Laser-induced backscattering imaging for classification of seeded and seedless watermelons

•Classification of watermelon samples based on the backscattering parameters.•Seeded and seedless watermelons were classified using principal component analysis.•PCA classification of watermelons can be done by using backscattering imaging. This paper evaluates the feasibility of laser-induced backs...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers and electronics in agriculture Ročník 140; s. 311 - 316
Hlavní autoři: Mohd Ali, Maimunah, Hashim, Norhashila, Bejo, Siti Khairunniza, Shamsudin, Rosnah
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.08.2017
Elsevier BV
Témata:
Algorithms
Backscattering
Backscattering imaging
data collection
Datasets
Discriminant analysis
Feasibility studies
Fruits
image analysis
Image classification
Imaging
Laser light
Lasers
Pattern recognition
Pattern recognition algorithm
principal component analysis
Principal components analysis
Scattering
Storage
Watermelon
watermelons
Backscattering imaging
Pattern recognition algorithm
Laser light
Storage
Watermelon
ISSN:0168-1699, 1872-7107
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Classification of watermelon samples based on the backscattering parameters.•Seeded and seedless watermelons were classified using principal component analysis.•PCA classification of watermelons can be done by using backscattering imaging. This paper evaluates the feasibility of laser-induced backscattering imaging for the classification of seeded and seedless watermelons during storage. Backscattering images were obtained from seeded and seedless watermelon samples through a laser diode emitting at 658nm using a backscattering imaging system developed for the purpose. The pre-processed datasets extracted from the backscattering images were analysed using principal component analysis (PCA). The datasets were separated into training (75%) and testing (25%) datasets as the inputs in the classification algorithms. Three multivariate pattern recognition algorithms were used including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and k-nearest neighbour (kNN). The QDA-based algorithms obtained the highest overall average classification accuracies (100%) for both the seeded and seedless watermelons. The LDA and kNN-based algorithms also obtained quite high classification accuracies with all the accuracies above 90%. The laser-induced backscattering imaging technique is potentially useful for classification of seeded and seedless watermelons.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2017.06.010