Print Inspection Using Gray Scale Erosion Filters for Warped Media
Solution Overview
Problem
Conventional inspection methods for printed matters struggle to accurately detect defects under conditions of positional displacement, warping, or varying imaging conditions, particularly when printed matters are conveyed independently or have different contours due to punching or die cutting, leading to missed detection of minor defects.
Innovation Solution
The method involves applying a gray scale erosion or dilation filter to a non-defect image, adjusting density values, and using a density compensation process to create a differential image, followed by edge detection and binary conversion, which helps reduce the impact of positional displacement and warping, enabling accurate defect detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional inspection methods are used with simple differential image conversion, then the inspection process is simple and fast, but detection accuracy deteriorates under positional displacement and warping conditions
Solution Approach 1:
The patent applies preliminary action by pre-processing the reference image with gray scale erosion or dilation filters before differential conversion. This preliminary modification of the reference image compensates for expected positional displacements and warping, allowing accurate defect detection without requiring complex real-time alignment algorithms during the actual inspection process.
Solution Approach 2:
The patent changes the parameter of image density by applying gray scale erosion or dilation filters to the reference image, thereby modifying the density distribution to account for positional displacement and warping. This parameter transformation enables the differential image to accurately represent defects even when the printed matter is displaced or warped during conveyance.
2Measurement precision
If masking is applied to remove edge regions with sharp density changes, then positional displacement errors are reduced, but inspection coverage deteriorates by removing potentially defective regions
Solution Approach 1:
Instead of masking edge regions, the patent applies gray scale erosion or dilation filters that modify the density parameters across the entire image. This parameter transformation naturally handles edge regions without requiring explicit masking, thereby maintaining full inspection coverage while still compensating for positional displacement and warping effects.
3Measurement precision
If gray scale erosion or dilation filters are applied to the reference image, then detection accuracy improves under displacement conditions, but processing time increases
Solution Approach 1:
The patent performs the computationally intensive gray scale erosion or dilation filter application in advance on the reference image, before the actual defect inspection. This preliminary action shifts the processing burden from real-time inspection to pre-processing, thereby maintaining high detection accuracy under displacement conditions while minimizing processing time during the actual inspection process.
Data Source
AI summary
A method of inspecting a defect on a surface of a printed matter includes a step of applying a gray scale erosion filter to a non-defect surface of a printed matter to prepare a gray scale erosion filter applied image and then adding a predetermined density value to the gray scale erosion filter applied image, thereby preparing a reference image, a step of subtracting a captured image of the surface of the printed matter to be inspected from the reference image, thereby preparing a differential image, and a step of applying a density compensation process to the differential image to prepare a density compensated image, then applying an edge detection filter to the density compensated image to prepare an edge detection filter applied image and then converting the edge detection filter applied image into binary data according to a predetermined threshold value.