• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.3
• /
• pp.229-234
• /
• 2018

Texture is one of the most useful features in classifying and segmenting images. The LBP-based approach previously presented in the literature has been successful in many applications. However, it's theoretical foundation is based only on the difference of pixel values, and consequently it has a number of drawbacks like it performs poorly for the images corrupted with noise, and especially it cannot be used as a multiscale texture descriptor due to the exploding increase of feature vector dimension with increase of the number of neighbor pixels. In this paper, we present a method to address these drawbacks of LBP-based approach. More specifically, our approach quantizes the range of pixels values and construct a 3D histogram which captures the correlative information of pixels. This histogram is used as a texture feature. Several tests with texture images show that the proposed method outperforms the LBP-based approach in the problem of texture classification.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.48-54
• /
• 1999

A new method for wavelet embedded image coding is presented extending the bases of the Shapiro's algorithm by incorporating edge detection, zerotree scheme, and classified VQ(CVQ). Generally edges in the image are regarded an visually important components and the previous literatures have proved that significant coefficients in wavelet transform domain correspond to the edges in spatial domain. Hence, by identifying the edge elements, the significant coefficient can be easily detected in wavelet domain without investigating descendant coefficients across layer. Hierarchical trees for the significant components are organized, and then CVQ method is applied to these trees. Since the significant information has higher priority in transmission, the simulation shows that our coder provides a superior performance over the conventional method and can be successfully applied to the application areas that require of progressive transmission.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.103-114
• /
• 2005

This paper presents a content-based image retrieval (CBIR) method using the combination of color and texture features. As a color feature, a color autocorrelogram is chosen which is extracted from the hue and saturation components of a color image. As a texture feature, BDIP(block difference of inverse probabilities) and BVLC(block variation of local correlation coefficients) are chosen which are extracted from the value component. When the features are extracted, the color autocorrelogram and the BVLC are simplified in consideration of their calculation complexity. After the feature extraction, vector components of these features are efficiently quantized in consideration of their storage space. Experiments for Corel and VisTex DBs show that the proposed retrieval method yields 9.5% maximum precision gain over the method using only the color autucorrelogram and 4.0% over the BDIP-BVLC. Also, the proposed method yields 12.6%, 14.6%, and 27.9% maximum precision gains over the methods using wavelet moments, CSD, and color histogram, respectively.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.75-84
• /
• 2006

With considering center-biased characteristic, NTSS(New Three-Step Search Algorithm) can improve the performance of TSS(Three-Step Search Algorithm) which is one of the most popular fast block matching algorithms(BMA) to search a motion vector in a video sequence. Although NTSS has generally better Quality than TSS for a small motion sequence, it is hard to say that NTSS can provide better quality than TSS for a large motion sequence. It even deteriorates the quality to increase a search window size using NTSS. In order to address this drawback, this paper aims to develop a new adaptive window size-based three step search scheme, called AWTSS, which can improve quality at various window sizes in both the small and the large motion video sequences. In this scheme, the search window size is dynamically changed to improve coding efficiency according to the characteristic of motion vectors. AWTSS can improve the video quality more than 0.5dB in case of large motion with keeping the same quality in case of small motion.

• Journal of KIISE:Software and Applications
• /
• v.28 no.7
• /
• pp.501-510
• /
• 2001

Generally, it is essential to estimate exact disparity for the 3D modeling from stereo images. Because existing methods calculate disparities from a whole image, they require too much cimputational time and bring about the mismatching problem. In this article, using the characteristic that the disparity vectors in stereo images are distributed not equally in a whole image but only exist about the background and obhect, we do a wavelet transformation on stereo images and estimate coarse disparity fields from the reduced lowpass field using area-based method at first-step. From these coarse disparity vectors, we generate disparity histogram and then separate object from background area using it. Afterwards, we restore only object area to the original image and estimate dense and accurate disparity by our two-step pixel-based method which does not use pixel brightness but use second gradient. We also extract feature points from the separated object area and estimate depth information by applying disparity vectors and camera parameters. Finally, we generate 3D model using both feature points and their z coordinates. By using our proposed, we can considerably reduce the computation time and estimate the precise disparity through the additional pixel-based method using LOG filter. Furthermore, our proposed foreground/background method can solve the mismatching problem of existing Delaunay triangulation and generate accurate 3D model.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.333-336
• /
• 2007

