Object recognition by computer: the role of geometric constraints
Object recognition by computer: the role of geometric constraints
Toward 3D curved object recognition from image contours
Geometric invariance in computer vision
Using photometric invariants for 3D object recognition
Computer Vision and Image Understanding
Noise tolerance of moment invariants in pattern recognition
Pattern Recognition Letters
Robot Vision
Computer and Robot Vision
Digital Image Processing
Repeated Structures: Image Correspondence Constraints and 3D Structure Recovery
Proceedings of the Second Joint European - US Workshop on Applications of Invariance in Computer Vision
Invariant Object Recognition with Discriminant Features Based on Local Fast-Fourier Mellin Transform
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Recognition and Reconstruction of 3-D Objects Using Model-Based Perceptual Grouping
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Direct Object Recognition Using No Higher Than Second or Third Order Statistics of the Image
Direct Object Recognition Using No Higher Than Second or Third Order Statistics of the Image
Image Processing, Analysis, and Machine Vision
Image Processing, Analysis, and Machine Vision
Hi-index | 0.01 |
We report on a method for achieving a significant truncation of the training space necessary for recognizing rigid 3D objects from perspective images. Considering objects lying on a table, the configuration space of continuous coordinates is three-dimensional. In addition the objects have a few distinct support modes. We show that recognition using a stationary camera can be carried out by training each object class and support mode in a two-dimensional configuration space. We have developed a transformation used during recognition for projecting the image information into the truncated configuration space of the training. The new concept gives full flexibility concerning the position of the camera since perspective effects are treated exactly. The concept has been tested using 2D object silhouettes as image property and central moments as image descriptors. High recognition speed and robust performance are obtained.