Use of genetic artificial neural networks and spectral imaging for defect detection on cherries

Abstract A machine vision system was created to identify different types of tissue characteristics on cherries. It consists of an enhanced NIR range vidicon black and white camera (sensing range 400–2000 nm), a monochrometer controlled light source, and a computer. Multiple spectral images of cherry samples were collected over the 680–1280 nm range at increments of 40 nm. Using the spectral signatures of different tissues on cherry images, artificial neural networks were applied to pixel-wise classification. An enhanced genetic algorithm was applied to design the topology and evolve the weights for multi-layer feed forward artificial neural networks. An average of 73% classification accuracy was achieved for correct identification as well as quantification of all types of cherry defects. No false positives or false negatives occurred, errors resulted only from misclassification of defect type or quantification of defect.

[1]  J. A. Throop,et al.  OPTICAL DETECTION OF BRUISES AND EARLY FROST DAMAGE ON APPLES , 1991 .

[2]  L. Segerlind,et al.  Near-Infrared Reflectance of Bruised Apples , 1974 .

[3]  W. S. Reid.  Optical detection of apple skin, bruise, flesh, stem and calyx , 1976 .

[4]  Richard G. Leffler,et al.  Near Infrared Analysis of Soluble Solids in Intact Cantaloupe , 1989 .

[5]  Q. Yang,et al.  The potential for applying machine vision to defect detection in fruit and vegetable grading , 1992 .

[6]  C. T. Morrow,et al.  Computer vision sorting of potatoes , 1987 .

[7]  S. Grossberg,et al.  Neural networks for vision and image processing , 1992 .

[8]  F. Sevila,et al.  Automatic detection of surface defects on fruit by using a vision system , 1988 .

[9]  M. J. Delwiche,et al.  PRUNE DEFECT DETECTION BY LINE-SCAN IMAGING , 1990 .

[10]  John A. Marchant,et al.  Accurate blemish detection with active contour models , 1996 .

[11]  George E. Meyer,et al.  Optics in Agriculture and Forestry , 1993 .

[12]  Gerald S. Birth,et al.  RADIOMETRIC MEASUREMENT OF FOOD QUALITY‐A REVIEW , 1979 .

[13]  George C. Stockman,et al.  Tissue reflectance and machine vision for automated sweet cherry sorting , 1996, Other Conferences.

[14]  Q. Yang,et al.  An approach to apple surface feature detection by machine vision , 1994 .

[15]  M. J. Delwiche,et al.  PEACH DEFECT DETECTION WITH MACHINE VISION , 1991 .

[16]  Gerald E. Rehkugler,et al.  Image Processing Algorithm for Apple Defect Detection , 1987 .

[17]  C.M.W. Daft.  Neural networks for image analysis , 1990, IEEE Symposium on Ultrasonics.

[18]  Steven K. Rogers,et al.  An Introduction to Biological and Artificial Neural Networks for Pattern Recognition , 1991 .

[19]  A. Lynn Abbott,et al.  Machine vision using artificial neural networks with local 3D neighborhoods , 1997 .

[20]  James A. Throop,et al.  Time effects on near-infrared imaging for detecting bruises on apples , 1993, Other Conferences.

[21]  M. J. Delwiche,et al.  Spectral analysis of peach surface defects. , 1990 .

[22]  B. Upchurch,et al.  Pattern recognition models for spectral reflectance evaluation of apple blemishes , 1998 .

[23]  C. T. Morrow,et al.  Comparison of a Neural Network and Traditional Classifier for Machine Vision Inspection of Potatoes , 1995 .

[24]  James A. Throop,et al.  Considerations for implementing machine vision for detecting watercore in apples , 1993, Other Conferences.

[25]  P. Williams,et al.  Near-Infrared Technology in the Agricultural and Food Industries , 1987 .