• 대한전자공학회논문지
• /
• 제26권8호
• /
• pp.1262-1269
• /
• 1989

For the efficient recognition of Korean characters, a modified ternary phase-only synthetic discriminanty function filter(MTPOF-SDF) is proposed. MTPOF-SDF can not only discriminate the true class patterns and the similar, symmetric, or patially included false ones but also recognize the diverse variations in true class patterns due to combinatorial form as the same ones. And scale and rotation-invariant recognition is achieved. To preserve the features of the characters, phase information should be used. And to contsrol phase information easily, ternary quantization of the phase is preferred. Also low resolution requirement is achieved for compatibility with low resulution devices such as spatial light modulators.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.304-306
• /
• 2007

Methods of Object recognition from camera image are to compare features of color. edge or pattern with model in a general way. SIFT(scale-invariant feature transform) has good performance but that has high complexity of computation. Using simple color histogram has low complexity. but low performance. In this paper we represent a model as a color cooccurrence histogram. and we improve performance using pyramid matching. The color cooccurrence histogram keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color cooccurrence histogram adds geometric information to the normal color histogram. We suggest object recognition by pyramid matching of color cooccurrence histogram.

• 전기학회논문지
• /
• 제59권2호
• /
• pp.429-435
• /
• 2010

Three dimensional (3-D) object detection and pose estimation from a single view query image has been an important issue in various fields such as medical applications, robot vision, and manufacturing automation. However, most of the existing methods are not appropriate in a real time environment since object detection and pose estimation requires extensive information and computation. In this paper, we present a fast 3-D object detection and pose estimation scheme based on surrounding camera view-changed images of objects. Our scheme has two parts. First, we detect images similar to the query image from the database based on the shape feature, and calculate candidate poses. Second, we perform accurate pose estimation for the candidate poses using the scale invariant feature transform (SIFT) method. We earned out extensive experiments on our prototype system and achieved excellent performance, and we report some of the results.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (2)
• /
• pp.604-606
• /
• 2003

본 논문은 향상된 Scale Invariant Feature Transform (SIFT) 기법과 이로부터 얻어진 로컬 특징 영역에서 다중특징을 이용한 물체인식 방법에 대하여 논하였다. SIFT 기법 [1]은 물체의 크기. 회전. 3차원 좌표변환에 강인한 특성을 갖는다. 이 기법에서는 크기가 다른 가우시안 (Gaussian) 함수를 적용한 영상들의 차이에서의 최대 및 최소값이 특징점으로 결정된다. 하지만 SIFT 알고리듬의 특성상, 인식되어야 될 물체의 비교적 큰 크기 변화, 중요도가 낮은 특징점들의 추출, 그리고 서로 다른 물체에서 추출된 유사한 특징벡터등이 인식 시스템의 신뢰도를 저하 시킬 수 있다. 이에 대응방안으로, 본 논문에서는 상대적으로 낮은 인식정보를 갖는 추출된 특징점을 제거하기 위한 기법과 서로 다른 물체에서 생성된 유사 특징벡터의 구분을 위한 특징점에서의 방위 (orientation) 비교법 및 색차 (chrominance) 정보를 사용에 대하여 기술하였다.

• 한국멀티미디어학회논문지
• /
• 제18권1호
• /
• pp.17-24
• /
• 2015

In this paper, a novel scheme for correcting rotated region in medical images using SIFT(Scale Invariant Feature Transform) algorithm is presented. Using the feature extraction function of SIFT, the rotation angle of rotated object in medical images is calculated as follows. First, keypoints of both reference and rotated medical images are extracted by SIFT. Second, the matching process is performed to the keypoints located at the predetermined ROI(Region Of Interest) at which objects are not cropped or added by rotating the image. Finally, degrees of matched keypoints are calculated and the rotation angle of the rotated object is determined by averaging the difference of the degrees. The simulation results show that the proposed scheme has excellent performance for correcting the rotated region in medical images.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.549-550
• /
• 2019

본 논문에서는 딥 러닝을 이용해 화면 전환을 검출하는 방식을 제안한다. 특징점을 추출할 때는 딥 뉴럴 네트워크를 사용하였고 추출한 특징점을 SIFT(Scale Invariant Features Transform) 기술자를 이용해 128차원 벡터를 생성한다. 이를 기반으로 각 픽셀마다 매칭 여부를 판단하여 25% 미만일 경우 화면 전환이라고 판단한다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 하계학술대회
• /
• pp.1311-1314
• /
• 2022

