Title :
Object detection and recognition in a multiresolution representation
Author :
Micheli-Tzanakou, Evangelia ; Marsic, Ivan
Author_Institution :
Dept. of Biomed. Eng., Rutgers Univ., Piscataway, NJ, USA
Abstract :
The authors discuss the detection and recognition of visual objects. They deal with recognizing objects in natural scenes. Two assumptions are vital in the whole process: that the object representation is equivalent to some 2D function, and that the stability and sensitivity of the representation are preserved and are of equal importance. A truncated multiresolution pyramid neural net is used
Keywords :
neural nets; pattern recognition; picture processing; 2D function; multiresolution representation; natural scenes; object detection; object recognition; representation sensitivity; representation stability; truncated multiresolution pyramid neural net; Artificial neural networks; Biomedical engineering; Frequency; Image resolution; Layout; Object detection; Spatial resolution; Stability; Visual system; Wavelet transforms;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170775
