• Journal of Digital Policy
• /
• v.2 no.3
• /
• pp.1-7
• /
• 2023

In this paper, I proposes a method for performing single image super resolution by separating texture-spatial domains and then classifying features based on detailed information. In CNN (Convolutional Neural Network) based super resolution, the complex procedures and generation of redundant feature information in feature estimation process for enhancing details can lead to quality degradation in super resolution. The proposed method reduced procedural complexity and minimizes generation of redundant feature information by splitting input image into two channels: texture and spatial. In texture channel, a feature refinement process with step-wise skip connections is applied for detail restoration, while in spatial channel, a method is introduced to preserve the structural features of the image. Experimental results using proposed method demonstrate improved performance in terms of PSNR and SSIM evaluations compared to existing super resolution methods, confirmed the enhancement in quality.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.3 no.2 s.5
• /
• pp.19-28
• /
• 2004

This paper shows how to compensate the skew from the traffic sign included in the natural image and extract the text. The research deals with the Process related to the array image. Ail the process comprises four steps. In the first fart we Perform the preprocessing and Canny edge extraction for the edge in the natural image. In the second pan we perform preprocessing and postprocessing for Hough Transform in order to extract the skewed angle. In the third part we remove the noise images and the complex lines, and then extract the candidate region using the features of the text. In the last part after performing the local binarization in the extracted candidate region, we demonstrate the text extraction by using the differences of the features which appeared between the tett and the non-text in order to select the unnecessary non-text. After carrying out an experiment with the natural image of 100 Pieces that includes the traffic sign. The research indicates a 82.54 percent extraction of the text and a 79.69 percent accuracy of the extraction, and this improved more accurate text extraction in comparison with the existing works such as the method using RLS(Run Length Smoothing) or Fourier Transform. Also this research shows a 94.5 percent extraction in respect of the extraction on the skewed angle. That improved a 26 percent, compared with the way used only Hough Transform. The research is applied to giving the information of the location regarding the walking aid system for the blind or the operation of a driverless vehicle

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.149-162
• /
• 2005

This paper suggest a way to detect a specific wanted figure in public places such as subway stations and banks by comparing color face images extracted from the real time CCTV with the face images of designated specific figures. Assuming that the characteristic of the surveillance camera allows the face information in screens to change arbitrarily and to contain information on numerous faces, the accurate detection of the face area was focused. To solve this problem, the normalization work using subsampling with $20{\times}20$ pixels on arbitrary face images, which is based on the Perceptron Neural Network model suggested by R. Rosenblatt, created the effect of recogning the whole face. The optimal linear filter and the histogram shaper technique were employed to minimize the outside interference such as lightings and light. The addition operation of the egg-shaped masks was added to the pre-treatment process to minimize unnecessary work. The images finished with the pre-treatment process were divided into three reception fields and the information on the specific location of eyes, nose, and mouths was determined through the neural network. Furthermore, the precision of results was improved by constructing the three single-set network system with different initial values in a row.

• Proceedings of the Safety Management and Science Conference
• /
• 2002.05a
• /
• pp.73-80
• /
• 2002

