• KIEE International Transactions on Electrophysics and Applications
• /
• v.5C no.3
• /
• pp.138-142
• /
• 2005

In this paper, we compared recognition rates between NN(neural networks) and clustering method as a scheme of off-line PD(partial discharge) diagnosis which occurs at the stator coil of traction motor. To acquire PD data, three defective models are made. PD data for classification were acquired from PD detector. And then statistical distributions are calculated to classify model discharge sources. These statistical distributions were applied as input data of two classification tools, BP(Back propagation algorithm) and ANFIS(adaptive network based fuzzy inference system) pre-processed FCM(fuzzy c-means) clustering method. So, classification rate of BP were somewhat higher than ANFIS. But other items of ANFIS were better than BP; learning time, parameter number, simplicity of algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3177-3195
• /
• 2014

In many moving object detection problems of an aerial video, accurate and robust stabilization is of critical importance. In this paper, a novel accurate image alignment algorithm for aerial electronic image stabilization (EIS) is described. The feature points are first selected using optimal derivative filters based Harris detector, which can improve differentiation accuracy and obtain the precise coordinates of feature points. Then we choose the Delaunay Triangulation edges to find the matching pairs between feature points in overlapping images. The most "useful" matching points that belong to the background are used to find the global transformation parameters using the projective invariant. Finally, intentional motion of the camera is accumulated for correction by Sage-Husa adaptive filtering. Experiment results illustrate that the proposed algorithm is applied to the aerial captured video sequences with various dynamic scenes for performance demonstrations.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.161-164
• /
• 2000

본 논문에서 제안한 동시통화 검출기는 기존의 전대역에서 이루어지던 상호상관계수를 이용한 동시통화 검출기의 검출성능을 향상시키기 위하여 웨이브릿변환된 각각의 서브밴드 내에서 동시통화 및 반향경로를 구별하여 효율적으로 검출할 수 있도록 구성하였다. 서브밴드 동시통화 검출기 사용으로 동시통화 시에 발생하는 적응필터의 계수 발산을 막음으로써 시스템의 안정성을 높이고, 근단화자 신호가 원단화자에게 더 유쾌하게 들릴 수 있게 함으로써 원활한 통화환경을 제공할 수 있도록 구현하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.67-72
• /
• 2019

This paper proposes a computer vision-based banknote recognition system intended to assist the blind. This system is robust and fast in recognizing banknotes on videos recorded with a smartphone on real-life scenarios. To reduce the computation time and enable a robust recognition in cluttered environments, this study segments the banknote candidate area from the background utilizing a technique called Pixel-Based Adaptive Segmenter (PBAS). The Speeded-Up Robust Features (SURF) interest point detector is used, and SURF feature vectors are computed only when sufficient interest points are found. The proposed algorithm achieves a recognition accuracy of 98%, a 100% true recognition rate and a 0% false recognition rate. Although Korean banknotes are used as a working example, the proposed system can be applied to recognize other countries' banknotes.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.1
• /
• pp.37-55
• /
• 2023

In this paper we propose a new algorithm for detecting and counting flowers in a complex background based on digital images. The algorithm mainly includes the following parts: edge contour extraction of flowers, edge contour determination of overlapped flowers and flower counting. We use a contour detection technique in Computer Vision (CV) to extract the edge contours of flowers and propose an improved algorithm with a concave point detection technique to find accurate segmentation for overlapped flowers. In this process, we first use the polygon approximation to smooth edge contours and then adopt the second-order central moments to fit ellipse contours to determine whether edge contours overlap. To obtain accurate segmentation points, we calculate the curvature of each pixel point on the edge contours with an improved Curvature Scale Space (CSS) corner detector. Finally, we successively give three adaptive judgment criteria to detect and count flowers accurately and automatically. Both experimental results and the proposed evaluation indicators reveal that the proposed algorithm is more efficient for flower counting.

• Korean Journal of Optics and Photonics
• /
• v.17 no.5
• /
• pp.383-390
• /
• 2006

The SharkHartmann wavefront sensors are the most popular devices to measure wavefront in the field of adaptive optics. The Shack-Hartmann sensors measure the centroids of spot irradiance distribution formed by each corresponding micro-lens. The centroids are linearly proportional to the local mean slopes of the wavefront defined within the corresponding sub-aperture. The wavefront is then reconstructed from the evaluated local mean slopes. The uncertainty of the Shack-Hartmann sensor is caused by various factors including the detector noise, the limited size of the detector, the magnitude and profile of spot irradiance distribution, etc. This paper investigates the noise propagation in two major centroid evaluation algorithms through computer simulation; 1st order moments of the irradiance algorithms i.e. center of gravity algorithm, and correlation algorithm. First, the center of gravity algorithm is shown to have relatively large dependence on the magnitudes of noises and the shape & size of irradiance sidelobes, whose effects are also shown to be minimized by optimal thresholding. Second, the correlation algorithm is shown to be robust over those effects, while its measurement accuracy is vulnerable to the size variation of the reference spot. The investigation is finally confirmed by experimental measurements of defocus wavefront aberrations using a Shack-Hartmann sensor using those two algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.41-51
• /
• 2024

