Computer analysis of visual properties of curved objects
Project MAC, Massachusetts Institute of Technology, 1971 - Perceptrons - 126 pages
A method is presented for the visual analysis of objects by computer. It is particularly well suited for opaque objects with smoothly curved surfaces. The method extracts information about the object's surface properties, including measures of its specularity, texture, and regularity. It also aids in determining the object's shape. The application of this method to a simple recognition task -- the recognition of fruit -- is discussed. The results on a more complex smoothly curved object, a human face, are also considered. (Author).
What people are saying - Write a review
We haven't found any reviews in the usual places.
added region area algorithm analysis angle area in points axis background Bartlett pear branch tip camera center of mass Computer Vision considered contiguity scan contour map curvature dark speckles detection Edge detection edges extract highl highl ight Highlight Depth identified ight image tree impulse response intensity function irregularities large number light intensity light source lnformation locally dark areas main branch eccentricity marked points matte component matte surface matte white measured Medial Axis method nodes object identification objects with smoothly oranges parameters pattern recognition Peach pointer procedures produce Project MAC protrusion recognition task reflectance Region Area Curve region center region representing region statistics represent regions routines Sample Set scratch array shape descriptors shown in figure significant simple small region smoothly curved object smoothly curved surfaces specular component stem hollow surface properties surface smear Sweet pear tactile texture Texture Test Spheres threshold levels tree structure