• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.487-490
• /
• 1999

In this paper we propose an efficient content-based image retrieval method using the color and wavelet based features. The color features are extracted from color histograms of the global image and the wavelet based features are extracted from the invariant moments of the high-pass band image through the spatial-frequency analysis of the wavelet transform. The proposed algorithm, called color and wavelet features based query(CWBQ), is composed of two-step query operations for efficient image retrieval: the coarse level filtering operation and the fine level matching operation. In the first filtering operation, the color histogram feature is used to filter out the dissimilar images quickly from a large image database. The second matching operation applies the wavelet based feature to the retained set of images to retrieve all relevant images successfully. The experimental results show that the proposed algorithm yields more improved retrieval accuracy with computationally efficiency than the previous methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.93-96
• /
• 2002

This paper presents robust and efficient scene-based video watermarking method using visual rhythm (spatio-temporal slice) in compressed domain. Scene change can be detected easily using visual rhythm and video sequences are conveniently edited at the scene boundaries. Therefore, scene-based watermark embedding Process it a natural choice. Temporal spread spectrum can be achieved by applying spread spectrum methods to visual rhythm. Additive Gaussian noise, low-pass filtering, median filtering and histogram equalization attack are simulated for all frames. Frame sub-sampling is also simulated as a typical video attack Simulation results show that proposed algorithm is robust and efficient in the presence of such kind of attacks.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2015년도 하계학술대회
• /
• pp.69-72
• /
• 2015

본 논문에서는 디지털 영상 컨텐츠의 저작권 보호를 위해 DWT 를 이용하여 강인성(robustness), 비가시성(invisibility), 보안성(security)을 만족하는 blind 워터마킹 방법을 제안한다. 이 방법은 영상정보에 대한 변화를 원본 영상의 특정 부분에 국한하지 않게 하기 위해서, 특정 주파수 성분에 워터마크를 삽입하는 것이 아닌 전체 영상에 워터마크를 삽입하는 방법이다. 이 방법에서 저작권에 대한 판단은 추출한 워터마크 정보를 통합 판단하는 방법을 사용한다. 이 방법은 저작권 보호를 위해 원본 영상을 보관할 필요가 없으며, Gaussian filtering, average filtering, sharpening 의 영상 필터링, JPEG 손실 영상 압축, resizing, 영상 품질 향상을 위한 Contrast 나 histogram equalization 등의 공격에 충분한 강인성을 보여준다.

• 대한전기학회논문지
• /
• 제41권8호
• /
• pp.938-946
• /
• 1992

A novel 2-dimensional matched filter of the parallel-jaw type using fuzzy logic is proposed for bin picking. Specifically, the averaged pixel intensity of the windowed region for the filtering is considered to be fuzzy. Also membership functions for darkness and brightness are designed by employing the intensity histogram of the image. Then a rule is given to know how much a windowed region can be a possible holdsite. Furthermore eight rules are made to determine the part orientation, where Mamdani's reasoning method is applied. The proposed technique shows better performances than that of the conventional matched filtering technique in the following senses` 1) most of holdsites determined by the proposed technique are not concentrated at the locations nearly the end of part and 2) our filter is rather insensitive to noises than the conventional method. To show the validities of our proposed technique, some experimental results are illustrated and compared with the results by conventional matched filter technique.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1405-1408
• /
• 1987

X-ray filmed data converted by Image digitizer were processed through the digital computer for edge detections. Sobel operator with the high-pass and the low-pass filtering of the histogram of the images were applied to this work and 3 examples were processed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.979-983
• /
• 1991

A novel 2-dimensional matched filter of the parallel-jaw type using fuzzy logics is proposed for bin picking. Specifically, averaged pixel intensity of the windowed region for the filtering is considered to be fuzzy. Also membership function for darkness and brightness are designed by employing the intensite histogram of image. Then a rule is given to know how much a windowed region can be a possible holdsite. Furthermore eight rules are made to determine the part orientation, where Mamadi's resoning method is applied. To show the validities of our proposed technique. some experimental results are illustrated and compared with the results by conventional matched filter technique.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.219-222
• /
• 2002

In this paper, we propose a new blind image watermarking method in wavelet domain. It is necessary to find out watermark insertion location in blind watermark. We use horizontal and vertical difference of LL components to select watermark insertion location, because increment or decrement of successive components is rarely changed in LL band. A pseudo-random sequence is used as a watermark. Experimental results show that the proposed method is robust to various kinds of attacks such as JPEG lossy compression, averaging, median filtering, resizing, histogram equalization, and additive Gaussian noise.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.209-210
• /
• 2007

Obtained disparity map from the stereo camera by using the several stereo matching algorithms carries lots of noise because of various causes. In our approach, mode filtering and noise elimination technique using the histogram and projection-based region merging methods are adopted for improving the quality of disparity map and image segmentation. The proposed algorithms are implemented in VHDL and the real-time experimentation shows the accurately divided objects.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1998년도 추계학술대회 논문집
• /
• pp.595-600
• /
• 1998

Train wheels tend to wear abrasion due to frequent Starlings and brakings. They are important factors of train safety and noise. However, it is difficult and inaccurate to measure their shape and profile manually. Profile measurement system of train wheel with image processing is proposed. The system consists of CCD cameras, PCI image grabber board, and PC operated on Windows '95. Image processing algorithms such as filtering, histogram equalization, and edge detection are presented, and some processing results are illustrated.

• 대한의용생체공학회:의공학회지
• /
• 제21권4호
• /
• pp.333-338
• /
• 2000

본 논문에서는 T1 강조영상, T2 강조 영상 그리고 PD의 영상의 특징을 상호 보완적으로 이용한 자동적인 영상 분할법을 제안한다. 제안한 분할 알고리듬은 3단계로 이루어지는데, 첫 단계에서는 PD 영상으로부터 대뇌 마스크를 획득한 후, T1과 T2, PD의 입력 영상에 대뇌 마스크를 씌워 각각의 대뇌 영상을 추출하고, 둘째 단계에서는 대뇌 내부 조직에 해당하는 두드러진 클러스터(outstanding cluster)를 3차원 클러스터들 중에서 선택한다. 3차원 클러스터는 최적스케일 영상(optimal scale image)으로 이루어지는 3차원 공간상에서 화소가 밀집된 봉우리들을 교집합해서 생성되는 클러스터로 결정한다. 최적스케일 영상은 각 2타원 히스토그램에 스케일 스페이스 필터링을 적용시키고 그래프(graph) 구조를 검색하여 2차원 히스토그램의 모양을 가장 잘 나타내는 봉우리(peak) 영상을 최적 스케일 영상으로 선택한다. 마지막 단계에서는 앞에서 찾은 두드러진 클러스터의 중심값을 FCM 알고리듬의 초기중심 값으로 두고, FCM 알고리듬을 이용하여 대뇌 영상을 분할한다. 제안한 분할 알고리듬은 정확한 클러스터의 중심값을 계산함으로 초기 값을 영향을 많이 받는 FCM 알고리듬의 단점을 보완하였고 다중 스펙트럼 영상의 특성을 조합하여 분할에 이용함으로 단일 스펙트럼 영상만을 이용하는 방법보다 향상된 결과를 얻을 수 있었다.