• KIISE Transactions on Computing Practices
• /
• v.21 no.10
• /
• pp.631-638
• /
• 2015

Today, the demand for speech recognition systems in mobile environments is increasing rapidly. This paper proposes a novel method for Korean phoneme segmentation that is applicable to a phoneme based Korean speech recognition system. First, the input signal constitutes blocks of the same size. The proposed method is based on a volatility indicator calculated for each block of the input speech signal, and the bulk indicators calculated for each bulk in blocks, where a bulk is a set of adjacent samples that have the same sign as that of the primitive indicators for phoneme segmentation. The input signal vowels, voiced consonants, and voiceless consonants are sequentially recognized and the boundaries among phonemes are found using three devoted recognition algorithms that combine the two types of primitive indicators. The experimental results show that the proposed method can markedly reduce the error rate of the existing phoneme segmentation method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.3 s.37
• /
• pp.3-11
• /
• 2006

The need for edge detection about topography data from the high resolution satellite imagery is happening with increasing frequency according to many people utilize the its imagery as various fields recently. Many experts is recognizing of other GIS will make use of the road detection from the high resolution satellite imagery, including ITS (Intelligent Transportation Systems) and urban planning. This paper is comparative analysis of LPF (Low Pass Filtering) and HPF (High Pass Filtering) for roads edge detection from high resolution satellite imagery. As a result, LPF and HPF can be highlight selective pixels at edge area about input data. In case or applying to other techniques such as LPF for the same purpose, they aye more effective for wide road width which often cause the slight distortion of boundary or overall change of brightness values on the whole Image. Whereas, HPF has ability to enhance selectively detailed components in a target image.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.217-219
• /
• 2003

본 논문에서는 실시간으로 상호작용이 가능한 광범위한 3차원의 넓은 외부영역을 렌더링하기 위해 공간문할 방법으로 제한적 옥트리를 이용하고, 충돌검출 방법으로 계층적 경계상자를 사용하여 효과적으로 충돌검출을 하는 방법을 소개한다. 넓은 외부 영역을 동적으로 빠르게 처리하기 위해 공간을 분할시켜 처리영역을 축소하고 3차원 공간을 고정볼륨 바운드를 구축한 후 이를 처리 값으로 이용한 계층적 경계상자를 이용하여 충돌처리를 한다. 옥트리는 정적인 물체에 대한 정확한 표현 시 주로 사용되나 본 논문에서는 이를 동적인 환경에 이용하기 위하여 제한적 OSF를 사용한다. 또한 폴리곤의 충돌검사를 모두 하지 않고 빠른 시간에 충돌검출을 판단할 수 있는 방법과 경계상자의 충돌검출에 대한 비용이 3차원 개체 개수에 대해 비례하여 증가하는 데에 대한 개선 방법을 제안한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.307-308
• /
• 2015

자동차 번호판의 문자를 검출하기 위한 과정 중 그림자가 있는 후면 번호판을 이진화하는 방법을 제안한다. 대부분의 경우 차량구조에 의한 그림자 발생이 문자를 검출하는데 오류를 발생시킨다. 이를 해결하기 위해 그림자 영역과 아닌 영역의 경계를 검출해야 한다. 하지만, 기존 방법은 히스토그램에서 세 개의 영역사이에 있는 임계값 2개를 수동으로 결정해야 되는 점과 현재번호판의 색상인 흰색 바탕에 검은 문자에 적용하면 문자 영역의 그림자 경계선 검출이 모호하다는 단점이 있다. 본 논문에서는 이 문제를 해결하기 위하여 슬라이딩 윈도우를 이용한 히스토그램과 탐색하는 픽셀의 좌, 우 픽셀들을 스캔하여 연결되지 않은 에지를 찾아 그림자 경계선 에지를 연결하는 방법을 제안한다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.582-592
• /
• 2001

Video indexing plays an important role in the applications such as digital video libraries or web VOD which archive large volume of digital videos. Video indexing is usually based on video segmentation. In this paper, we propose a software tool called V2Web Studio which can generate video clips utilizing shot boundary detection algorithm. With the V2Web Studio, the process of clip generation consists of the following four steps: 1) Automatic detection of shot boundaries by parsing the video, 2) Elimination of errors by manually verifying the results of the detection, 3) Building a modeling structure of logical hierarchy using the verified shots, and 4) Generating multiple video clips corresponding to each logically modeled segment. The aforementioned steps are performed by shot detector, shot verifier, video modeler and clip generator in the V2Web Studio respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.41-49
• /
• 2012

