Recognition of seed varieties using a time-delay neural network: analysis of electrophoretic images

被引:8
作者
Jedra, M [1 ]
El Khattabi, N [1 ]
Limouri, M [1 ]
Essaid, A [1 ]
机构
[1] Fac Sci, Lab Concept & Syst, Rabat 10000, Morocco
关键词
seed varieties; neural networks; TDNN; electrophoresis;
D O I
10.1016/S0168-1699(98)00034-9
中图分类号
S [农业科学];
学科分类号
09 ;
摘要
This paper presents a method for seed variety recognition using one-dimensional electrophoresis gels. It employs the time-delay neural network (TDNN) which was initially developed for phoneme recognition. The TDNN can be trained to recognise the presence of a phoneme in speech by reference to the sound pattern over a sequence of time steps. Electrophoresis creates a set of bands in the gel, caused by migration of protein from the seed. Each seed variety generates a characteristic pattern. The bands are made visible by staining. They can then be imaged and digitised to create an input to a TDNN, which treats the variation with distance along the lane in the same way as the time sequence for which it was originally employed. In that way the characteristic signature of a seed variety can be recognised. A set of 30 images-each containing ten to 15 lanes-was used to train and test the performance of a TDNN in recognising ten cereal varieties. The network could achieve a recognition rate of 98%, provided that the gel was not distorted or cracked during heating or drying. Details of the design and training of the TDNN are given. (C) 1999 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:1 / 10
页数:10
相关论文
共 13 条
[1]  
ALLEN RC, 1984, GELS ELECTROPHORESIS
[2]  
[Anonymous], 1989, PRECIS ANAL IMAGES
[3]  
[Anonymous], B MATH BIOPHYS
[4]  
HAMES BD, 1981, GELS ELECTROPHORESIS
[5]  
Hebb D, 1949, ORG BEHAV
[6]  
HORAUD R, 1995, VISION ORDINATEUR OU
[7]  
Righetti P.G., 1983, LAB TECHNIQUES BIOCH, V11
[8]   THE PERCEPTRON - A PROBABILISTIC MODEL FOR INFORMATION-STORAGE AND ORGANIZATION IN THE BRAIN [J].
ROSENBLATT, F .
PSYCHOLOGICAL REVIEW, 1958, 65 (06) :386-408
[9]  
Rumelhart D. E., 1986, PARALLEL DISTRIBUTED, V1
[10]   LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS [J].
RUMELHART, DE ;
HINTON, GE ;
WILLIAMS, RJ .
NATURE, 1986, 323 (6088) :533-536