DNN을 사용하여 객체 인식 과정에서 객체를 잘 분류하기 위해서는 시각적 설명성이 요구된다. 시각적 설명성은 object class에 대한 예측을 pixel-wise attribution으로 표현해 예측 근거를 해석하기 위해 제안되었다, Scale-invariant한 특징을 제공하도록 설계된 pyramidal features 기반 backbone 구조는 object detection 및 classification 등에서 널리 쓰이고 있으며, 이러한 특징을 갖는 feature pyramid를 trainable attention mechanism에 적용하고자 할 때 계산량 및 메모리의 복잡도가 증가하는 문제가 있다. 본 논문에서는 일반적인 FPN에서 객체 인식 성능과 설명성을 높이기 위한 피라미드-주의집중 계층네트워크 (FPN-Attention Layered Network) 방식을 제안하고, 실험적으로 그 특성을 평가하고자 한다. 기존의 FPN만을 사용하였을 때 객체 인식 과정에서 설명성을 향상시키는 방식이 객체 인식에 미치는 정도를 정량적으로 평가하였다. 제안된 모델의 적용을 통해 낮은 computing 오버헤드 수준에서 multi-level feature를 고려한 시각적 설명성을 개선시켜, 결괴적으로 객체 인식 성능을 향상 시킬 수 있음을 실험적으로 확인할 수 있었다.

• Journal of information and communication convergence engineering
• /
• 제12권4호
• /
• pp.263-270
• /
• 2014

Corner detection and feature extraction are essential aspects of computer vision problems such as object recognition and tracking. Feature detectors such as Scale Invariant Feature Transform (SIFT) yields high quality features but computationally intensive for use in real-time applications. The Features from Accelerated Segment Test (FAST) detector provides faster feature computation by extracting only corner information in recognising an object. In this paper we have analyzed the efficient object detection algorithms with respect to efficiency, quality and robustness by comparing characteristics of image detectors for corner detector and feature extractors. The simulated result shows that compared to conventional SIFT algorithm, the object recognition system based on the FAST corner detector yields increased speed and low performance degradation. The average time to find keypoints in SIFT method is about 0.116 seconds for extracting 2169 keypoints. Similarly the average time to find corner points was 0.651 seconds for detecting 1714 keypoints in FAST methods at threshold 30. Thus the FAST method detects corner points faster with better quality images for object recognition.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.575-578
• /
• 2005

Topographical images, in case of aerial or satellite images, are usually similar in colors and textures, and complex in shapes. Thus we have to use shape features of images for efficiently retrieving a query image from topographical image databases. In this paper, we propose a shape feature extraction method which is suitable for topographical images. This method, which improves the existing projection in the Cartesian coordinates, performs the projection operation in the polar coordinates. This method extracts three attributes, namely the number of region pixels, the boundary pixel length of the region from the centroid, the number of alternations between region and background, along each angular direction of the polar coordinates. It extracts the features of complex shape objects which may have holes and disconnected regions. An advantage of our method is that it is invariant to rotation/scale/translation of images. Finally we show the advantages of our method through experiments by comparing it with CSS which is one of the most successful methods in the area of shape feature extraction

• 대기
• /
• 제22권3호
• /
• pp.331-344
• /
• 2012

The changes in the Hadley circulation during the second half of the 20th century were examined using observations and the 20C3M (Twentieth Century Climate in Coupled Models) simulations by the 21 IPCC AR4 models. Multi-model ensemble (MME) mean shows that the mean features of the Hadley circulation, such as the intensity, magnitude, and the seasonal variations, are very realistically reproduced, compared to the ERA40 reanalysis. But the long-term trends of the Hadley circulation in 20C3M MME are quite different to those of observations. The observed intensity of the Hadley cell is persistently enhanced, particularly during boreal winter. In comparison, the meridional overturning circulations reproduced in the MME mean remains invariant in time, and even weakened in boreal summer. This discrepancy between the ERA40 and 20C3M MME is consistently shown in the overall structure of the Hadley circulations, such as mass streamfunction, the velocity potential, the vertical shear of meridional wind, and the vertical velocity in the tropical region. This results indicate that the current climate models are skill-less to capture the long-term trend of Hadley circulation yet, and should be improved in simulation of the large-scale features to enhance the confidence level of future climate change projection.