Detection and classification of CCD defects with an artificial neural network

Details Detection and classification of CCD defects with an artificial neural network Detection and classification of CCD defects with an artificial neural network

May 1994

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=1994pasp..106..532r&link_type=abstract

Astronomical Society of the Pacific, Publications (ISSN 0004-6280), vol. 106, no. 699, p. 532-541

Statistics

Applications

3

Algorithms, Charge Coupled Devices, Defects, Image Classification, Image Processing, Mathematical Models, Neural Nets, Conjugate Gradient Method, Feedforward Control, Telescopes, Training Devices

Scientific paper

We have developed an artificial neural-network (ANN) system which locates and classifies defects in CCDs. This system, based on a feedforward neural network, was trained with a conjugate gradient training algorithm using observational data from an astronomical telesope. The network was tested with data from four large CCDs (2048 x 2048 pixels each) and found defects with a higher efficiency and in a much shorter time than human inspectors. This method of detecting and classifying objects in images is quite general and we discuss other applications in astronomy. In an appendix we provide a recipe for neural computing to make this technique more acessible to the astronomical community.

Affiliated with

Also associated with

No associations

Rating

Detection and classification of CCD defects with an artificial neural network does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Detection and classification of CCD defects with an artificial neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Detection and classification of CCD defects with an artificial neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1680758