which we call supervised Multidimensional Scaling (sMDS). Experimental results on a database containing images of several different objects with large variation in scale, viewpoint, illumination conditions and background clutter support the view that embedding class information into the feature representation is beneficial and results in more accurate object recognition.

• 出版日期2013-2