• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.715-717
• /
• 2004

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on a recursive error back-projection of top-down machine learning. A face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes, In addition to, a recursive error back-projection is applied to improve the accuracy of synthesized high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution one captured at a distance.

• Imaging Science in Dentistry
• /
• v.43 no.3
• /
• pp.145-151
• /
• 2013

Purpose: This study was performed to evaluate and compare the radiopacity of dentin, enamel, and 8 restorative composites on conventional radiograph and digital images with different resolutions. Materials and Methods: Specimens were fabricated from 8 materials and human molars were longitudinally sectioned 1.0 mm thick to include both enamel and dentin. The specimens and tooth sections were imaged by conventional radiograph using #4 sized intraoral film and digital images were taken in high speed and high resolution modes using a phosphor storage plate. Densitometric evaluation of the enamel, dentin, restorative materials, a lead sheet, and an aluminum step wedge was performed on the radiographic images. For the evaluation, the Al equivalent (mm) for each material was calculated. The data were analyzed using one-way ANOVA and Tukey's test (p<0.05), considering the material factor and then the radiographic method factor, individually. Results: The high speed mode allowed the highest radiopacity, while the high resolution mode generated the lowest values. Furthermore, the high resolution mode was the most efficient method for radiographic differentiation between restorative composites and dentin. The conventional radiograph was the most effective in enabling differentiation between enamel and composites. The high speed mode was the least effective in enabling radiographic differentiation between the dental tissues and restorative composites. Conclusion: The high speed mode of digital imaging was not effective for differentiation between enamel and composites. This made it less effective than the high resolution mode and conventional radiographs. All of the composites evaluated showed radiopacity values that fit the ISO 4049 recommendations.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.1-7
• /
• 2023

Large-size, organic light-emitting device (OLED) panels based on highly reliable gate driver circuits integrated using InGaZnO thin film transistors (TFTs) were developed to achieve ultra-high resolution TVs. These large-size OLED panels were driven by using a novel gate driver circuit not only for displaying images but also for sensing TFT characteristics for external compensation. Regardless of the negative threshold voltage of the TFTs, the proposed gate driver circuit in OLED panels functioned precisely, resulting from a decrease in the leakage current. The falling time of the circuit is approximately 0.9 ㎲, which is fast enough to drive 8K resolution OLED displays at 120 Hz. 120 Hz is most commonly used as the operating voltage because images consisting of 120 frames per second can be quickly shown on the display panel without any image sticking. The reliability tests showed that the lifetime of the proposed integrated gate driver is at least 100,000 h.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.98-101
• /
• 2019

At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.515-517
• /
• 2007

In this study we attempted to estimate damage scope such as bridges destruction, farmland deformation, forest damage, etc occurred by typhoon using two digital aerial images for future high-resolution Kompsat-3 applications. The process procedures are followings: First, image registration between time-different aerial images was implemented. In this process one image was geometrically corrected by image-to-image registration. Second, image classification was done according to 4 classes. Finally through the comparison of classified two images the area of damage by flood and storm was approximately calculated. These results showed that it is possible to estimate the damage scale relatively rapidly using high-resolution images.

• 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.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.1
• /
• pp.19-27
• /
• 2014

Compressive sensing is an emerging sampling technique which enables sampling a signal at a much lower rate than the Nyquist rate. In this paper, we propose a novel framework based on Kronecker compressive sensing that provides multi-resolution image reconstruction capability. By exploiting the relationship of the sensing matrices between low and high resolution images, the proposed method can reconstruct both high and low resolution images from a single measurement vector. Furthermore, post-processing using BM3D improves its recovery performance. The experimental results showed that the proposed scheme provides significant gains over the conventional framework with respect to the objective and subjective qualities.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.295-302
• /
• 2010

Example-based super resolution(EBSR) is a method to reconstruct high-resolution images by learning patch-wise correspondence between high-resolution and low-resolution images. It can reconstruct a high-resolution from just a single low-resolution image. However, when it is applied to a text image whose font type and size are different from those of training images, it often produces lots of noise. The primary reason is that, in the patch matching step of the reconstruction process, input patches can be inappropriately matched to the high-resolution patches in the patch dictionary. In this paper, we propose a new patch matching method to overcome this problem. Using an image observation model, it preserves the correlation between the input and the output images. Therefore, it effectively suppresses spurious noise caused by inappropriately matched patches. This does not only improve the quality of the output image but also allows the system to use a huge dictionary containing a variety of font types and sizes, which significantly improves the adaptability to variation in font type and size. In experiments, the proposed method outperformed conventional methods in reconstruction of multi-font and multi-size images. Moreover, it improved recognition performance from 88.58% to 93.54%, which confirms the practical effect of the proposed method on recognition performance.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.266-274
• /
• 2007

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on top-down machine learning and recursive error back-projection. A face is represented by a linear combination of prototypes of shape and that of texture. With the shape and texture information of each pixel in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those that of texture by solving least square minimizations. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. In addition, a recursive error back-projection procedure is applied to improve the reconstruction accuracy of high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution images captured at a distance.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.85-92
• /
• 2022

In this paper, we propose a technique that can express low-resolution hair and fur simulations in high-resolution without noise using ConvNet and geometric images of strands in the form of lines. Pairs between low-resolution and high-resolution data can be obtained through physics-based simulation, and a low-resolution-high-resolution data pair is established using the obtained data. The data used for training is used by converting the position of the hair strands into a geometric image. The hair and fur network proposed in this paper is used for an image synthesizer that upscales a low-resolution image to a high-resolution image. If the high-resolution geometry image obtained as a result of the test is converted back to high-resolution hair, it is possible to express the elastic movement of hair, which is difficult to express with a single mapping function. As for the performance of the synthesis result, it showed faster performance than the traditional physics-based simulation, and it can be easily executed without knowing complex numerical analysis.