Object recognition from local scale-invariant features

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.

[1]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[2]  James L. Crowley,et al.  A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass Transform , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  W. Eric L. Grimson,et al.  Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[5]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  T. Lindeberg.  Scale-Space Theory : A Basic Tool for Analysing Structures at Different Scales , 1994 .

[7]  Minami Ito,et al.  Size and position invariance of neuronal responses in monkey inferotemporal cortex. , 1995, Journal of neurophysiology.

[8]  N. Logothetis,et al.  Shape representation in the inferior temporal cortex of monkeys , 1995, Current Biology.

[9]  Rachid Deriche,et al.  A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry , 1995, Artif. Intell..

[10]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[11]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[12]  Katsushi Ikeuchi,et al.  Detectability, Uniqueness, and Reliability of Eigen Windows for Stable Verification of Partially Occluded Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Nathan Intrator,et al.  Complex cells and Object Recognition , 1997 .

[15]  Keiji Tanaka.  Mechanisms of visual object recognition: monkey and human studies , 1997, Current Opinion in Neurobiology.

[16]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  D I Perrett,et al.  Visual Recognition Based on Temporal Cortex Cells: Viewer-Centred Processing of Pattern Configuration , 1998, Zeitschrift fur Naturforschung. C, Journal of biosciences.

[18]  R. Nelson,et al.  Large-scale tests of a keyed, appearance-based 3-D object recognition system , 1998, Vision Research.

[19]  A. Treisman,et al.  Perceiving visually presented objets: recognition, awareness, and modularity , 1998, Current Opinion in Neurobiology.