Identification and Classification of Snack-Type Watermelon (Citrullus lanatus) Genotypes Using Seed Morphology and
Uğur Ercan1, Sıtkı Ermiş2, Onder Kabas3
1Department of Informatics, Akdeniz University, 07070 Antalya, Türkiye.
Foods (Basel, Switzerland)
|December 11, 2025
Summary
Machine learning accurately identifies watermelon genotypes from seeds using morphological and color data. The Random Forest model achieved 92.22% accuracy, offering reliable genotypic classification for breeding and seed production.
Area of Science:
- Agricultural Science
- Computer Science
- Genetics
Background:
- Accurate genotypic identification of watermelon (Citrullus lanatus) seeds is crucial for breeding programs and commercial production.
- Traditional methods for seed identification can be time-consuming and may lack precision.
- Developing automated, non-destructive methods for genotypic classification is highly desirable.
Purpose of the Study:
- To evaluate the effectiveness of machine learning (ML) algorithms for automatic identification of watermelon genotypes based on seed characteristics.
- To compare the performance of Artificial Neural Network (ANN), Random Forest (RF), and Extra Tree (ET) models in classifying watermelon seeds.
- To determine if morphological, physical, and colorimetric seed attributes can reliably predict genotype.
Main Methods:
- Collected data from nine watermelon genotypes, analyzing 200 seeds per genotype.
- Extracted morphological (size, shape), physical (weight), and colorimetric (L, a, b) attributes using high-resolution imaging and digital measurement.
- Trained and validated ANN, RF, and ET models using a 10-fold cross-validation approach.
Main Results:
- The Random Forest (RF) model demonstrated the highest performance, achieving 92.22% accuracy, 91.87% F1-score, and 0.9118 Cohen's Kappa.
- Extra Tree (ET) and Artificial Neural Network (ANN) models showed lower accuracy at 90.00% and 86.11%, respectively.
- Statistical analysis confirmed RF and ET significantly outperformed ANN, with RF offering superior stability.
Conclusions:
- Machine learning frameworks provide a rapid, reliable, and non-destructive method for classifying snack-type watermelon seeds by genotype.
- These ML approaches have strong potential for improving varietal traceability in breeding, quality control in seed production, and meeting industrial demands.
- The study validates the use of seed morphological, physical, and colorimetric data for accurate genotypic classification.
More Related Videos
07:22Generating Homo- and Heterografts Between Watermelon and Bottle Gourd for the Study of Cold-responsive MicroRNAs
Published on: November 20, 2018
8.0K
11:48A Contrast of Three Inoculation Techniques used to Determine the Race of Unknown Fusarium oxysporum f.sp. niveum Isolates
Published on: October 28, 2021
3.7K
Related Concept Videos
02:16Light Acquisition
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
01:58Fruit Development, Structure, and Function
Fruits form from a mature flower ovary. As seeds develop from the ovules contained within, the ovary wall undergoes a series of complex changes to form fruit. In some fruits, such as soybeans, the ovary wall dries; in other fruits, such as grapes, it remains fleshy. In some cases, organs other than the ovary contribute to fruit formation; such fruits are called accessory fruits.
01:59Plant Breeding and Biotechnology
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.
01:28Methods of Classification and Identification
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...