Title :
SHOSLIF: a framework for object recognition from images
Author_Institution :
Dept. of Comput. Sci., Michigan State Univ., East Lansing, MI, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
A new framework called self-organizing hierarchical optimal subspace learning and inference framework (SHOSLIF) is introduced for recognizing and segmenting real-world objects from images. It addresses critical problems in real-world recognition including visual attention, feature representation efficiency, shape variation in unsegmented data (including size, position and orientation), decision optimality, and geometric inference
Keywords :
image segmentation; inference mechanisms; learning (artificial intelligence); neural nets; object recognition; self-adjusting systems; SHOSLIF; decision optimality; feature representation efficiency; geometric inference; image recognition; image segmentation; object recognition; self-organizing hierarchical optimal subspace learning; shape variation; subspace inference; visual attention; Backpropagation; Computer science; Face detection; Humans; Image recognition; Image segmentation; Neural networks; Object recognition; Pattern recognition; Shape;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374940
