• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1149-1155
• /
• 2012

In this paper, we propose cause diagnosis method of semiconductor defects from semiconductor industrial images. Our method constructs feature database (DB) of defect images. Then, defect and input images are subdivided by uniform block. And the block similarity is measured using histogram kai-square distance after color histogram calculation. Then, searched blocks in each image are merged into connected objects using clustering. Finally, the most similar defect image from feature DB is searched with the defect cause by measuring cluster similarity based on features of each cluster. Our method was validated by calculating the search accuracy of n output images having high similarity. With n = 1, 2, 3, the search accuracy was measured to be 100% regardless of defect categories. Our method could be used for the industrial applications.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.77-83
• /
• 2015

Block Truncation Coding, or BTC, is a type of lossy image compression technique for grayscale images. It divides the original images into blocks and then reduces the number of grey levels in each block to compute the mean and standard deviation. BTC has also been adapted to video compression. Another variation of BTC is Absolute Moment Block Truncation Coding. AMBTC is computationally simpler than BTC. In this paper, we proposed new image compression method based on BTC, which is applied patterns to improve compression rate and image quality. This method make two codebooks to extract 36 and 64 patterns from the highest frequency patterns in BTC. When you are compressing an image, you compare many block patterns to that of codebook and use to compress indexes of identical patterns. We experiment our proposed scheme with 36 patterns and the experimental results showed the compression rate of 1.37 bpp. In this paper, our proposed scheme showed higher compression rate rather than that of BTC. In experiment, we used standard images for the performance evaluation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1349-1352
• /
• 2000

대용량의 동영상 데이터 이용에 있어 효과적인 동영상 검색을 위해서는 동영상 데이터의 색인과정이 필요하다. 본 논문은 AVI 영상에서의 내용기반 색인에 기초가 될 동영상의 장면 변환점 검출에 관한 효과적인 방법을 제안하고자 한다. 제안된 방법은 프레임을 블록화 시켜 대각선 방향으로 블록간의 ALH(Average of Luminance Histogram)를 비교하여 일정한 임계치에 도달하지 못할 경우 이 프레임을 장면 변환점으로 검출하게 된다. 점진적 장면의 변화에 대비하기 위해 장면 변환점이 추출될 때까지 임계치 값을 낮춰줌으로서 정확한 장면 전환 지점을 검출하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.253-255
• /
• 2016

본 논문에서는 다중 지역 이진 패턴(Multi-scale Bock LBP, MB-LBP) 특징과 랜덤 포레스트에 기반한 새로운 기법의 머리 방향 분류 기법을 제안한다. 제안 기법에서는 occlusion 과 조명의 변화에 강인한 분류 정확도를 얻기 위해서 랜덤화된 트리를 학습하는 것을 목표로 한다. 우선, 얼굴 이미지로부터 많은 MB-LBP 특징을 추출하고, 얼굴 영상들을 랜덤하게 입력하고 MB-LBP 크기 파라미터와 같은 랜덤 특징과 블록 좌표들을 사용하여 트리를 생성한다. 게다가 각 노드에서 정보 이득을 최대화 하는 트리의 내부 노드를 생성하기 위해서 uniform LBP 의 특성을 고려한 분할 함수를 개발한다. 랜덤화된 트리는 랜덤 포레스트에 포함되어 있으며 마지막 결정단계에서 Maximum-A-Posteriori criterion 으로 최종 결정을 한다. 실험 결과는 제안 기법이 다양한 조명, 자세, 표현, occlusion 상황에서 기존의 방법보다 개선된 성능으로 머리 방향을 분류 할 수 있음을 보여준다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.8C
• /
• pp.598-604
• /
• 2008

The hold-type display panel such as a liquid crystal displays(LCD) has problem of motion blur. The problem can be improved by a Frame Rate-up Conversion(FRC) using a frame interpolation. We propose a Motion Estimation(ME) by using adaptively expanded block based on frame difference for PRC. The proposed method is executed using an adaptively expanded block in order to get more accurate motion vector. By using frame difference, we can reduce complexity more significantly than conventional methods. We use quantitative analysis in order to evaluate experimental results. The results show that the proposed method has better performance and lower complexity than conventional methods.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.306-308
• /
• 2003

본 논문은 컬러영상내 움직이는 객체의 효과적인 검출을 위해 색상과 위치정보를 적용시킨 K-means 클러스터링 알고리즘을 이용하여 움직이는 객체들을 추출한 방법을 제안하고 있다. 최종 클러스터링된 중심픽셀(prototype)이 갖고있는 RGB 값을 사용해 프레임을 비교해 객체와 배경의 분리를 가능하게 했고 마지막으로 후처리를 이용해 남아있는 배경잡음을 제거하였다. 본 연구의 실험은 여러 교통장면을 포함한 다양한 영상에서 이루어졌으며 실험결과 제안된 알고리즘은 기존의 픽셀이나 블록기반의 방법에 비해 보다 정확한 객체 검출이 가능했으며 한 가지 특징 정보를 사용한 클러스터링에 비해 보다 높은 정확도를 보였다.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.272-275
• /
• 2016

This paper presents a method of single image dehazing and surface-based feature detection for remote sensing images. In the conventional dark channel prior (DCP) algorithm, the resulting transmission map invariably includes some block artifacts because of patch-based processing. This also causes image blur. Therefore, a refined transmission map based on a hidden Markov random field and expectation-maximization algorithm can reduce the block artifacts and also increase the image clarity. Also, the proposed algorithm enhances the accuracy of image matching surface-based features in an remote sensing image. Experimental results confirm that the proposed algorithm is superior to conventional algorithms in image haze removal. Moreover, the proposed algorithm is suitable for the problem of image matching based on feature extraction.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.159-167
• /
• 2006

Lipreading has been suggested as one of the methods to improve the performance of speech recognition in noisy environment. However, existing methods are developed and implemented only in software. This paper suggests a hardware design for real-time lipreading. For real-time processing and feasible implementation, we decompose the lipreading system into three parts; image acquisition module, feature vector extraction module, and recognition module. Image acquisition module capture input image by using CMOS image sensor. The feature vector extraction module extracts feature vector from the input image by using parallel block matching algorithm. The parallel block matching algorithm is coded and simulated for FPGA circuit. Recognition module uses HMM based recognition algorithm. The recognition algorithm is coded and simulated by using DSP chip. The simulation results show that a real-time lipreading system can be implemented in hardware.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.163-168
• /
• 2003

In transmitting compressed video bit-stream over Internet, packet loss causes error propagation in both spatial and temporal domain, which in turn leads to severe degradation in image quality. In this paper, a new approach for the recovery of lost or erroneous Motion Vector(MV)s by classifying the movements of neighboring blocks by their homogeneity is proposed. MVs of neighboring blocks are classified according to the direction of MVs and a representative value for each class is determined to obtain the candidate MV set. By computing the distortion of the candidates, a MV with the minimum distortion is selected. Experimental results show that the proposed algorithm exhibits better performance in many cases than existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.11-18
• /
• 2001

In this paper, we proposed the image compression algorithm using triangular feature based GHA. In feature extraction, the input images are divided into eight areas of triangular shape, that has positional information for face image compression. The proposed algorithm reduces blocking effects in image reconstruction and contains informations of face feature and shapes of face as input images are divided into eight. We used triangular feature extraction for positional information and GHA for shape information of face images. Simulation results show that the proposed algorithm has a better performance than the block based K-means and non-parsed image based GHA in PSNR at the same bpp.