• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.142-147
• /
• 2024

The emergence of programs like Midjourney, particularly known for its text-to-image capability, has significantly impacted design and creative industries. Midjourney continually updates its database and algorithms to enhance user experience, with a focus on character consistency. This paper's examination of the latest V6 version of Midjourney reveals notable advancements in its characteristics and design principles, especially in the realm of character generation. By comparing V6 with its predecessors, this study underscores the significant strides made in ensuring consistent character portrayal across different plots and timelines.Such improvements in AI-driven character consistency are pivotal for storytelling. They ensure coherent and reliable character representation, which is essential for narrative clarity, emotional resonance, and overall effectiveness. This coherence supports a more immersive and engaging storytelling experience, fostering deeper audience connection and enhancing creative expression.The findings of this study encourage further exploration of Midjourney's capabilities for artistic innovation. By leveraging its advanced character consistency, creators can push the boundaries of storytelling, leading to new and exciting developments in the fusion of technology and art.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1953-1962
• /
• 1999

While acquiring the image, the shaking of the image capturing equipment or the object seriously damages the image quality. This phenomenon, which degrades the clarity and the resolution of the image is called motion blur. In this paper, a newly defined function is introduced for finding the degree and the length of the motion blur. The domain of this function defined as Peak-trace domain. In The Peak-trace domain, the noise dominant region for calculating the noise variance and the signal dominant region for extracting the degree and the length of the motion blur are defined and analyzed. Using the information of the Peak-trace in the signal dominant region, we can find the direction of the motion regardless of the noise corruption. Weighted least mean square method helps extracting the Peak-trace more precisely. After getting the direction of the motion blur, we can find the length of the motion blur based on one dimensional Cepstrum. In the experiment, we could efficiently restore the degraded image using the information obtained by the proposed algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.2
• /
• pp.70-77
• /
• 2010

This study proposed an auto focusing method for a multi-focus image in assembling lens modules in digital camera phones. A camera module in a camera phone is composed of a lens barrel, an IR glass, a lens mount, a PCB board and aspheric lenses. Alignment among the components is one of the important factors in product quality. Auto-focus is essential to adjust image quality of an IR glass in a lens holder, but there are two focal points in the captured image due to thickness of IR glass. So, sharpness, probability and a scale factor are defined to find desired focus from a multi-focus image. The sharpness is defined as clarity of an image. Probability and a scale factors are calculated using pattern matching with a registered image. The presented algorithm was applied to a lens assembly machine which has 5 axes, two vacuum chucks and an inspection system. The desired focus can be determined on the local maximum of the sharpness, the probability and the scale factor in the experiment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.2
• /
• pp.73-80
• /
• 2006

Fingerprint-based verification system has been used for a very long time. Because of their well-known uniqueness and immutability, fingerprint is one of the most widely used biometric features. However, fingerprint identification system has such a critical weakness that the performance of verification is reduced drastically for a poor input fingerprint. In this paper, an image enhancement algorithm using enhanced direction and enhanced binary and aiming image is used to mitigate the problem in the preprocessing. The goal of image enhancement is to estimate the quality of input fingerprint image and to improve the clarity of ridge and valley structures of input fingerprint image. Also, a ridge orientation extraction method using index table is proposed to improve the speed of verification. It is shown by the experiments that proposed fingerprint verification system improves the minutiae extraction accuracy and performance of verification.

• Investigative Magnetic Resonance Imaging
• /
• v.21 no.2
• /
• pp.71-81
• /
• 2017

Purpose: To compare three, motion-resistant, T1-weighted MR sequences on the hepatobiliary phase for gadoxetic acid-enhanced MR imaging of the liver. Materials and Methods: In this retrospective study, 79 patients underwent gadoxetic acid-enhanced, 3T liver MR imaging. Fifty-nine were examined using a standard protocol, and 20 were examined using a motion-resistant protocol. During the hepatocyte-specific phase, three MR sequences were acquired: 1) gradient recalled echo (GRE) with controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA); 2) radial GRE with the interleaved angle-bisection scheme (ILAB); and 3) radial GRE with golden-angle scheme (GA). Two readers independently assessed images with motion artifacts, streaking artifacts, liver-edge sharpness, hepatic vessel clarity, lesion conspicuity, and overall image quality, using a 5-point scale. The images were assessed by measurement of liver signal-to-noise ratio (SNR), and tumor-to-liver contrast-to-noise ratio (CNR). The results were compared, using repeated post-hoc, paired t-tests with Bonferroni correction and the Wilcoxon signed rank test with Bonferroni correction. Results: In the qualitative analysis of cooperative patients, the results for CAIPIRINHA had significantly higher ratings for streak artifacts, liver-edge sharpness, hepatic vessel clarity, and overall image quality as compared to, radial GRE, (P < 0.016). In the imaging of uncooperative patients, higher scores were recorded for ILAB and GA with respect to all of the qualitative assessments, except for streak artifact, compared with CAIPIRINHA (P < 0.016). However, no significant differences were found between ILAB and GA. For quantitative analysis in uncooperative patients, the mean liver SNR and lesion-to-liver CNR with radial GRE were significantly higher than those of CAIPIRINHA (P < 0.016). Conclusion: In uncooperative patients, the use of the radial GRE sequence can improve the image quality compared to GRE imaging with CAIPIRINHA, despite the data acquisition methods used. The GRE imaging with CAIPIRINHA is applicable for patients without breath-holding difficulties.

