Image Defect Cause Detection Using Feature Image Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the cause of image defects in image forming devices face challenges such as high computational demands and the need for extensive training data, leading to inaccurate or omitted determinations.
Innovation Solution
An image processing method that generates feature images from a test image using a processor, followed by pattern recognition to identify the cause of defects, reducing computational load while maintaining accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pattern recognition process is executed on the entire test image to accurately determine the cause of image defects, then determination accuracy is improved, but computational load becomes excessively large
Solution Approach 1:
The test image is divided into multiple regions of interest (ROIs) based on detected defect positions and types. Pattern recognition is then executed only on these specific ROIs rather than the entire image, significantly reducing computational load while maintaining determination accuracy for the defective areas.
Solution Approach 2:
Different processing approaches are applied to different regions of the image. High-accuracy pattern recognition is concentrated on defect-containing ROIs, while other areas receive minimal or no processing, optimizing the balance between accuracy and computational efficiency.
2Power
If threshold-based parameter comparison is used to determine image defect causes, then computational load is reduced, but determination accuracy decreases due to omission or erroneous determination
Solution Approach 1:
Instead of applying full pattern recognition to the entire image (excessive action), the system applies it only to necessary regions (partial action). This selective approach maintains sufficient determination accuracy while avoiding the computational burden of processing the complete image.
3Measurement precision
If enormous amount of training data is prepared to increase determination accuracy, then accuracy is improved, but time and effort required for data preparation increases significantly
Solution Approach 1:
The training data requirement is segmented by focusing on specific defect types and their corresponding image regions. Instead of requiring comprehensive training data for all possible image conditions, the system trains on targeted datasets relevant to specific defect scenarios, reducing overall data preparation time while maintaining accuracy for those defect types.
Data Source
AI summary
An object of the present invention is to determine the cause of an image defect that occurs in an image forming device with high accuracy while suppressing the amount of calculation at a processor. A processor (80) determines the cause of an image defect on the basis of a test image read from an output sheet of an image forming device (2). The processor (80) generates a plurality of feature images by executing a feature extraction process on the test image. Further, the processor (80) uses each of the plurality of feature images as an input image and determines which of a plurality of cause candidates corresponding to the image defect the input image corresponds to by pattern recognition of the input image.