본 논문에서는 감정인식 분야에서 가장 많이 사용되어지는 음성신호와 얼굴영상을 가지고 4개의(기쁨, 슬픔, 화남, 놀람) 감정으로 인식하고 각각 얻어진 감정인식 결과를 Multi modal 기법을 이용해서 이들의 감정을 융합한다. 이를 위해 얼굴영상을 이용한 감정인식에서는 주성분 분석(Principal Component Analysis)법을 이용해 특징벡터를 추출하고, 음성신호는 언어적 특성을 배재한 acoustic feature를 사용하였으며 이와 같이 추출된 특징들을 각각 신경망에 적용시켜 감정별로 패턴을 분류하였고, 인식된 결과는 감정표현 시스템에 작용하여 감정을 표현하였다.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.77-85
• /
• 1998

This paper proposes progressive image transmission(PIT) methods based on the wavelet packet transform, in which quantizers are optimized at each stage for the given bit rate. Scalar and vector quantizers are used and the performance of each quantizer is compared. After quantization, selected subbands are ordered by their priority for transmission. Subjective quality of the reconsetructed image is improved by human visual system (HVS) weighting.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.427-430
• /
• 2005

사람의 홍채는 태어날 때 한번 정해지면 평생 변화하지 않는 특성을 가지고 있으며, 개개인별로 모양이 모두 다른 것으로 알려져 있다. 이에, 본 논문에서는 홍채영상 취득시 조명에 의한 동공의 크기 변화에 민감하지 않은 2차원의 홍채패턴을 취득하여, 2D Gabor Wavelet과 Fuzzy LDA를 이용하여 특징 벡터를 추출한다. 인식과정에서는 correlation 계수를 이용하여 서로 다른 홍채의 특징 값에 대해 유사도를 측정하고 유사도가 가장 큰 대상을 찾게 된다. 이때, 4개 방향의 Gabor Wavelet을 거쳐 얻어진 영상에 대해 최고의 값을 인식 대상자로 인정하므로 오 인식 될 확률을 최소화 할 수 있다. 제안한 알고리듬의 유용성을 확인하기 위해 대상자 50명에 대하여 각각 6회씩 촬영한 두 가지 데이터베이스(CASIA, CBNU)를 이용하였으며, 실험 결과 90% 이상의 높은 인식률을 얻었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.550-552
• /
• 1998

스포츠 비디오는 역동적인 특성과 비정형적인 구조를 가지고 있으므로 뉴스와 같은 정형적인 비디오와는 달리 분석이 쉽지 않다. 본 논문에서는 이러한 어려움을 극복하기 위하여 축구 경기에서 하이라이트를 추출하여 색인하고 이에 대하여 선수 위치 추적, 파노라마 영상 구성, 경기장 모델 상에서의 선수 이동 궤적 도시 등을 수행하는 방법을 제안한다. 이를 위하여 제한된 색상의 HSV 영상을 구성하여 골대와 선수 위치를 추적하고, 움직임 벡터를 추출하여 카메라 동작을 분석하였으며 경기장 모델 구성을 위해 경기장 내의 특징점을 추출하여 투영 변환을 수행하였다. 실험 결과를 통해서 제안된 방법이 축구 경기 비디오 분석에 효율적으로 이용될 수 있음을 확인할 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.161-164
• /
• 1998

카메라이 동작 정보는 컴퓨터 비전, 영상 코딩 및 비디오 검색 등의 분야에서 사용되는 강력하고 중요한 특징이다. 특히, 최근에 관심의 초점이 되고 있는 내용기반 비디오 검색을 위한 자동색인에서 장면전환 검출이나 이동 물체의 동작 정보 추출 등에 값지게 활용될 수 있다. 본 논문에서는 파라미터 모델을 이용해서 카메라의 동작을 추출하는 방법을 제안한다. 먼저, 영상의 공간적인 특성을 고려하면서 전체 과정의 속도를 탐색 영역 내에서 동적 백터를 추출한다. 그리고 추출된 동작 벡터를 파라미터 모델에 적용하여 파라미터를 추출하고, 카메라의 동작을 파라미터들의 상호 관계를 이용하여 정의하므로써 최종적인 카메라의 동작을 추출한다. 본 논문에서 제안한 방법은 기존의 방법에 비해 계산 시간상의 비용을 축소시켰고, 화소 단위가 아니라 셀 단위로 카메라의 동작을 추출하므로 다른 방법에 비해 잡음에 보다 강건하다. 또한, 이동 물체의 움직임으로 발생할 수 있는 오류를 최대한 배재한다.