• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.277-280
• /
• 2003

본 연구에서는 자궁종양 세포를 정상, 비정상으로 진단하기 위한 세포핵의 특성값 추출 방법으로 3차원 형태학적 분석 방법을 제안한다. 컨포컬 현미경을 이용하여 3차원 볼륭데이터를 획득하고 3차원 연결 성분 레이블링을 적용하였다 레이블링 후, 각각의 세포핵으로부터 3차원 형태학적 특성값을 추출하였으며 정상세포핵과 비정상세포핵의 3차원 형태계측에 대한 차이를 비교하였다. 이는 잘린 단면의 각도나 두께에 따라 서로 다른 분석 결과를 나타내는 2차원 영상분석방법의 한계를 극복할 수 있으며 실체에 가까운 계측으로 보다 객관적이고 정확한 병리진단을 위한 보조도구로써 활용될 수 있다.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.846-855
• /
• 2007

Significant feature extraction in cancer cell image analysis is an important process for grading cell carcinoma. In this study, we propose a method for 3D quantitative analysis of cell nuclei based upon digital image cytometry. First, we acquired volumetric renal cell carcinoma data for each grade using confocal laser scanning microscopy and segmented cell nuclei employing color features based upon a supervised teaming scheme. For 3D visualization, we used a contour-based method for surface rendering and a 3D texture mapping method for volume rendering. We then defined and extracted the 3D morphological features of cell nuclei. To evaluate what quantitative features of 3D analysis could contribute to diagnostic information, we analyzed the statistical significance of the extracted 3D features in each grade using an analysis of variance (ANOVA). Finally, we compared the 2D with the 3D features of cell nuclei and analyzed the correlations between them. We found statistically significant correlations between nuclear grade and 3D morphological features. The proposed method has potential for use as fundamental research in developing a new nuclear grading system for accurate diagnosis and prediction of prognosis.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.83-92
• /
• 2011

The aim of this study is to evaluate whether 3D nuclear chromatin texture features are significant in recognizing the progression of cervical cancer. In particular, we assessed that our method could detect subtle differences in the chromatin pattern of seemingly normal cells on specimens with malignancy. We extracted nuclear texture features based on 3D GLCM(Gray Level Co occurrence Matrix) and 3D Wavelet transform from 100 cell volume data for each group (Normal, LSIL and HSIL). To evaluate the feasibility of 3D chromatin texture analysis, we compared the correct classification rate for each of the classifiers using them. In addition to this, we compared the correct classification rates for the classifiers using the proposed 3D nuclear texture features and the 2D nuclear texture features which were extracted in the same way. The results showed that the classifier using the 3D nuclear texture features provided better results. This means our method could improve the accuracy and reproducibility of quantification of cervical cell.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.866-876
• /
• 1996

A feature extraction method for the objects that have a circular cross section is proposed.To implement a robust recognition system which can effectively deal with various types of 2-dimensional image and 3-dimensional image, both 2- dimensional information and 3-dimensional information should be collectively extracted and combined for the optimum. For this, this paper presents a feature extraction method for 3-dimensional objects, particularly for the objects with a circular cross section which most objects in the real world are known to have. Firstly, the Z gradient is proposed to extract the shape information from those objects. Using this information, normal vectors are derived from the surface patches. The intersection points between the vectors are applied to the geometric feature extraction.Also, for more accurate recognition, a feature extraction method for between surface regions is proposed.Finally, the extraction method of function information is investigated for the final recognition process.The usefulness of the proposed method is proved through the experimentation.

• Journal of Korea Multimedia Society
• /
• v.8 no.1
• /
• pp.34-45
• /
• 2005

In this paper, a novel implementation of a person verification system based on depth-weighted Hausdorff distance (DWHD) using the surface curvature of the face is proposed. The definition of Hausdorff distance is a measure of the correspondence of two point sets. The approach works by finding the nose tip that has a protrusion shape on the face. In feature recognition of 3D face image, one has to take into consideration the orientated frontal posture to normalize after extracting face area from original image. The binary images are extracted by using the threshold values for the curvature value of surface for the person which has differential depth and surface characteristic information. The proposed DWHD measure for comparing two pixel sets were used, because it is simple and robust. In the experimental results, the minimum curvature which has low pixel distribution achieves recognition rate of 98% among the proposed methods.

• Journal of Korea Multimedia Society
• /
• v.11 no.4
• /
• pp.423-433
• /
• 2008

The surface curvatures extracted from the face contain the most important personal facial information. In particular, the face shape using the depth information represents personal features in detail. In this paper, we develop a method for recognizing the range face images by combining the multiple face regions using fuzzy integral. For the proposed approach, the first step tries to find the nose tip that has a protrusion shape on the face from the extracted face area and has to take into consideration of the orientated frontal posture to normalize. Multiple areas are extracted by the depth threshold values from reference point, nose tip. And then, we calculate the curvature features: principal curvature, gaussian curvature, and mean curvature for each region. The second step of approach concerns the application of eigenface and Linear Discriminant Analysis(LDA) method to reduce the dimension and classify. In the last step, the aggregation of the individual classifiers using the fuzzy integral is explained for each region. In the experimental results, using the depth threshold value 40 (DT40) show the highest recognition rate among the regions, and the maximum curvature achieves 98% recognition rate, incase of fuzzy integral.