본 연구는 U자형 생산라인(U라인)에서의 라인밸런싱 문제를 해결하기 위한 유전알고리즘을 제시한다. U라인에서는 사이클 타임 내에 제품이 들어가는 방향과 나오는 방향의 작업을 한 작업자가 수행 할 수 있어서, 재공품 수량을 일정하게 유지한다거나 작업부하를 평활화 하는 등의 라인관리가 기존 직선라인에 비해 용이하다. U라인은 JIT(Just-ln-Time)생산 시스템에서 흔히 볼 수 있다. 본 연구는 U라인에서 사이클 타임이 고정되었을 때 작업장 또는 작업자의 수를 최소로 하면서 동시에 작업장에 할당된 작업들 간의 관련성을 최대화하는 라인밸런싱 문제를 다루었다. 라인밸런싱에 관한 기존 연구는 대부분 직선라인에 관한 것으로 U라인의 장점을 충분히 활용하지 못한다. 특히, 라인의 작업장의 수를 최소화하는 문제는 많은 대안해가 있음에도 불구하고, 작업관련성을 고려하여 해를 구하는 기법에 관한 연구는 아직 미미한 실정이다. 실제 조립라인에서는 가능한 한 관련된 작업들을 동일한 작업자에 할당하는 것이 바람직하며, 이러한 작업편성은 작업자의 작업능률을 향상시킬 수 있다. 유전알고리즘은 자연계의 적자생존과 생물학적 진화과정을 모방한 탐색기법으로 조합최적화 문제에 효과적인 기법으로 널리 알려져 있다. 본 연구는 유전알고리즘을 이용하여 U라인에서 작업관련성을 고려한 라인밸런싱 문제를 해결하기 위한 기법을 개발하였다. 문제의 목적에 적합한 개체의 평가함수가 제시되었으며, 개체의 형질을 효과적으로 자손에 유전할 수 있고 유전 연산이 용이한 개체의 표현방법과 개체의 해석방법이 제시되었다. 컴퓨터 실험을 통하여 개발한 알고리즘의 성능을 보였다.월 초순부터 중순에 각각 최고 성기를 나타내었다. H. papariensis의 암컷과 수컷의 발광양상을 분석하고자 정지발광과 구애 발광을 구분하여 조사하였고 각각의 발광지속시간과 발광주기를 구분하여 측정하였다. 수컷의 발광지속시간은 정지발광(0.12초)보다 구애발광(0.17초)에서 1.4배 증가하였으며 암컷의 발광지속시간은 정지발광(0.15초)보다 구애발광(0.19초)에서 1.5배 증가하였다. 발광주기는 수컷에서 정지발광(1.26초)보다 구애발광(1.12초)에서 0.88배 감소하였고, 암컷에서 정지발광(2.99초)보다 구애발광(1.06초)에서 0.35배 감소하였다. 발광양상에서 발광주파수는 수짓의 정지발광에서 0.8 Hz, 수컷 구애발광에서 0.9 Hz, 암컷의 정지발광에서 0.3 Hz, 암컷의 구애발광에서 0.9 Hz로 각각 나타났다. H. papariensis의 발광파장영역은 400 nm에서 700 nm에 이르는 모든 영역에서 확인되었으며 가장 높은 첨두치는 600 nm에 있고 500에서 600 nm 사이의 파장대가 가장 두드러지게 나타났다. 발광양상과 어우러진 교미행동은 Hp system과 같은 결과를 얻었다.하는 방법을 제안한다. 즉 채널 액세스 확률을 각 슬롯에서 예약상태에 있는 음성 단말의 수뿐만 아니라 각 슬롯에서 예약을 하려고 하는 단말의 수에 기초하여 산출하는 방법을 제안하고 이의 성능을 분석하였다. 시뮬레이션에 의해 새로 제안된 채널 허용 확률을 산출하는 방식의 성능을 비교한 결과 기존에 제안된 방법들보다 상당한 성능의 향상을 볼 수 있었다., 인삼이 성장될 때 부분적인 영양상태의 불충분이나 기후 등에 따른 영향을

• Food Science and Preservation
• /
• v.19 no.1
• /
• pp.95-103
• /
• 2012

The objective of this study was to develop models for the predict of the milk properties (fat, protein, SNF, lactose, MUN) of unhomogenized milk using the visible and near-infrared (NIR) spectroscopic technique. A total of 180 milk samples were collected from dairy farms. To determine optimal measurement temperature, the temperatures of the milk samples were kept at three levels ($5^{\circ}C$, $20^{\circ}C$, and $40^{\circ}C$). A spectrophotometer was used to measure the reflectance spectra of the milk samples. Multilinear-regression (MLR) models with stepwise method were developed for the selection of the optimal wavelength. The preprocessing methods were used to minimize the spectroscopic noise, and the partial-least-square (PLS) models were developed to prediction of the milk properties of the unhomogenized milk. The PLS results showed that there was a good correlation between the predicted and measured milk properties of the samples at $40^{\circ}C$ and at 400~2,500 nm. The optimal-wavelength range of fat and protein were 1,600~1,800 nm, and normalization improved the prediction performance. The SNF and lactose were optimized at 1,600~1,900 nm, and the MUN at 600~800 nm. The best preprocessing method for SNF, lactose, and MUN turned out to be smoothing, MSC, and second derivative. The Correlation coefficients between the predicted and measured fat, protein, SNF, lactose, and MUN were 0.98, 0.90, 0.82, 0.75, and 0.61, respectively. The study results indicate that the models can be used to assess milk quality.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.268-273
• /
• 2017

Recently, deep learning encoder-based approach has been actively applied in the field of sentiment classification. However, Long Short-Term Memory network deep learning encoder, the commonly used architecture, lacks the quality of vector representation when the length of the documents is prolonged. In this study, for effective classification of the sentiment documents, we suggest the use of attention method-based deep learning encoder that generates document vector representation by weighted sum of the outputs of Long Short-Term Memory network based on importance. In addition, we propose methods to modify the attention method-based deep learning encoder to suit the sentiment classification field, which consist of a part that is to applied to window attention method and an attention weight adjustment part. In the window attention method part, the weights are obtained in the window units to effectively recognize feeling features that consist of more than one word. In the attention weight adjustment part, the learned weights are smoothened. Experimental results revealed that the performance of the proposed method outperformed Long Short-Term Memory network encoder, showing 89.67% in accuracy criteria.