In this paper, we explore the enhancement of target detection accuracy in the guided weapon using deep learning object detection on infrared (IR) images. Due to the characteristics of IR images being influenced by factors such as time and temperature, it's crucial to ensure a consistent representation of object features in various environments when training the model. A simple way to address this is by emphasizing the features of target objects and reducing noise within the infrared images through appropriate pre-processing techniques. However, in previous studies, there has not been sufficient discussion on pre-processing methods in learning deep learning models based on infrared images. In this paper, we aim to investigate the impact of image pre-processing techniques on infrared image-based training for object detection. To achieve this, we analyze the pre-processing results on infrared images that utilized global or local information from the video and the image. In addition, in order to confirm the impact of images converted by each pre-processing technique on object detector training, we learn the YOLOX target detector for images processed by various pre-processing methods and analyze them. In particular, the results of the experiments using the CLAHE (Contrast Limited Adaptive Histogram Equalization) shows the highest detection accuracy with a mean average precision (mAP) of 81.9%.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.17 no.3
• /
• pp.411-424
• /
• 2017

An all-digital delay-locked loop (DLL) for a mobile memory interface, which runs at 0.11-2.5 GHz with a phase-shift capability of $180^{\circ}$, has two internal DLLs: a global DLL which uses a time-to-digital converter to assist fast locking, and shuts down after locking to save power; and a local DLL which uses a phase detector with an adaptive phase sampling window (WPD) to reduce jitter accumulation. The WPD in the local DLL adjusts the width of its sampling window adaptively to control the loop bandwidth, thus reducing jitter induced by UP/DN dithering, input clock jitter, and supply/ground noise. Implemented in a 65 nm CMOS process, the DLL operates over 0.11-2.5 GHz. It locks within 6 clock cycles at 0.11 GHz, and within 17 clock cycles at 2.5 GHz. At 2.5 GHz, the integrated jitter is $954fs_{rms}$, and the long-term jitter is $2.33ps_{rms}/23.10ps_{pp}$. The ratio of the RMS jitter at the output to that at the input is about 1.17 at 2.5 GHz, when the sampling window of the WPD is being adjusted adaptively. The DLL consumes 1.77 mW/GHz and occupies $0.075mm^2$.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.451-456
• /
• 2004

Signature based intrusion detection system (IDS), having stored rules for detecting intrusions at the library, judges whether new inputs are intrusion or not by matching them with the new inputs. However their policy has two restrictions generally. First, when they couldn't make rules against new intrusions, false negative (FN) errors may are taken place. Second, when they made a lot of rules for maintaining diversification, the amount of resources grows larger proportional to their amount. In this paper, we propose the learning algorithm which can evolve the competent of anomaly detectors having the ability to detect anomalous attacks by genetic algorithm. The anomaly detectors are the population be composed of by following the negative selection procedure of the biological immune system. To show the effectiveness of proposed system, we apply the learning algorithm to the artificial network environment, which is a computer security system.

• Journal of KIISE:Software and Applications
• /
• v.36 no.1
• /
• pp.82-91
• /
• 2009

Sign language spotting is the task of detecting and recognizing the signs in a signed utterance. The difficulty of sign language spotting is that the occurrences of signs vary in both motion and shape. Moreover, the signs appear within a continuous gesture stream, interspersed with transitional movements between signs in a vocabulary and non-sign patterns(which include out-of-vocabulary signs, epentheses, and other movements that do not correspond to signs). In this paper, a novel method for designing a threshold model in a conditional random field(CRF) model is proposed. The proposed model performs an adaptive threshold for distinguishing between signs in the vocabulary and non-sign patterns. A hand appearance-based sign verification method, a short-sign detector, and a subsign reasoning method are included to further improve sign language spotting accuracy. Experimental results show that the proposed method can detect signs from continuous data with an 88% spotting rate and can recognize signs from isolated data with a 94% recognition rate, versus 74% and 90% respectively for CRFs without a threshold model, short-sign detector, subsign reasoning, and hand appearance-based sign verification.