Out-of-Focus Image Deblurring for Mobile Display Vision Inspection

In vision inspection tasks, moiré patterns caused by frequency aliasing can severely degrade image quality. To prevent moiré patterns, we used images that were intentionally out-of-focused, and we performed deblurring to restore details during the acquisition of the images. As existing deblurring methods fail to output satisfactory results for low-contrast Mura images, we applied some simple techniques, minimum-maximum normalization, and edge mask fine-tuning to one of the state-of-the-art non-blind deblurring methods by utilizing parametric generalized Gaussian kernels. Structural image details were preserved through edge mask fine-tuning, and image contrast was improved with minimum-maximum normalization. By parameterizing the blur kernel as a generalized Gaussian kernel, we greatly improved the robustness of the blind image deblurring. We evaluated the effects of each module by conducting thorough experiments. The proposed method showed better performance than existing blind deblurring methods for blur-specific no-reference metrics, the image profile, and frequency domain analysis.

I. Introduction

In the manufacturing of organic light-emitting diode (OLED) or liquid crystal display (LCD) panels, the Mura defect, also called a stain defect occurs quite frequently [1]. The defect is very difficult to detect via the naked eye because it has a contrast that is similar to the background, and it consists of various sizes, from very small (a few pixels) to very large (covering half of panel). Currently, camera inspection is the most popular method for obtaining accurate functional defect identification [2], [3], [4], [5]. However, one of the greatest problems in camera inspection is that captured images are often contaminated with moiré patterns as shown in Fig. 1(a). Fig. 1.

Mobile display Mura images taken using various camera settings. (a) Mura image with a moiré pattern taken by an in-focus camera, (b) blurred Mura image without a moiré pattern taken by an out-of-focus camera, and (c) deblurred result using the proposed method.