• Journal of Broadcast Engineering
• /
• v.19 no.4
• /
• pp.453-467
• /
• 2014

A typical histogram equalization contrast enhancement effect for improving the image quality is excellent. However, because it appears that excessive changes of the brightness values, The average brightness of the image is changing in units of frames of applications such as a TV video is unsuitable. In order to solve these drawbacks, a modified method of histogram equalization on various studies have been made. But the result images of existing methods sometimes shown visual degradations such as over-enhancement and false contouring. In this paper, we propose improved contrast enhancement method through bi-histogram equalization using target mean brightness based on differential compression method. The proposed method is based on the average brightness value by dividing the histogram, the histogram for each zone, according to the frequency differential of compression. And equalize the modified histogram based on target mean brightness. This allows to suppress deterioration of picture quality, and changes in the average brightness of each frame of video, while maintaining and improving the contrast. Experimental results show that the proposed method compared to the conventional method, the average brightness of each frame from a movie well maintained, and no degradation of the image quality showed a good effect to improve the contrast.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.329-341
• /
• 2014

Kernel-based mean-shift object tracking has gained more interests nowadays, with the aid of its feasibility of reliable real-time implementation of object tracking. This algorithm calculates the best mean-shift vector based on the color histogram similarity between target model and target candidate models, where the color histograms are usually produced after uniform color-space quantization for the implementation of real-time tracker. However, when the image of target model has a reduced contrast, such uniform quantization produces the histogram model having large values only for a few histogram bins, resulting in a reduced accuracy of similarity comparison. To solve this problem, a non-uniform quantization algorithm has been proposed, but it is hard to apply to real-time tracking applications due to its high complexity. Therefore, this paper proposes a fast non-uniform color-space quantization method using the histogram equalization, providing an adjusted histogram distribution such that the bins of target model histogram have as many meaningful values as possible. Using the proposed method, the number of bins involved in similarity comparison has been increased, resulting in an enhanced accuracy of the proposed mean-shift tracker. Simulations with various test videos demonstrate the proposed algorithm provides similar or better tracking results to the previous non-uniform quantization scheme with significantly reduced computation complexity.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.235-247
• /
• 2002

For an efficient indexing and retrieval of digital video data, research on video caption extraction and recognition is required. This paper proposes methods for extracting artificial captions from video data and enhancing their image quality for an accurate Hangul and English character recognition. In the proposed methods, we first find locations of beginning and ending frames of the same caption contents and combine those multiple frames in each group by logical operation to remove background noises. During this process an evaluation is performed for detecting the integrated results with different caption images. After the multiple video frames are integrated, four different image enhancement techniques are applied to the image: resolution enhancement, contrast enhancement, stroke-based binarization, and morphological smoothing operations. By applying these operations to the video frames we can even improve the image quality of phonemes with complex strokes. Finding the beginning and ending locations of the frames with the same caption contents can be effectively used for the digital video indexing and browsing. We have tested the proposed methods with the video caption images containing both Hangul and English characters from cinema, and obtained the improved results of the character recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.1-6
• /
• 2014

In this study, we propose optimized RBFNNs based on night vision face recognition simulator with the aid of $(2D)^2$ PCA algorithm. It is difficult to obtain the night image for performing face recognition due to low brightness in case of image acquired through CCD camera at night. For this reason, a night vision camera is used to get images at night. Ada-Boost algorithm is also used for the detection of face images on both face and non-face image area. And the minimization of distortion phenomenon of the images is carried out by using the histogram equalization. These high-dimensional images are reduced to low-dimensional images by using $(2D)^2$ PCA algorithm. Face recognition is performed through polynomial-based RBFNNs classifier, and the essential design parameters of the classifiers are optimized by means of Differential Evolution(DE). The performance evaluation of the optimized RBFNNs based on $(2D)^2$ PCA is carried out with the aid of night vision face recognition system and IC&CI Lab data.