• 한국공작기계학회논문집
• /
• 제15권4호
• /
• pp.69-73
• /
• 2006

This paper present the optimal cleaning condition of the out-hull preprocessing robot by Taguchi method in design of experiments. A $L_8(2^4)$ orthogonal array is adopted to study the effect of adjustment parameters. The adjustment parameters consist of robot speed, motor torque, motor speed and tool angle. And the quality feature is selected as surface roughness of sheet metal. Taguchi analysis is performed in order to evaluate the effect of adjustment parameters of the quality feature of cleaning process by $Minitab^{(R)}$.

• 한국산업정보학회논문지
• /
• 제13권4호
• /
• pp.56-63
• /
• 2008

얼굴 인식률 향상을 위해서는 전처리 단계에서의 영상 보정이 매우 중요하며, 특히 배경 잡음 제거는 얼굴 인식의 정확도에 중대한 영향을 미친다. 본 논문에서는 얼굴 인식률 향상을 위하여 전처리 단계에서 타원 모델을 이용하여 배경 영역을 제거하는 방법을 제안하였다. 사람의 얼굴 윤곽은 타원의 형태를 나타내기 때문에 얼굴 영상에서 타원 모델을 이용할 경우 얼굴 영역을 용이하게 검출할 수 있다. ETRI, ORL, 및 XM2VTS 얼굴 데이터베이스에 대한 실험 분석을 통하여 제안된 방법이 얼굴 인식 성능을 뚜렷하게 개선시켰음을 알 수 있었다.

• 대한전자공학회논문지
• /
• 제27권6호
• /
• pp.929-936
• /
• 1990

This paper describes the method of the Korean character recognition by means of feature points extraction. Also, the preprocessing neural chip for noise elimination, smoothing, thinning and feature point extraction has been designs. The subpatterns were separated by means of advanced index algorithm using mask, and recognized by means of feature points classification. The separation of the Korean character subpatterns was abtained about 97%, and the recognition of the Korean characters was abtained about 95%. The preprocessing neural chip was simulated on SPICE and layouted by double CMOS 2\ulcorner design rule.

• 한국콘텐츠학회논문지
• /
• 제2권4호
• /
• pp.46-50
• /
• 2002

본 논문은 지문 영상의 전처리중 이진화 수행과정에서 지문 영상의 국부적 밝기 차이에 따른 가장 큰 애로점인 임계치(threshold value) 설정을 대상 지문 영역의 밝기 등에 스스로 적응할 수 있도록 Silt Sum 방법을 응용한 적을 이진화를 수행하였다. 기존의 방법과 비교하여 본 연구에서 제시한 개선된 전처리 방법은 보다 높은 인식 정확도를 제공하며, 이에 따라 실험 결과에서 보는 바와 같이 지문 인식을 위한 특징점 추출 알고리즘에 적용될 수 있다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권4호
• /
• pp.251-258
• /
• 2005

Automatic document classification may differ significantly according to the characteristics of documents that are subject to classification, as well as classifier's performance. This research identifies e-mail document's characteristics to apply a three-step preprocessing algorithm that can minimize e-mail document's atypical characteristics. In the first 5go, uncertain based sampling algorithm that used Mean Absolute Deviation(MAD), is used to address the question of selection learning document for the rule generation at the time of classification. In the subsequent stage, Weighted vlaue assigning method by attribute is applied to increase the discriminating capability of the terms that appear on the title on the e-mail document characteristic level. in the third and last stage, accuracy level during classification by each category is increased by using Naive Bayesian Presumptive Algorithm's Dynamic Threshold. And, we implemented an E-Mail Recommendtion System using a three-step preprocessing algorithm the enable users for direct and optimal classification with the recommendation of the applicable category when a mail arrives.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.1002-1005
• /
• 1995

This paper presents an enhanced preprocessing and recognition algorithm for automatic vehicle license plate recognition system. The algorithm first applies horizontal gradient filter followed by thresholding and mathematical morphology operation for preprocessing. The final stage of the preprocessing is the application of connected component analysis in order to estimate the license plate region. For the recognition of the serial numbers of the plates, we developed a very effective algorithm. We call this zerocrossing count algorithm. This paper presents a detail of this algorithm and compare the performance with a template matching algorithm which utilizes correlation coefficient.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.250-253
• /
• 1998

This paper presents a multi-modal neural network composed of a preprocessing module and a multi-layer neural network module in order to enhance the nonlinear characteristics of neural network. The former module is based on spectral method using Chebyschev polynomials and transforms input data into spectra. The latter module identifies the system using the spectra generated by the preprocessing module. The omnibus numerical experiments show that the method is applicable to many a nonlinear dynamic system in the real world, and that preprocessing using Chebyschev polynomials reduces the number of neurons required for the multi-layer neural network.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.399-410
• /
• 2021

Aiming at the problem that complex external variables in natural scenes have a greater impact on facial expression recognition results, a facial expression recognition method based on two-stream convolutional neural network is proposed. The model introduces exponentially enhanced shared input weights before each level of convolution input, and uses soft attention mechanism modules on the space-time features of the combination of static and dynamic streams. This enables the network to autonomously find areas that are more relevant to the expression category and pay more attention to these areas. Through these means, the information of irrelevant interference areas is suppressed. In order to solve the problem of poor local robustness caused by lighting and expression changes, this paper also performs lighting preprocessing with the lighting preprocessing chain algorithm to eliminate most of the lighting effects. Experimental results on AFEW6.0 and Multi-PIE datasets show that the recognition rates of this method are 95.05% and 61.40%, respectively, which are better than other comparison methods.

• 한국컴퓨터정보학회논문지
• /
• 제24권4호
• /
• pp.51-56
• /
• 2019

In this paper, we propose an algorithm that can quickly generate and synthesize city maps in racing games. Racing games are characterized by moving a wide map rather than a fixed map, but designing and developing a wide map requires a lot of production time. This problem can be mitigated by creating a large map in the preprocessing step, but a fixed map makes the game tedious. It is also inefficient to process all the various maps in the preprocessing step. In order to solve this problem, we propose a technique to create a terrain pattern in the preprocessing process, to generate a map in real time, and to synthesize various maps randomly. In addition, we reduced unnecessary rendering computations by integrating view-dependent techniques into the proposed framework. This study was developed in Unity3D and can be used for various contents as well as racing game.

• 천문학회보
• /
• 제43권2호
• /
• pp.38.2-38.2
• /
• 2018

To understand the assembly of the galaxy population in clusters today, it is important to first understand preprocessing, the impact of environments prior to cluster infall. We use 15 cluster samples from YZiCS, a hydrodynamic cluster zoom-in simulation to determine the significance of preprocessing, and focus on the tidal mass loss of dark matter halos. We find ~48% of the cluster member halos were once satellites of another host. The preprocessed fraction depends on each cluster's recent mass growth history. Also, we find that the total mass loss is a clear function of the time spent in a host. However, two factors can increase the mass loss rate considerably. First, if the satellite mass is approaching the mass of its host. Second, when the halo suffers tidal mass loss at a higher redshift. Being in hosts before cluster infall enables halos to experience tidal mass loss for an extended period of time.