Title :
Towards semen quality assessment using neural networks
Author :
Linneberg, Chr ; Salamon, P. ; Svarer, C. ; Hansen, L.K. ; Meyrowitsch, J.
Author_Institution :
Electron. Inst., Tech. Univ. Denmark, Lyngby, Denmark
Abstract :
The paper presents the methodology and results from a neural net based classification of human sperm head morphology. The methodology uses a preprocessing scheme in which invariant Fourier descriptors are lumped into “energy” bands. The resulting networks are pruned using optimal brain damage. Performance comparable to the error rate for human technicians is obtained
Keywords :
Fourier analysis; cellular biophysics; image classification; medical image processing; neural nets; classification; energy bands; human sperm head morphology; invariant Fourier descriptors; neural networks; optimal brain damage; preprocessing; semen quality assessment; Artificial neural networks; Biological neural networks; Data mining; Humans; Magnetic heads; Morphology; Neural networks; Quality assessment; Robustness; Shape;
Conference_Titel :
Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop
Conference_Location :
Ermioni
Print_ISBN :
0-7803-2026-3
DOI :
10.1109/NNSP.1994.366015
