• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.97-100
• /
• 2000

본 논문에서는 얼굴의 특징 추출 알고리즘을 제안한다. 입력 영상을 이진 영상으로 처리한 후, 얼굴 요소 후보 블록의 면적, 둘레, 원형도, 종횡비를 이용하여 불변하는 눈, 코, 입의 특징 요소를 추출한다. 사람의 얼굴에 대한 특징 요소를 추출하기 위하여 우선 이진 영상을 생성한다. 하나 하나의 고립된 영역으로 분리하기 위하여 화소 레이블링을 한 후 만들어진 얼굴 요소 후보 블록 단위로 면적을 구하고, 윤곽선 추적 방법에 의하여 둘레를 구한 다음 면적, 둘레, 원형도 및 종횡비의 유사도를 구한다 블록의 종합 유사도, 대칭적 거리, 위치의 유사도를 활용하여 눈, 코, 입을 추출한다. 추출된 각 특징 요소간의 거리와 각도를 이용하여 12개의 특징 인수를 구하는 제안 알고리즘을 수행함으로써 얼굴의 특징 인수들을 추출한다. 각 특징점 사이의 거리와 각 거리간의 기울기를 이용하여 100명으로부터 획득한 297개의 원 영상을 대상으로 12개의 특징 파라미터를 추출한 결과 92.93%의 추출 성공률을 보였다. 이러한 결과는 외부 환경의 영향을 덜 받는 눈, 코, 입의 위치 관계의 블록을 근거로 특징 요소를 추출할 수 있도록 제안 알고리즘을 구성하였던 것으로 판단된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.10
• /
• pp.1891-1896
• /
• 2006

In this paper, we propose an improved Active Shape Model for extracting lip contour. Lip deformation is modeled by a statistically deformable model based Active Shape Model. Because each point is moved independently using local profile information in Active Shape Model, many error may happen. To use a global information, we define an energy function similar to an energy function in Active Contour Model, and points are moved to positions at which the total energy is minimized. The experiments have been performed for many lip images of Tulip 1 database, and show that our method extracts lip shape than a traditional ASM more exactly.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.2
• /
• pp.132-135
• /
• 2009

The video similarity measure is very important factor to index and to retrieve for video data. In this paper, we propose the luminance projection model to measure the video similarity efficiently. Most algorithms for video indexing have been commonly used histograms, edges, or motion features, whereas in this paper, the proposed algorithm is employed an efficient measure using the luminance projection. To index effectively the video sequences and to decrease the computational complexity, we calculate video similarity using the key frames extracted by the cumulative measure, and compare the set of key frames using the modified Hausdorff distance. Experimental results show that the proposed luminance projection model yields the remarkable accuracy and performance than the conventional algorithm.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.829-840
• /
• 2013

In this paper, we propose a new lung segmentation method for chest x-ray images which can take both global and local properties into account. Firstly, the initial lung segmentation is computed by applying the active shape model (ASM) which keeps the shape of deformable model from the pre-learned model and searches the image boundaries. At the second segmentation stage, we also applied the localizing region-based active contour model (LRACM) for correcting various regional errors in the initial segmentation. Finally, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by a radiologist. The comparison experiments were performed using 5 lung x-ray images. In our experiment, the Dice coefficient with manually segmented area was $95.33%{\pm}0.93%$ for the proposed method. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for a more accurate early diagnosis and prognosis regarding lung cancer in chest x-ray images.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.256-263
• /
• 2022

Skin cancer is one of the most common diseases in the world, and the incidence rate in Korea has increased by about 100% over the past five years. In the United States, more than 5 million people are diagnosed with skin cancer every year. Skin cancer mainly occurs when skin tissue is damaged for a long time due to exposure to ultraviolet rays. Melanoma, a malignant tumor of skin cancer, is similar in appearance to Atypical melanocytic nevus occurring on the skin, making it difficult for the general public to be aware of it unless secondary signs occur. In this paper, we propose a skin cancer lesion edge detection algorithm and a deep learning model, CRNN, which performs skin cancer lesion classification for early detection and classification of these skin cancers. As a result of the experiment, when using the contour detection algorithm proposed in this paper, the classification accuracy was the highest at 97%. For the Canny algorithm, 78% was shown, 55% for Sobel, and 46% for Laplacian.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.12 no.5
• /
• pp.415-427
• /
• 1987