This paper proposes a detection method of wipes including horizontal wipes with linear moving borders, such as horizontal or vertical wipes, Barn Doors, and Iris Rounds with circular moving borders. The suggested method first obtains a difference image between two adjacent frames, and extracts lines and circles by applying Hough transformation to the extracted difference image. Then, we detect wipe transitions by employing an evaluation function that analyzes the number of moving trajectories of lines or circles, their moving direction and magnitude. To evaluate the performance of the suggested algorithm, experimental results show that the proposed method can effectively detect wipe transitions with linear and circular moving borders rather than some existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.224-229
• /
• 1999

In the field of speech recognition, the research area can be classified into the following two categories: one which is concerned with the development of phoneme-level recognition system, the other with the efficiency of word-level recognition system. The resonable phoneme-level recognition system should detect the phonemic boundaries appropriately and have the improved recognition abilities all the more. The traditional LPC methods detect the phoneme boundaries using Itakura-Saito method which measures the distance between LPC of the standard phoneme data and that of the target speech frame. The MFCC methods which treat spectral transitions as the phonemic boundaries show the lack of adaptability. In this paper, we present new speech recognition system which uses auto-correlation method in the phonemic boundary detection process and the multi-layered Feed-Forward neural network in the recognition process respectively. The proposed system outperforms the traditional methods in the sense of adaptability and another advantage of the proposed system is that feature-extraction part is independent of the recognition process. The results show that frame-unit phonemic recognition system should be possibly implemented.

• Journal of KIISE:Software and Applications
• /
• v.27 no.4
• /
• pp.402-411
• /
• 2000

It is an important step in video indexing and retrieval to detect shot boundaries on video data. Some approaches are proposed to detect shot changes by computing color histogram differences or the variances of DCT coefficients. However, these approaches do not consider the content or meaningful features in the image data which are useful in high level video processing. In particular, it is desirable to detect these features from compressed video data because this requires less processing overhead. In this paper, we propose a new method to detect shot boundaries from MPEG data using region flow and color information. First, we reconstruct DC images and compute region flow information and color histogram differences from HSV quantized images. Then, we compute the points at which region flow has discontinuities or color histogram differences are high. Finally, we decide those points as shot boundaries according to our proposed algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.4
• /
• pp.793-799
• /
• 2007

Generally, a semiconductor chip measured with a few micro units is captured by line scan camera for higher inspection accuracy. However, the faulty inspection requires an exact boundary detection algorithm, because it is very sensitive to scan speed and lighting conditions. In this paper we propose boundary detection with subpixel edge detection in order to increase the accuracy of bump faulty detection on chips. The bump edge is detected by first derivative to four directions from bump center point and the exact edge positions are searched by the subpixel method. Also, the exact bump boundary to calculate the actual bump size is computed by LSM(Least Squares Method) to minimize errors since the bump size is varied such as bump protrusion, bump bridge, and bump discoloration. Experimental results exhibit that the proposed algorithm shows large improvement comparable to the other conventional boundary detection algorithms.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.418-420
• /
• 2001

최근 디지털 비디오 데이터의 사용이 급격히 증가하면서 보다 정확하게 샷을 검출하는 기법이 요구되고 있다. 비디오 정보를 이용하여 샷을 검출하는 역는 크게 이산코사인 변환의 결과값을 이용하는 방법과 움직임 보상의 결과값을 이용하는 방법으로 그룹화할 수 있는데 전자의 방법은 점진적인 변화를 검출할 수 있는 반면에 전체적인 검출율이 떨어진다는 단점이 있고, 후자의 방법은 전체적인 검출율은 높지만 점진적인 변화를 검출할 수 없다는 단점이 있다. 본 논문에서는 실험을 통하여 이러한 두 가지 방법의 특징을 살펴본 후 이 방법들을 이용한 새로운 샷 경계 검출 방법을 제안한다. 전체적으로 검출율을 높이는 데 목적을 두었기 때문에 매크로블록 타입을 이용하는 방법을 기본으로 하면서 히스토그램을 이용하는 방법을 추가하여 precision을 높일 수 있도록 하였다. 히스토그램을 이용하는 방법에서는 단순히 프레임과의 비교를 하던 기존의 방법에다 프레임들간의 차이의 차이를 이용하여 성능을 높일 수 있도록 하였다. 본 논문에서 제안한 알고리즘을 이용하여 실험을 한 결과 평균 0.96의 recall과 0.96의 precision을 보이고 있음을 알 수 있었다.