• Journal of Korea Multimedia Society
• /
• v.1 no.2
• /
• pp.173-182
• /
• 1998

As a result of remarkable developments in multimedia technology, the image database system that can efficiently retrieve image data becomes a core technology of information-oriented society. In this paper, we proposed the 2-phase Image Retrieval System considering both color and shape information as the method of image features extraction for content-based image data retrieval. At the first level, to get color information, with improving and extending the indexing method using color distribution characteristic suggested by Striker et al., i.e. the indexing method considering local color distribution characteristics, the system roughly classifies images through the improved method. At the second level, the system finally retrieves the most similar image from the image queried by the user using the shape information about the image groups classified at the first level. To extract the shape information, we use the Improved Moment Invariants (IMI) that manipulates only the pixels on the edges of objects in order to overcome two main problems of the existing Moment Invariant methods large amount of processing and rotation sensitiveness which can frequently be seen in the Directive Histogram Intersection technique suggested by Jain et al. Experiments have been conducted on 300 automobile images. And we could obtain the more improved results through the comparative test with other methods.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.134-142
• /
• 2006

In this paper, we investigate a Hausdorff distance, which is used for the measurement of image similarity, to see whether it is also effective for document retrieval. The proposed method uses a local crowdedness and a Hausdorff distance to locate text images by determining whether a pair of images scanned at different time comes from the same text or not. To reduce the processing time, which is one of the disadvantages of a Hausdorff distance algorithm, we adopt a local crowdedness for feature point extraction. We apply the proposed method to 190 pairs of the same class and 190 pairs of the different class collected from postal envelop images. The results show that the modified Hausdorff distance proposed in this paper performed well in locating the tort region and calculating the degree of similarity between two images. An improvement of accuracy by 2.7% and 9.0% has been obtained, compared to a binary correlation method and the original Hausdorff distance method, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.6
• /
• pp.87-97
• /
• 2015

An Aerial video summarization is not only the key to effective browsing video within a limited time, but also an embedded cue to efficiently congregative situation awareness acquired by unmanned aerial vehicle. Different with previous works, we utilize sensor operation mode of unmanned aerial vehicle, which is global, local, and focused surveillance mode in order for accurately summarizing the aerial video considering flight and surveillance/reconnaissance environments. In focused mode, we propose the moving-react tracking method which utilizes the partitioning motion vector and spatiotemporal saliency map to detect and track the interest moving object continuously. In our simulation result, the key frames are correctly detected for aerial video summarization according to the sensor operation mode of aerial vehicle and finally, we verify the efficiency of video summarization using the proposed mothed.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.5
• /
• pp.45-54
• /
• 2009

In this paper, we propose an adult images detection algorithm using a mean intensity filter and an improved 2D Hough Transform. This paper is composed of three major steps including a training step, a recognition step, and a verification step. The training step generates a mean nipple variance filter that will be used for detecting nipple candidate regions in the recognition step. To make the mean variance filter, we converts an input color image into a gray scale image and normalize it, and make an average intensity filter for nipple areas. The recognition step first extracts edge images and finds connected components, and decides nipple candidate regions by considering the ratio of width and height of a connected component. It then decides final nipple candidates by calculating the similarity between the learned nipple average intensity filter and the nipple candidate areas. Also, it detects breast lines of an input image through the improved 2D Hough transform. The verification step detects breast areas and identifies adult images by considering the relations between nipple candidate regions and locations of breast lines.

• The Journal of the Korea Contents Association
• /
• v.13 no.8
• /
• pp.284-291
• /
• 2013

The importance of ultrasound examination in the field of medical imaging has been emphasized and the interest in sonographic image evaluation is growing. However image evaluations by the non-standardized criteria and methods, so establishment of legal provisions and objective evaluation criteria are needed. In this study, we used SNR to find out more quantitative way and supplement the limitations of the existing phantom image evaluation. The results of acquired 8 images using ATS-539 multipurpose phantom were compared in SNR of sensitivity and gray-scale dynamic range. In the result of the experiment, excellent equipment of existing phantom images are G1, S1 and G2 in regular sequence. In SNR of sensitivity, G1, S1 and G2 and in SNR of gray-scale dynamic range, S1 G1 and G2 in order. In the conclusion, all the experiment results did not show big difference and regular pattern neither. Therefore, the new evaluation measures should be used with the existing phantom image evaluation method for more objective and quantitative evaluation of the ultrasound imaging device.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.763-765
• /
• 2004

