• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.71-76
• /
• 2020

In this paper, we propose a super-resolution method that reconstructs compressed low-resolution images into high-resolution images. We propose a CNN model with a small number of parameters, and even if quantization is applied to the proposed model, super-resolution can be implemented without deteriorating the image quality. To further improve the quality of the compressed low-resolution image, a new degradation model was proposed instead of the existing bicubic degradation model. The proposed degradation model is used only in the training process and can be applied by changing only the parameter values to the original CNN model. In the super-resolution image applying the proposed degradation model, visual artifacts caused by image compression were effectively removed. As a result, our proposed method generates higher PSNR values at compressed images and shows better visual quality, compared to conventional CNN-based SR methods.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.95-101
• /
• 2019

Recently, there have been many issues related to text recognition using Tesseract. One of these issues is that the text recognition accuracy is significantly lower for smaller fonts. Tesseract extracts text by creating an outline with direction in the image. By searching the Tesseract database, template matching with characters with similar feature points is used to select the character with the lowest error. Because of the poor text extraction, the recognition accuracy is lowerd. In this paper, we compared text recognition accuracy after applying various super-resolution methods to smaller text images and experimented with how the recognition accuracy varies for various image size. In order to recognize small Korean text images, we have used super-resolution algorithms based on deep learning models such as SRCNN, ESRCNN, DSRCNN, and DCSCN. The dataset for training and testing consisted of Korean-based scanned images. The images was resized from 0.5 times to 0.8 times with 12pt font size. The experiment was performed on x0.5 resized images, and the experimental result showed that DCSCN super-resolution is the most efficient method to reduce precision error rate by 7.8%, and reduce the recall error rate by 8.4%. The experimental results have demonstrated that the accuracy of text recognition for smaller Korean fonts can be improved by adding super-resolution methods to the OCR preprocessing module.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.17-22
• /
• 2021

Recently, image super-resolution techniques used in convolutional neural networks (CNN) have led to remarkable performance in the research area of digital image processing applications and computer vision tasks. Convolutional layers stacked on top of each other can design a more complex network architecture, but they also use more memory in terms of the number of parameters and introduce the vanishing gradient problem during training. Furthermore, earlier approaches of single image super-resolution used interpolation technique as a pre-processing stage to upscale the low-resolution image into HR image. The design of these approaches is simple, but not effective and insert the newer unwanted pixels (noises) in the reconstructed HR image. In this paper, authors are propose a novel single image super-resolution architecture based on synchronized depthwise separable convolution with Dense Skip Connection Block (DSCB). In addition, unlike existing SR methods that only rely on single path, but our proposed method used the synchronizes path for generating the SISR image. Extensive quantitative and qualitative experiments show that our method (SDCN) achieves promising improvements than other state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.116-119
• /
• 2005

As to the synthetical estimation of land covering parameters or the compounded land covering classification for multi-resolution satellite data, former researches mainly adopted linear or nonlinear regression models to describe the regression relationship of land covering parameters caused by the degradation of spatial resolution, in order to improve the retrieval accuracy of global land covering parameters based on 1;he lower resolution satellite data. However, these methods can't authentically represent the complementary characteristics of spatial resolutions among different satellite data at arithmetic level. To resolve the problem above, a new compounded land covering classification method at arithmetic level for multi-resolution satellite data is proposed in this .paper. Firstly, on the basis of unsupervised clustering analysis of the higher resolution satellite data, the likelihood distribution scatterplot of each cover type is obtained according to multiple-to-single spatial correspondence between the higher and lower resolution satellite data in some local test regions, then Parzen window approach is adopted to derive the real likelihood functions from the scatterplots, and finally the likelihood functions are extended from the local test regions to the full covering area of the lower resolution satellite data and the global covering area of the lower resolution satellite is classified under the maximum likelihood rule. Some experimental results indicate that this proposed compounded method can improve the classification accuracy of large-scale lower resolution satellite data with the support of some local-area higher resolution satellite data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1124-1132
• /
• 2009

We proposed a new method to improve the resolution of elemental image set in the integral imaging system using super-resolution image reconstruction method. Adjacent elemental images have same image region which is projected from the common area of object. These projected images in the elemental image can be used for low resolution images of super-resolution method. Two methods for resolution improvement of elemental image set using super-resolution method are proposed. One is super-resolution among the elemental image sets and the other is among the elemental images. Simulation results are compared with resolution improved elemental image set using interpolated method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.2
• /
• pp.169-174
• /
• 2013

In counterfire warfare, it is important to detect and attack enemy targets faster than the enemy using sensing The grided environmental data is usually provided by the numerical simulation coupled with a data assimilation technique and various inter- or extrapolation algorithms, both of which are based on the observation spanning from simple equipments to satellites. In order to employ the gridded environmental data in the M&S system frequently cutting area and changing its resolution, interpolation algorithms such as linear, cubic spline, IDW, and Kriging methods are necessary to apply. These methods, however, require much time in the M&S system. This paper introduces a technic to reduce time to change the resolution of data. using the binary search method, which finds a point to interpolate quickly and interpolate data in the vicinity of. We also show the efficiency of proposed methods by way of measuring the respective elapsed times.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.70.4-70.4
• /
• 2019

Image super-resolution (SR) is a technique that enhances the resolution of a low resolution image. In this study, we use three SR models (RCAN, ProSRGAN and Bicubic) for enhancing solar SDO/HMI magnetograms using deep learning. Each model generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). The pixel resolution of HMI is about 0.504 arcsec. Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained three models with HMI images in 2014 and test them with HMI images in 2015. We find that the RCAN model achieves higher quality results than the other two methods in view of both visual aspects and metrics: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is also much better than the conventional bi-cubic interpolation. We apply this model to a full-resolution SDO/HMI image and compare the generated image with the corresponding Hinode NFI magnetogram. As a result, we get a very high correlation (0.92) between the generated SR magnetogram and the Hinode one.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.8-12
• /
• 1999

Since the advent of high resolution satellite image, possibilities of applying various human interpretation mechanism to these images have increased. Also many studies about these possibilities in many fields such as computer vision, pattern recognition, artificial intellegence and remote sensing have been done. In this field of these studies, texture is defined as a kind of quantity related to spatial distribution of brightness and tone and also plays an important role for interpretation of images. Especially, methods of obtaining texture by statistical model have been studied intensively. Among these methods, texture measurement method based on cooccurrence matrix is highly estimated because it is easy to calculate texture features compared with other methods. In addition, these results in high classification accuracy when this is applied to satellite images and aerial photos. But in the existing studies using cooccurrence matrix, features have been chosen arbitrarily without considering feature variation. And not enough studies have been implemented for appropriate resolution selection in which cooccurrence matrix can extract texture. Therefore, this study reviews the concept of cooccurrence matrix as a texture measurement method, evaluates usefulness of several features obtained from cooccurrence matrix, and proposes appropriate resolution by investigating variance trend of several features.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.91-99
• /
• 2004

This paper proposed two transcodiing methods, which maintain the same spatio-temporal resolution and reduce a spatial resolution, to convert a H.264 video bitstream into an MPEG-4 video bitstream. When the H.264 video bitstream is transformed into the MPEG-4 video bitstream, the conversions between H.264 block types and MPEG-4 block types are performed by minimizing distortion and the ${\times}4$ block-based motion vector mapping is performed. The proposed two transcoding methods run 4.14～5.1 times as fast as the cascaded transcoding methods in MPEG-4 encoder side, while the PSNR (peak-signal-to ratio) is slightly degrade with maximum 0.3dB.