• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.9A
• /
• pp.2345-2354
• /
• 1998

There have been many researches to yield higher resolution image quality from the low resolution CCD device. The resolution of it is primary factor for the image quality of digital still camera and in manufacturing price. IN this paper, image enlargement algorithm, which reduces blocking effect of enlarged low resolution image and minimizes ringing and blur effect occurring around edge in linear interpolation, is proposed. This algorithm is composed of gaussian low pass filter which eliminates aliasing, least square spline interpolation and non-linear interpolation based on step edge model.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.9
• /
• pp.559-566
• /
• 2005

An effective do-blurring algorithm is proposed to remove the blur of the even and the odd line images of the interlaced scan type camera. n the object or the camera moves fast while the interlaced scan type digital camera is acquiring images, blur is often created due to the misalignment between two images of even and odd lines. In this paper, the blurred original image is separated into the even and the odd line images of the half size. Two full sized images are generated using interpolation technique based on these two in ages. Again, these images are signed and combined through the processes of feature extraction, matching, sub-pixel matching, outlier removal, and mosaicking. De-blurring simulations about the images of different camera motions have been done.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.96-104
• /
• 2009

In this paper, we propose a no-reference objective Quality assessment metrics of image. The blockiness and blurring of edge areas which are sensitive to the human visual system are modeled as step functions. Blocking and blur metrics are obtained by estimating local visibility of blockiness and edge width, For the blocking metric, horizontal and vertical blocking lines are first determined by accumulating weighted differences of adjacent pixels and then the local visibility of blockiness at the intersection of blocking lines is obtained from the total difference of amplitudes of the 2-D step function which is modelled as a blocking region. The blurred input image is first re-blurred by a Gaussian blur kernel and an edge mask image is generated. In edge blocks, the local edge width is calculated from four directional projections (horizontal, vertical and two diagonal directions) using local extrema positions. In addition, the kurtosis and SSIM are used to compute the blur metric. The final no-reference objective metric is computed after those values are combined using an appropriate function. Experimental results show that the proposed objective metrics are highly correlated to the subjective data.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.1
• /
• pp.43-48
• /
• 2014

Usually, image deconvolution is applied as a preprocessing step in surveillance systems to reduce the effect of motion or out-of-focus blur problem. In this paper, we propose a blind-image deconvolution filtering approach based on genetic programming (GP). A numerical expression is developed using GP process for image restoration which optimally combines and exploits dependencies among features of the blurred image. In order to develop such function, first, a set of feature vectors is formed by considering a small neighborhood around each pixel. At second stage, the estimator is trained and developed through GP process that automatically selects and combines the useful feature information under a fitness criterion. The developed function is then applied to estimate the image pixel intensity of the degraded image. The performance of developed function is estimated using various degraded image sequences. Our comparative analysis highlights the effectiveness of the proposed filter.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.252-259
• /
• 2022

Artificial intelligence is used in fusion with image processing techniques using cameras. Image processing technology is a technology that processes objects in an image received from a camera in real time, and is used in various fields such as security monitoring and medical image analysis. If such image processing reduces the accuracy of recognition, providing incorrect information to medical image analysis, security monitoring, etc. may cause serious problems. Therefore, this paper uses a mixture of YOLOv4-tiny model and image processing algorithm and uses the COCO dataset for learning. The image processing algorithm performs five image processing methods such as normalization, Gaussian distribution, Otsu algorithm, equalization, and gradient operation. For RGB images, three image processing methods are performed: equalization, Gaussian blur, and gamma correction proceed. Among the nine algorithms applied in this paper, the Equalization and Gaussian Blur model showed the highest object detection accuracy of 96%, and the gamma correction (RGB environment) model showed the highest object detection rate of 89% outdoors (daytime). The image binarization model showed the highest object detection rate at 89% outdoors (night).

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1228-1231
• /
• 2009

This paper presented an automatic system for display quality measurement by image processing. The goal is to replace human eyes for display quality evaluation by computer vision and get the objective quality review for consumer to make purchase of monitor or TV. Color, contrast, brightness, sharpness and motion blur are the main five factors to affect display quality that could be measured by supplying patterns and analyzing the corresponding images captured from webcam. The scores are calculated by image processing techniques. Linear regression model is then adopted to find the relation between human score and the measured display performance.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• Journal of the Korean Society of Costume
• /
• v.59 no.2
• /
• pp.29-41
• /
• 2009

Perception between real object and recognized subject of human on objective subject is not the same. The reason Is that individual perception of visual design components are transmitted as the image of whole. It is required process of visual perception. Therefore, I developed the vision of seeing image of pattern which is based on Gestalt visual perception theory in clothes. The summary of this study's results is like followings. Extremely antagonistic terms which are specialized by formative characteristics of formative components are clearness and blur of outline/ fixed shape and non-fixed shape/ visuality and tangibility of representation/ simplicity and complexity of structure/ invariability and variability of mobility/ symmetry and asymmetry of arrangements singularity and plurality of group number. The expression of motive shows that clearness, fixed shape, visuality and simplicity pursuit Determination image, and blur, non-fixed shape, tangibility and complexity pursuit Ambiguity image. The arrangements of motive shows that invariability, symmetry and singularity pursuit Order image, and variability asymmetry and plurality pursuit Disorder image. Therefore, the standard of the coordinator of Pattern image positioning is established as Determination and Ambiguity of motive are X-axis, and Order and Disorder of pattern are Y-axis. As the frame of Pattern image positioning, four separated dimensions have made.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.1
• /
• pp.8-14
• /
• 2007

X-ray digital tomosynthesis is widely used in the nondestructive testing and evaluation, especially for the printed circuit boards (PCBs). In this study, we propose a simple method to reduce the blur artefact, frequently claimed in the conventional digital tomosynthesis based on SAA (shift-and-add) algorithm, and thus restore the image sharpness. The proposed method is basically based on the SAA, but has a correction procedure by finding blur artefacts from the forward-and back-projection for the firstly obtained, manipulated backprojection data. The manipulation is the replacement of the original data at the POI (plane-of-interest) by zeros. This method has been compared with the conventional SAA algorithm using the experimental measurements and Monte Carlo simulation for the designed PCB phantom. The comparison showed a much enhancement of sharpness in the images obtained from the proposed method.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.58-66
• /
• 2020

The blur effect, which is generated by various external factors such as out-of-focus and object movement, degrades high-frequency components in the original sharp image. Based on this observation, we propose a novel method for blur detection using textural features. Specifically, the proposed method simultaneously adopts learning-based and watershed-based textural features, which effectively detect the blur on various situations. Moreover, we employ the region-based refinement to improve the processing time while also increasing detection accuracy. Experimental results demonstrate that the proposed method provides the competitive performance compared to previous approaches in literature.