Related Experiment Video
Updated: Sep 6, 2025
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
Published on: March 28, 2025
Identification of Maize with Different Moldy Levels Based on Catalase Activity and Data Fusion of Hyperspectral
Wenchao Wang1,2, Wenqian Huang2, Huishan Yu1
1College of Physical Science and Information Engineering, Liaocheng University, Liaocheng 252000, China.
Abstract:
Maize is susceptible to mold infection during growth and storage due to its large embryo and high moisture content. Therefore, it is essential to distinguish the moldy sample from healthy groups to prevent the spread of mold and avoid huger economic losses. Catalase is a metabolite in the growth of microorganisms; hence, all maize samples were accurately divided into four moldy grades (health, mild, moderate, and severe levels) by determining their catalase activity. The visible and shortwave near-infrared (Vis-SWNIR) and longwave near-infrared (LWNIR) hyperspectral images were investigated to jointly identify the moldy levels of maize. Spectra and texture information of each maize sample were extracted and used to build the classification models of maize with different moldy levels in pixel-level fusion and feature-level fusion. The result showed that the feature-level fusion of spectral and texture within Vis-SWNIR and LWNIR regions achieved the best results, overall prediction accuracy reached 95.00% for each moldy level, all healthy maize was correctly classified, and none of the moldy samples were misclassified as healthy level. This study illustrated that two hyperspectral image systems, with complementary spectral ranges, combined with feature selection and data fusion strategies, could be used synergistically to improve the classification accuracy of maize with different moldy levels.
Insights
Accurate mold detection in maize is crucial for preventing spoilage and economic loss. Combining visible and near-infrared hyperspectral imaging with feature fusion effectively classifies moldy maize with 95% accuracy.
Area of Science:
- Agricultural Science
- Food Science
- Spectroscopy
Background:
- Maize is prone to mold contamination due to its high moisture content and large embryo.
- Moldy maize poses significant risks, including health hazards and substantial economic losses.
- Early and accurate detection of mold is essential for food safety and quality control.
Purpose of the Study:
- To develop and evaluate a method for classifying different levels of mold contamination in maize.
- To investigate the synergistic potential of combining visible and near-infrared hyperspectral imaging for mold detection.
- To assess the efficacy of feature-level fusion of spectral and texture data for improved classification accuracy.
Main Methods:
- Maize samples were categorized into four moldy grades (healthy, mild, moderate, severe) based on catalase activity.
- Visible and shortwave near-infrared (Vis-SWNIR) and longwave near-infrared (LWNIR) hyperspectral imaging were employed.
- Spectral and texture information were extracted and fused at the feature level to build classification models.
Main Results:
- Feature-level fusion of spectral and texture data from Vis-SWNIR and LWNIR regions yielded the highest classification accuracy.
- The optimal model achieved an overall prediction accuracy of 95.00% for each moldy level.
- All healthy maize samples were correctly identified, and no moldy samples were misclassified as healthy.
Conclusions:
- The combined use of complementary hyperspectral imaging systems enhances the accuracy of moldy maize classification.
- Feature selection and data fusion strategies are critical for maximizing classification performance.
- This approach offers a promising non-destructive method for assessing maize mold contamination levels.
