A statistical approach to 3d object detection applied to faces and cars
Henry Schneiderman, Takeo Kanade · 2000
In this thesis, we describe a statistical method for 3D object detection. In this method, we decompose the 3D geometry of each object into a small number of viewpoints. For each view-point, we construct a decision rule that determines if the object is present at that specific orienta-tion. Each decision rule uses the statistics of both object appearance and “non-object ” visual appearance. We represent each set of statistics using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints. Acknowledgments I would like to thank my advisor, Takeo Kanade, for his guidance in this research. His ideas, insights, suggestions, questions, and enthusiasm were great help in stimulating my thought and in bringing this research forward. I would like to thank the other members of my dissertation com-