• Journal of Korea Multimedia Society
• /
• v.10 no.10
• /
• pp.1271-1283
• /
• 2007

To detect defect of FPD(flat panel displays) is very difficult due to uneven illumination on FPD panel image. This paper presents a method to detect various types of defects using the approximated image of the uneven illumination by B-spline. To construct a approximated surface, corresponding to uneven illumination background intensity, while reducing random noises and small defect signal, only the lowest smooth subband is used by wavelet decomposition, resulting in reducing the computation time of taking B-spline approximation and enhancing detection accuracy. The approximated image in lowest LL subband is expanded as the same size as original one by wavelet reconstruction, and the difference between original image and reconstructed one becomes a flat image of compensating the uneven illumination background. A simple binary thresholding is then used to separate the defective regions from the subtracted image. Finally, blob analysis as post-processing is carried out to get rid of false defects. For applying in-line system, the wavelet transform by lifting based fast algorithm is implemented to deal with a huge size data such as film and the processing time is highly reduced.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.5
• /
• pp.746-754
• /
• 2008

This paper proposes a method to detect calibration patterns for accurate camera calibration under complicated backgrounds and uneven lighting conditions of industrial fields. Required to measure object dimensions, the preprocessing of camera calibration must be able to extract calibration points from a calibration pattern. However, industrial fields for visual inspection rarely provide the proper lighting conditions for camera calibration of a measurement system. In this paper, a probabilistic criterion is proposed to detect a local set of calibration points, which would guide the extraction of other calibration points in a cluttered background under irregular lighting conditions. If only a local part of the calibration pattern can be seen, input data can be extracted for camera calibration. In an experiment using real images, we verified that the method can be applied to camera calibration for poor quality images obtained under uneven illumination and cluttered background.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.10 no.1
• /
• pp.47-60
• /
• 2006

Due to the uneven illumination of FPD panel surface, it is difficult to detect the defects. The paper proposes a method to find the uneven illumination compensation using wavelets, which are done based on multi-resolution structure. The first step is to decompose the image into multi-resolution levels. Second, elimination of lowest smooth sub-image with highest frequency band removes the high frequency noise and low varying illumination. In particular, the main algorithm was implemented by lifting scheme for realtime inline process.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.575-586
• /
• 2022

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.

• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.9-17
• /
• 2009

License plate recognition is an active research area. but few comparative studies on license plate binarization have been conducted. Many related researchers have experienced similar trial and error for finding an effective binarization method. To reduce this trial and error, this study implemented some binarization methods and quantitatively compared the performance of the methods. The performance evaluation consists of a low level measure and a high level measure, so it can evaluate not only the quality of binarized image itself but also the usefulness of the result. The performance evaluation was separately performed with three groups of images so as to understand the properties of the binarization methods. Experimental results show that the quality of binarization is more dependent on the evenness of illumination than the intensity of illumination. The Otsu's method has acquired the most effective performance in the group of even illumination images and the Niblack's method with parameter correction has shown the best quality in the group of uneven illumination images.

• ETRI Journal
• /
• v.35 no.3
• /
• pp.491-500
• /
• 2013

A connected component analysis from a binary image is a popular character segmentation method but occasionally fails to segment the characters owing to image noise and uneven illumination. A multimethod binarization scheme that incorporates two or more binary images is a novel solution, but selection of binarization methods has never been analyzed before. This paper reveals the best combination of binarization methods and parameters and presents an in-depth analysis of the multimethod binarization scheme for better character segmentation. We carry out an extensive quantitative evaluation, which shows a significant improvement over conventional single-method binarization methods. Experiment results of six binarization methods and their combinations with different test images are presented.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.2
• /
• pp.307-313
• /
• 2008

In this paper, we propose a novel defects inspection algorithm for TFT-LCD panels. We first compensate the distorted image caused by the camera distortion and the uneven illumination environment using the least squares method and the bezier surface. We find a starting point of each pattern for restricting each pattern. A clean image is compared to each pattern to find defects using modified PCSR-G algorithm. The simulation example shows that our algorithm not only inspects the defects well, but also is robust to the 1-pixel error.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.149-150
• /
• 2007

In this paper, we propose a novel defects inspection algorithm for TFT-LCD panels. We first compensate the distorted image caused by the camera distortion and the uneven illumination environment using the least squares method and the bezier surface. We find a starting point of each pattern. The reference frame, made by subtract method using several clean patterns, is compared to each pattern to find defects. The simulation example shows that our algorithm not only inspects the defects well, but also is robust to the 1-pixel error.

• Smart Media Journal
• /
• v.2 no.1
• /
• pp.31-36
• /
• 2013

A robust and efficient text extraction is very important for an accuracy of Optical Character Recognition (OCR) systems. Natural scene images with degradations such as uneven illumination, perspective distortion, complex background and multi color text give many challenges to computer vision task, especially in text extraction. In this paper, we propose a method for extraction of the text in signboard images based on a combination of mean shift algorithm and weighting scheme of hue and saturation in HSI color space for clustering algorithm. The number of clusters is determined automatically by mean shift-based density estimation, in which local clusters are estimated by repeatedly searching for higher density points in feature vector space. Weighting scheme of hue and saturation is used for formulation a new distance measure in cylindrical coordinate for text extraction. The obtained experimental results through various natural scene images are presented to demonstrate the effectiveness of our approach.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11
• /
• pp.3165-3177
• /
• 1999

With the recent outstanding advance in computer software and hardware, a number of researches to enhance the manufacturing speed and the process accuracy has been undertaken in many fields of textile industry. Frequently issued problems of automatic recognition of textile wrinkles in a grey scale image are as follows. First, changes in grey level intensity of wrinkles are so minute. Second, as both colors and patterns in a grey scale image appear in grey level intensity, it is difficult to sort out the wrinkle information only. Third, it is also difficult to distinguish grey level intensity changed by wrinkles from those by uneven illumination. This paper suggests a method of automatic recognition of textile wrinkles that can solve above problems concerned with wrinkles, which can be raised in a manufacturing process as one of errors. In this paper, we first make the outline of wrinkles distinctly, apply the block matching algorithm used in motion estimation, and then estimate block locations of target images corresponding to blocks of standard images with the assumption that wrinkles are kind of textile distortions caused by directional forces. We plot a "wrinkle map" considering distances between wrinkles as depths of wrinkles. But because mismatch can occur by different illumination intensity and changes in tensions and directions of the force, there are also undesirable patterns in the map. Post processing is needed to filter them out and get wrinkles information only. We use average grey level intensity of wrinkle map to recognize wrinkles. When it comes to textile with colors and patterns, previous researches on wrinkles in grey scale image hasn't been successful. But we make it possible by considering wrinkles as distortion.istortion.