01337naa a2200193 a 450000100080000000500110000800800410001910000200006024500690008026000090014952006700015865000120082865300330084065300190087365300230089265300280091570000190094377301810096215804982010-01-14       2002    bl ---       0--  u    #d1 aCRUVINEL, P. E.  aImage processing in automated pattern classification of oranges.  c2002  aA rapid method for automated classification of oranges in living trees by size has been developed. It is based on image processing with correlation analysis in the frequency domain. This technique has the advantage of being a direct measurement method that automatically idenfies and counts oranges for quality control. Calibration was performed using standard imae with known orange sizes. Orange's sizes, ranging from less then 2 cm to over 10 cm in diameter have been automatically recognized and successfully measured. Error was not larger than 1.4%. In addition, practical examples of use of the method for determining characteristics of oranges are presented.  aLaranja  aAgricultural instrumentation  aMachine vision  aOrange measurement  aProcessamento de imagem1 aMINATEL, E. R.  tIn: WORLD CONGRESS OF COMPUTERS IN AGRICULTURE AND NATURAL RESOURCES, 2001, Iguaçu Falls. Proceedings... St. Joseph: American Society of Agricultural Engineers, 2002. p.56-61.