Plant Disease Detection Using Color Normalization and Bayesian Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-based diagnostic methods for plant diseases require high computational effort and are less reliable due to variability in illumination conditions and the inability to adapt to changes in photography settings, leading to inconsistent disease detection.
Innovation Solution
A system that combines image processing techniques with statistical inference methods, utilizing color normalization, segmentation, and Bayesian filtering to efficiently detect plant diseases by reducing data processing and improving reliability through color constancy and machine learning-based analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If image processing techniques are used to detect plant diseases, then disease detection capability is improved, but computational effort increases significantly
Solution Approach 1:
The patent segments the image processing task into distinct stages: color normalization to handle illumination variability, feature extraction to identify relevant visual characteristics, and classification to diagnose diseases. This segmentation allows each stage to be optimized independently, reducing overall computational burden while maintaining detection accuracy.
Solution Approach 2:
The patent applies color normalization as a preliminary action before disease detection. By pre-processing images to correct for illumination and photography changes, the system reduces the complexity of subsequent disease identification tasks, thereby lowering computational effort required for the main detection algorithm.
2Speed
If traditional image processing methods are applied without adaptation, then processing speed is maintained, but reliability decreases due to illumination variability
Solution Approach 1:
The patent implements dynamic adaptation through color normalization that adjusts processing parameters based on the specific illumination conditions of each image. The system dynamically corrects for varying light conditions and photography settings, maintaining high reliability across different environmental conditions without sacrificing processing speed through efficient algorithm design.
3Adaptability or versatility
If multiple disease candidates are detected and analyzed separately, then detection coverage is improved, but reliability decreases due to lack of global disease presence determination
Solution Approach 1:
The patent merges multiple disease candidate analyses into a unified classification framework. Instead of treating each detected candidate independently, the system combines evidence from multiple sources and stages of processing to determine global disease presence, thereby improving reliability while maintaining comprehensive detection coverage.
Data Source
AI summary
A system (100), method and computer program product for determining plant diseases. The system includes an interface module (110) configured to receive an image (10) of a plant, the image (10) including a visual representation (11) of at least one plant element (1). A color normalization module (120) is configured to apply a color constancy method to the received image (10) to generate a color-normalized image. An extractor module (130) is configured to extract one or more image portions (11e) from the color-normalized image wherein the extracted image portions (11e) correspond to the at least one plant element (1). A filtering module (140) configured: to identify one or more clusters (C1 to Cn) by one or more visual features within the extracted image portions (11e) wherein each cluster is associated with a plant element portion showing characteristics of a plant disease; and to filter one or more candidate regions from the identified one or more clusters (C1 to Cn) according to a predefined threshold, by using a Bayes classifier that models visual feature statistics which are always present on a diseased plant image. A plant disease diagnosis module (150) configured to extract, by using a statistical inference method, from each candidate region (C4, C5, C6, Cn) one or more visual features to determine for each candidate region one or more probabilities indicating a particular disease; and to compute a confidence score (CS1) for the particular disease by evaluating all determined probabilities of the candidate regions (C4, C5, C6, Cn).