This paper presents an experimental model-based vision system which can identify and locate objects in scenes containing multiple occluded parts. The objects are assumed to be rigid and planar parts. In any recognition system the-type of objects that might appear in the image dictates the type of knowledge that is needed to recognize the object. The data is reduced to a sequential list of points or pixels that appear on the boundary of the objects. Next the boundary of the objects is smoothed using a polygonal approximation algorithm. Recognition cosists in finding the prototype that matches model to image. Now the hidden edge is reconstructed by transition model objects into occluded objects. The best match is obtained by optimising some similarity measure.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.1-8
• /
• 2000

This paper describes an algorithm for semantic video object tracking using semi automatic method. In the semi automatic method, a user specifies an object of interest at the first frame and then the specified object is to be tracked in the remaining frames. The proposed algorithm consists of three steps: object boundary projection, uncertain area extraction, and boundary refinement. The object boundary is projected from the previous frame to the current frame using the motion estimation. And uncertain areas are extracted via two modules: Me error-test and color similarity test. Then, from extracted uncertain areas, the exact object boundary is obtained by boundary refinement. The simulation results show that the proposed video object extraction method provides efficient tracking results for various video sequences compared to the previous methods.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2396-2398
• /
• 2001

Active contour로 알려져 있는 snake는 반복적인 계산으로 이미지상에서 찾고자 하는 물체의 외곽선에 수렴하는 contour로 이미지 상의 물체의 외곽선으로부터 발생하는 외부 에너지(external energy)와 contour 자체로부터 기인하는 내부 에너지(internal energy)를 최소화하는 방향으로 움직인다. 그러나 물체의 윤곽선으로부터 발생하는 외부 에너지는 찾고자 하는 물체뿐만 아니라 주위의 다른 물체로부터도 발생하므로 만일 추적하고자 하는 물체의 주변에 다른 물체들이 존재한다면 snake은 올바르게 동작하지 않게 된다. 본 논문에서는 이러한 단점을 극복하기 위하여 물체의 색상정보를 이용하는 방식을 제안하였다. 물체의 색상 정보는 물체의 고유한 특성 중의 하나로 본 논문에서는 색상정보를 이용하여 원래의 이미지를 찾고자 하는 물체의 색상과 얼마나 유사한가를 나타내는 확률 이미지로 변환하였다. 이렇게 변환된 확률 이미지 상에서 snake 알고리즘을 적용함으로써 배경의 다른 물체로부터 발생하는 외부 에너지를 효과적으로 제거할 수 있다. 또한 본 논문에서는 물체가 이동함에 따라 변화하는 색상 정보를 지속적으로 갱신함으로써 물체의 추적이 효과적으로 이루어지도록 하였다.

• Journal of KIISE:Databases
• /
• v.32 no.5
• /
• pp.498-508
• /
• 2005

A shape data is used one oi most important feature for image retrieval as data to reflect meaning of image. Especially, structural feature of shape is widely studied because it represents primitive properties of shape and relation information between basic units well. However, most structural features of shape have the problem that it is not able to guarantee an efficient search time because the features are expressed as graph or tree. In order to solve this problem, we generate curvature-based morphological graph, End design key to cluster shapes from this graph. Proposed this graph have contour features and morphological features of a shape. Shape retrieval is accomplished by stages. We reduce a search space through clustering, and determine total similarity value through pattern matching of external curvature. Various experiments show that our approach reduces computational complexity and retrieval cost.

• Journal of IKEEE
• /
• v.16 no.2
• /
• pp.95-101
• /
• 2012

A novel approach for the reconstruction of 3D building model from aerial image data is proposed in this paper. In this approach, a Centroid Neural Network (CNN) with a metric of line segments is proposed for connecting low-level linear structures. After the straight lines are extracted from an edge image using the CNN, rectangular boundaries are then found by using an edge-based grouping approach. In order to avoid producing unrealistic building models from grouping lined segments, a hierarchical grouping method is proposed in this paper. The proposed hierarchical grouping method is evaluated with a set of aerial image data in the experiment. The results show that the proposed method can be successfully applied for the reconstruction of 3D building model from satellite images.