• KSTLE International Journal
• /
• v.2 no.2
• /
• pp.133-137
• /
• 2001

This paper investigates the correlation between strip surface roughness and the surface of the work roll. As the actual temper mill(TM) is used, this data will be adopted to another actual temper mill for the application and operation of this experiment. Conclusions are as follows: Electro-discharge texturing(EDT) roll has homogeneous roughness distribution and shape, and also a sinuous peak surface and the life is 2 times longer than that of shot blast texturing(SBT) method. And the higher surface roughness of work roll, the more time is necessary at the EDT method. In the SBT method without the correlation of roughness, but impeller rotation speed with an uncontrollable peak count. The roughness of SBT roll is irregularity compared to that of EDT roll because the work roll roughness is transferred to the strip which was temper rolled, and produces a more desirable image and greater clarity to the color painted steel sheet.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.2
• /
• pp.408-417
• /
• 1995

A study on the surface roughness variation of work roll and strip at the temper rolling was performed. The results were obtained with changes according to the surface roughness of work roll and method to make the peak count on the roll in the temper rolling, and factors to affect to the work roll surface in actual rolling machine (ie. Temper mill). The results suggests that the electro-discharge textured roll has mere uniform roughness distribution than shot blasted roll and its life time is two times longer than shot blasted because it has more sine wave roughness, and it is possible to control the Rmax. In shot blasting method, Surface roughness is related to the impeller speed, But it can't control the peak count.

• Journal of the Korean institute of surface engineering
• /
• v.34 no.4
• /
• pp.327-336
• /
• 2001

The skinpassing conditions such as roll type, roll force and roll roughness of the work roll were evaluated to give the surface properties of the galvanized steel sheets that were required for automotive and to get rid of the surface defects that caused with the bad control of galvanized coating process parameters. The surface defects of the galvanized steel sheets such as the ripple mark and the scratch were completely removed as the roll force of SPM work roll was increased and the amount of the transfer of roll surface texture to the strip was also gained a lot. The image clarity of electro discharge textured (EDT) coated steel sheets before and after painting was higher than that of the bright (BRT) and shot blasted (SBT) coated steel sheets because of higher PPI value, lower waviness and uniform surface pattern. Since micro-craters transferred on the surface of the galvanized steel sheets played a role of nucleation sites of chromate reaction, Increase of micro-craters was bring to better corrosion resistance with the increase of the roll force and the use of EDT roll at the skin pass mill.

• Journal of the Korea Convergence Society
• /
• v.6 no.6
• /
• pp.1-8
• /
• 2015

In this paper, we proposed image enhancement method using sharpening filter for improving the accuracy of object detection using the existing Grabcut algorithm. GrabCut algorithm is the excellent performance extracting an object within a rectangular window range, but it has the drawback of the inferior performance in image with no clear distinction between background and objects. So, in this paper, reinforcing the brightness and clarity through histogram equalization, and tightening the border of the object using the sharpening filter look better than that extracted result of existing GrabCut algorithm in a similar image of the object and the background. Based on improved Grabcut algorithm, it is possible to obtain an improved result in the image processing convergence technique of character recognition, real-time object tracking and so on.

• Journal of KIBIM
• /
• v.11 no.3
• /
• pp.22-33
• /
• 2021

In order to maximize the use of BIM, all data related to individual elements in the model must be correctly assigned, and it is essential to check whether it corresponds to the IFC entity classification. However, as the BIM modeling process is performed by a large number of participants, it is difficult to achieve complete integrity. To solve this problem, studies on semantic integrity verification are being conducted to examine whether elements are correctly classified or IFC mapped in the BIM model by applying an artificial intelligence algorithm to the 2D image of each element. Existing studies had a limitation in that they could not correctly classify some elements even though the geometrical differences in the images were clear. This was found to be due to the fact that the geometrical characteristics were not properly reflected in the learning process because the range of the region to be learned in the image was not clearly defined. In this study, the CRF-RNN-based semantic segmentation was applied to increase the clarity of element region within each image, and then applied to the MVCNN algorithm to improve the classification performance. As a result of applying semantic segmentation in the MVCNN learning process to 889 data composed of a total of 8 BIM element types, the classification accuracy was found to be 0.92, which is improved by 0.06 compared to the conventional MVCNN.