본 연구는 간경변을 보유한 환자의 복부 CT 영상을 이용하여 비장의 웨이브 패턴(wave pattern)을 관찰하였는데 정상간을 보유한 환자의 복부 CT 영상과 차이가 있음을 발견하였다. 본 논문은 관찰된 두 가지 원리를 바탕으로 복부 CT 영상에서 비장의 웨이브 패턴을 이용하여 간경변을 효과적으로 진단하는 새로운 방법을 제시한다. 본 논문에서 실험에 사용한 영상들의 경우에 꼬리엽과 우엽의 비율로써 간경변을 보유한 영상임을 알 수 있는 경우에는 모두 비장의 웨이브 패턴 테스트들로써 간경변 보유 판정 결과를 얻었다. 이는 꼬리엽과 우엽의 비율 테스트를 생략하고 비장만으로 간경변 보유간을 판정해 낼 수 있음을 말해주는 것이다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.319-323
• /
• 2000

인터넷이 활성화되면서 청소년에게 유해한 영상을 제공하는 사이트들이 급속히 범람하고 있으며, 이로 인해 청소년들의 정신 건강이 심각하게 훼손되고 있다. 본 논문에서는 청소년들이 접근하기 쉬운 유해 URL 의 웹문서에 대해 그 문서 내에 포함되어 있는 영상들의 유해성을 판별하여 유해 영상을 선택적으로 차단할 수 있는 시스템을 구현하여 제시한다. 유해 URL들에 대해 실험한 결과, 제안한 시스템의 효율은 full nudity의 경우에는 89.6% , 반라의 경우는 70.1% 의 차단 효율을 나타내었으며, 얼굴영상의 경우는 2%의 오판별이 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.331-333
• /
• 2003

본 논문에서는 새로운 얼굴 인식 방법을 제안한다. 제안된 방법은 입력 영상에서 눈이라고 생각되는 영역을 형판 정합방법을 이용하여 먼저 추출하고. 양 눈의 위치 정보를 사용하여 얼굴 영역의 크기와 회전정도를 보정하여 정규화된 얼굴영상을 만들며, 결국 PCA 방법을 사용하여 인식하게 된다. 이렇게 함으로써 PCA가 안정된 영상이 입력되면 좋은 인식률을 보이지만 전반적인 조명의 변화에 잘 대응하지 못하고, 복잡한 배경인 경우 얼굴영역의 위치 변화에 민감하며, 많이 기울어진 영상에 취약하다는 단점을 형판 정합을 통한 전 처리 과정을 통해 보완할 수 있게 된다. 실험 결과 제안된 방법이 PCA의 인식 성능을 크게 향상시킬 수 있음을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10b
• /
• pp.1185-1188
• /
• 2001

본 논문에서는 디지털 영상을 비교하기 위해 평균값과 메디안을 이용한 영상에서의 거리 측정 방법을 제안한다. 그레이 블록 거리(Grey Block Distance: GBD)를 이용하여 완전 영상 해상도를 도입하여 해상도를 다르게 하여 영상을 비교하였다. 이 제안된 방법은 평균값을 이용한 것에 비해 상대적 식별이 더 용이함을 모의 실험을 통해서 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2000.11b
• /
• pp.131-134
• /
• 2000

본 논문에서는 스테레오 좌.우 영상간의 휘도 불균형 보정에 관한 연구를 수행하였다. 좌영상과 우영상의 관계를 선형관계 $(I_L = aI_R +b)$로서 가정하고 휘도 불균형을 보정한 기존 알고리듬(global balancing)의 문제점을 분석하였다. 또한 이러한 문제점을 해결하기 위한 방법으로 두 가지 방법을 제안하는데 히스토그램 균일화를 통한 방법과 영상의 국부적 특징을 이용하여 선형변환을 적용하는 방법(local balancing)이 보다 정확한 변이벡터를 찾는 전처리 과정임을 모의실험을 통해 검증하였다.