• Proceedings of the KSRS Conference
• /
• 2007.03a
• /
• pp.262-266
• /
• 2007

조간대의 생물상과 조류로는 조간대 내의 모래나 펄을 구성하는 입자의 크기와 조성에 의하여 많은 영향을 받는다. 이런 조류로의 특성을 파악하기 위하여 전통적으로 현장조사를 실시하였으나 이 방법은 짧은 조간대의 노출시간 동안 넓은 조간대 지역을 파악하기 힘든 단점이 있다. 이러한 단점을 극복하기 위하여 최근 국내외적으로 위성자료와 현장조사롤 통해 조간대내의 조류로 발달을 연구하는 노력이 활발히 진행 중 이다. 본 연구에서는 프랙탈 이론을 적용하여 발달양상이 다른 두 지역의 조류로의 발달정도를 정량적인 값으로 나타내었다. 본 연구에서는 강화도 남단 조간대에 대하여 IKONOS 영상에서 조류로를 추출한 뒤, 프랙탈 분석방법 중 2차원 분석에 많이 사용되는 box counting 방법을 적용하여 프랙탈 차원을 구하였다. 분석 결과, 강화도 남단 조간대 전체 지역에 대한 프랙탈 차원 값은 약 1.31 로 나타났다. 조류로의 지선이 단순하며 남북으로 수직방향으로 발달한 지역은 프랙탈 차원 값이 $1.0563{\sim}1.0672$로 나타났으며，조류로의 지선이 발달하고 매우 복잡한 형태를 보이는 곳은 프랙탈 차원 값이 $1.255{\sim}1.3016$로 나타나는 것을 알 수 있었다. 실제 해안선과 같은 곡선의 경우 프랙탈 차원 값이 $1.1{\sim}1.3$ 정도 나타나는데 본 연구에서 얻어진 프랙탈 차원 값을 보면 매우 흡사하게 나온 것을 알 수가 있다. 또한， 양상이 다른 두 지역의 프랙탈 차원 값이 약 0.2 정도 차이를 나타내는 것을 알 수가 있다. 이 결과는 영상에서의 조류로 발달의 복잡성에 대한 구분을 뒷받침 할 수 있을 것으로 생각한다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.3
• /
• pp.229-234
• /
• 2018

Texture is one of the most useful features in classifying and segmenting images. The LBP-based approach previously presented in the literature has been successful in many applications. However, it's theoretical foundation is based only on the difference of pixel values, and consequently it has a number of drawbacks like it performs poorly for the images corrupted with noise, and especially it cannot be used as a multiscale texture descriptor due to the exploding increase of feature vector dimension with increase of the number of neighbor pixels. In this paper, we present a method to address these drawbacks of LBP-based approach. More specifically, our approach quantizes the range of pixels values and construct a 3D histogram which captures the correlative information of pixels. This histogram is used as a texture feature. Several tests with texture images show that the proposed method outperforms the LBP-based approach in the problem of texture classification.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.696-699
• /
• 2004

본 논문은 현실감 있는 영상 기반 환경 모델의 생성을 위해 영상 분할 기반 환경 모델링 방법을 제안한다. 입력 영상을 환경 특성에 따라 바닥면, 천정(하늘), 주변 물체들로 분할하고 분할된 바닥면이나 천정을 참조 평면으로 설정하고 주변 물체들의 깊이값을 계산함으로써 상세한 환경 모델을 얻을 수 있다. 영상 분할 환경 모델링 방법은 환경 맵에 적용하기 용이하며 환경의 특성에 따른 깊이값 추출 방법으로 손쉽게 환경 모델링이 가능하다. 또한, 시점이 이동되고 시차를 갖는 환경의 표현이 가능하다.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.230-239
• /
• 2003

This paper presents face recognition algorithm using projection vector reflecting local feature for the area in contour lines. The outline shape of a face has many difficulties to distinguish people because human has similar face shape. For 3 dimensional(3D) face images include depth information, we can extract different face shapes from the nose tip using some depth values for a face image. In this thesis deals with 3D face image, because the extraction of contour lines from 2 dimensional face images is hard work. After finding nose tip, we extract two areas in the contour lilies from some depth values from 3D face image which is obtained by 3D laser scanner. And we propose a method of projection vector to localize the characteristics of image and reduce the number of index data in database. Euclidean distance is used to compare of similarity between two images. Proposed algorithm can be made recognition rate of 94.3% for face shapes using depth information.