Plant Image Segmentation for Biotic Damage Quantification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing technologies struggle to objectively and repeatably quantify biotic damage on crop plants, especially under non-ideal real-world conditions such as poor illumination and non-focused images.

Innovation Solution

A computer-implemented method that receives plant images and provides damage quantity indicators by segmenting the images to identify the aerial parts of the plant, using a convolutional neural network (CNN) to estimate damage, and applying regression techniques to quantify damage based on color changes and image processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If farmers manually quantify biotic damage on plants, then damage assessment can be performed, but the accuracy and repeatability vary between different farmers

Engineering Contradiction:

Improvedamage quantification accuracyVSAvoidmanual assessment dependency

Core Design Contradiction:

Measurement precisionVSExtent of automation

Solution Approach 1:

The system enables self-service damage quantification by automatically processing plant images through the computer. The computer independently performs segmentation, damage detection, and quantification without requiring human experts to manually assess each plant, thereby eliminating variability between different farmers' assessments while maintaining high accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical assessment process with an automated computer-based image processing system. The computer uses algorithms to automatically detect and quantify damage on plant leaves, substituting human visual inspection with computational analysis that provides consistent, repeatable results across different users and time points

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If images are taken under real-world field conditions, then plant damage can be captured, but poor illumination and focus reduce image quality

Engineering Contradiction:

Improvefield condition adaptabilityVSAvoidimage quality

Core Design Contradiction:

Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The system converts the harmful effects of poor illumination and out-of-focus images into beneficial processing opportunities. The computer's image processing algorithms are specifically designed to enhance low-quality images, extract relevant features despite blur, and compensate for poor lighting conditions, thereby transforming field condition limitations into workable input data for damage detection

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent applies parameter changes to image processing parameters to compensate for poor capture conditions. The computer adjusts processing parameters such as contrast enhancement, noise filtering, and feature detection sensitivity to optimize damage quantification from images taken under varying field conditions, maintaining accuracy despite variations in illumination and focus

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If the computer processes the entire plant image directly, then processing is simpler, but damage quantification accuracy decreases due to background interference

Engineering Contradiction:

Improveprocessing simplicityVSAvoiddamage quantification accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The computer implements segmentation by dividing the plant image into distinct regions: the plant region (containing stem, branches, and leaves) and the background region. This segmentation isolates the plant from interfering background elements, allowing the damage detection algorithms to focus exclusively on relevant areas and significantly improve quantification accuracy by eliminating false signals from the background

Inventive Principle:

Principle #1Segmentation

4Measurement precision

If detailed damage detection is performed on all plant parts, then comprehensive assessment is achieved, but processing time increases

Engineering Contradiction:

Improvedamage detection comprehensivenessVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies local quality by concentrating detailed damage detection efforts on specific plant regions where damage is most likely to occur and most visually apparent, particularly the leaves. The computer adjusts processing intensity and detection sensitivity based on the local characteristics of different plant parts, achieving comprehensive damage assessment while minimizing processing time by avoiding uniform high-intensity processing across all plant regions

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12307645B2Quantifying biotic damage on plants, by separating plant-images and subsequently operating a convolutional neural network

Publication Date: 2025.05.20 BASF SE

AI summary

In performing a computer-implemented method to quantify biotic damage in leaves of crop-plants, the computer receives a plant-image (410) showing a crop-plant, showing the aerial part of the plant, with stem, branches, and leaves and showing the ground on that the plant is placed. A segmenter module obtains a segmented plant-image being a contiguous set of pixels that shows in a contour (460A) of the aerial part, the contour (460A) having a margin region (458) that shows the ground partially. The computer uses convolutional neural network that processing the segmented plant-image by regression to obtain a damage degree, the convolutional neural network having been trained by processing damage-annotated segmented plant-images.