<title>Image quality in automated visual web inspection</title>

Abstract

In this study the relation between the performance of an imaging unit of a web inspection system and the final image quality is discussed. The basic idea is to analyze the results of the segmentation and feature extraction of defects in sample images as a function of imaging parameters. Determination of the quality of imaging and examples of the performance of a typical imaging unit are reviewed. The effect of the image quality on segmentation of the defects and feature extraction is analyzed in two cases: 1. The detection of small and low-contrast defects in paper inspection and 2. the depth of field considerations in steel inspection. Samples picked from the industrial manufacturing process are imaged using different imaging parameters and the defect areas in the images are segmented in order to illustrate the dependence of the system performance on the quality of imaging. Several segmentation methods are applied. These include direct thresholding, edge-based filtering, matched filtering and morphological filtering. The contrast of certain type of defects can be improved before segmentation by averaging the input data line by line. The signal processing methods presented here are computationally simple due to the need for highspeed real-time implementation in practical inspection.

Ultrafast dark-field surface inspection with hybrid-dispersion laser scanning

“…More specifically, the scan rate of the line scanner is limited by the frame rate (readout rate) of the complementary metal-oxide-semiconductor (CMOS) image sensor up to $100 000 frames per second. [4][5][6] Since in most settings of manufacturing, the frame rate of the inspection system is the limiting factor of the entire manufacturing process, it is critical to improve the speed of surface inspection for further cost reduction in manufacturing. 8 Such a speed increase is expected to enable high-performance, low-cost manufacturing of organic light-emitting diode (LED) displays for next-generation smart phones, lithium-ion batteries for green electronics, and high-efficiency solar cells.…”

Real-Time Vision-Based System for Textile Fabric Inspection

“…Table 3. Geometric features from Table 1 for defects from Figure 5, obtained from Figure 5 Black horizontal error c 6 White horizontal error c 7 Black spot c 8 White spot…”

“…The Radon transform is used for feature extraction and fuzzy logic is implemented for rating. A method for detecting low contrast defects is described in [7]. Four separate segmentation methods are considered.…”

Image-based classification of defects in frontal surface of fluted ingot

“…Vision-based inspection [1,2] of industrial products offers low-cost, high-speed and high-quality detection of defects. Automated visual inspection of materials, woven or non-woven, such as paper [3], steel roll [4], wood [5,6], carpet [7], textile fabric [8], etc., has been used for defect detection and quality assurance.…”