Exploring Nutrient Deficiencies in Lettuce Crops: Utilizing Advanced Multidimensional Image Analysis for Precision...

Area of Science:

• Agricultural Science
• Computer Vision
• Image Processing

Background:

• Lettuce growth, yield, and quality are significantly affected by nutrient deficiencies.
• Traditional nutrient detection methods are time-consuming, labor-intensive, and lack automation.
• Accurate and rapid diagnosis of crop nutrient status is crucial for effective agricultural management.

Purpose of the Study:

• To develop an automated system for detecting nutrient deficiencies in lettuce.
• To improve the accuracy and efficiency of crop nutrient diagnosis.
• To provide a reliable method for rapid identification of nutrient-impaired lettuce.

Main Methods:

• Development of a lettuce nutrient deficiency detection system utilizing multi-dimensional image analysis and Field-Programmable Gate Arrays (FPGA).
• Application of image preprocessing techniques including dynamic window histogram median filtering and adaptive contrast enhancement.
• Implementation of advanced image segmentation algorithms (threshold segmentation, Canny edge detection, gradient-guided adaptive threshold segmentation) for tissue differentiation.
• Quantitative assessment of nutrient deficiency based on the proportion of affected tissue identified in images.

Main Results:

• The developed system demonstrated high performance in detecting nutrient deficiencies across various lettuce growth stages.
• Achieved an average precision of 0.944, recall rate of 0.943, and F1 score of 0.943.
• Significantly improved automation, accuracy, and detection efficiency compared to traditional methods.
• Minimized sample interference, ensuring reliable diagnostic outcomes.

Conclusions:

• The developed system offers a reliable and efficient solution for the rapid diagnosis of nutrient deficiencies in lettuce.
• The integration of multi-dimensional image analysis and FPGA technology enhances the precision and automation of crop nutrient assessment.
• This technology has the potential to optimize agricultural practices and improve crop production outcomes.