Automatic identification of weed seeds by color image processing

The analysis and classification of seeds are essential activities contributing to the final added value in the crop production. Besides varietal identification and cereal grain grading, it is also of interest in the agricultural industry the early identification of weeds from the analysis of strange...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Granitto, Pablo Miguel, Navone, Hugo Daniel, Verdes, Pablo Fabián, Ceccatto, Hermenegildo Alejandro
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2000
Materias:
Ciencias Informáticas
Patterns
Neural nets
Image processing software
Digitization and Image Capture
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23599
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23599
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Patterns
Neural nets
Image processing software
Digitization and Image Capture
spellingShingle Ciencias Informáticas
Patterns
Neural nets
Image processing software
Digitization and Image Capture
Granitto, Pablo Miguel
Navone, Hugo Daniel
Verdes, Pablo Fabián
Ceccatto, Hermenegildo Alejandro
Automatic identification of weed seeds by color image processing
topic_facet Ciencias Informáticas
Patterns
Neural nets
Image processing software
Digitization and Image Capture
description The analysis and classification of seeds are essential activities contributing to the final added value in the crop production. Besides varietal identification and cereal grain grading, it is also of interest in the agricultural industry the early identification of weeds from the analysis of strange seeds, with the purpose of chemically controlling their growth. The implementation of new methods for reliable and fast identification and classification of seeds is thus of major technical and economical importance. Like the manual identification work, the automatic classification of seeds should be based on knowledge of seed size, shape, color and texture. In this work we present a study of the discriminating power of morphological, color and textural characteristics of weed seeds, which can be measured from video images. This study was conducted on a large basis, considering images of weed seeds found in Argentina’s commercial seed production industry and listed by the Secretary of Agriculture as prohibited and primary- and secondary-tolerated weeds. We first describe the experimental setting and hardware used to capture the seed images. Then, we define the morphological, color and textural parameters measured from these images, and discuss the selection of the most relevant ones for identification purposes. Finally, we present results for the identification of test images obtained using a Naive Bayes classifier and a committee of Artificial Neural Networks.
format Objeto de conferencia
Objeto de conferencia
author Granitto, Pablo Miguel
Navone, Hugo Daniel
Verdes, Pablo Fabián
Ceccatto, Hermenegildo Alejandro
author_facet Granitto, Pablo Miguel
Navone, Hugo Daniel
Verdes, Pablo Fabián
Ceccatto, Hermenegildo Alejandro
author_sort Granitto, Pablo Miguel
title Automatic identification of weed seeds by color image processing
title_short Automatic identification of weed seeds by color image processing
title_full Automatic identification of weed seeds by color image processing
title_fullStr Automatic identification of weed seeds by color image processing
title_full_unstemmed Automatic identification of weed seeds by color image processing
title_sort automatic identification of weed seeds by color image processing
publishDate 2000
url http://sedici.unlp.edu.ar/handle/10915/23599
work_keys_str_mv AT granittopablomiguel automaticidentificationofweedseedsbycolorimageprocessing
AT navonehugodaniel automaticidentificationofweedseedsbycolorimageprocessing
AT verdespablofabian automaticidentificationofweedseedsbycolorimageprocessing
AT ceccattohermenegildoalejandro automaticidentificationofweedseedsbycolorimageprocessing
bdutipo_str Repositorios
_version_ 1764820466010161155

Ejemplares similares