• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.191-204
• /
• 2018

To combat the adverse impact imposed by illumination variation in the face recognition process, an effective and feasible algorithm is proposed in this paper. Firstly, an enhanced local texture feature is presented by applying the central symmetric encode principle on the fused component images acquired from the wavelet decomposition. Then the proposed local texture features are combined with Deep Belief Network (DBN) to gain robust deep features of face images under severe illumination conditions. Abundant experiments with different test schemes are conducted on both CMU-PIE and Extended Yale-B databases which contain face images under various illumination condition. Compared with the DBN, LBP combined with DBN and CSLBP combined with DBN, our proposed method achieves the most satisfying recognition rate regardless of the database used, the test scheme adopted or the illumination condition encountered, especially for the face recognition under severe illumination variation.

• 한국의학물리학회지:의학물리
• /
• 제33권4호
• /
• pp.158-163
• /
• 2022

Purpose: We subjected scanning electron microscopic (SEM) images of the active layer of EBT3 film to texture analysis to determine the dose-response curve. Methods: Uncoated Gafchromic EBT3 films were prepared for direct surface SEM scanning. Absorbed doses of 0-20 Gy were delivered to the film's surface using a 6 MV TrueBeam STx photon beam. The film's surface was scanned using a SEM under 100× and 3,000× magnification. Four textural features (Homogeneity, Correlation, Contrast, and Energy) were calculated based on the gray level co-occurrence matrix (GLCM) using the SEM images corresponding to each dose. We used R-square to evaluate the linear relationship between delivered doses and textural features of the film's surface. Results: Correlation resulted in higher linearity and dose-response curve sensitivity than Homogeneity, Contrast, or Energy. The R-square value was 0.964 for correlation using 3,000× magnified SEM images with 9-pixel offsets. Dose verification was used to determine the difference between the prescribed and measured doses for 0, 5, 10, 15, and 20 Gy as 0.09, 1.96, -2.29, 0.17, and 0.08 Gy, respectively. Conclusions: Texture analysis can be used to accurately convert microscopic structural changes to the EBT3 film's surface into absorbed doses. Our proposed method is feasible and may improve the accuracy of film dosimetry used to protect patients from excess radiation exposure.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.138-145
• /
• 2016

LLAH(Locally Likely Arrangement Hashing) is a method which describes image features by exploiting the geometric relationship between their neighbors. Inherently, it is more robust to large view change and poor scene texture than conventional texture-based feature description methods. However, LLAH strongly requires that image features should be detected with high repeatability. The problem is that such requirement is difficult to satisfy in real applications. To alleviate the problem, this paper proposes a method that improves the matching rate of LLAH by exploiting together the brightness of features. Then, it is verified that the matching rate is increased by about 5% in experiments with synthetic images in the presence of Gaussian noise.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2000년도 춘계학술발표논문집
• /
• pp.328-331
• /
• 2000

In this paper , we propose a texture feature extraction method of reduce the massive computational time on extracting texture, features of large sized medical such as MRI, CT-scan , and an index structure, called GLTFT, to speed up the retrieval performance. For these, the original image is transformed into a compressed image by Wavelet transform , and textural features such as contrast, energy, entropy, and homogeneity of the compressed image is extracted by using GLCM(Gray Level Co-occurrence Metrix) . The proposed index structure is organized by using the textural features. The processing in compressed domain can give the solution of storage space and the reduction of computational time of feature extracting . And , by GLTFT index structure, image retrieval performance can be expected to be improved by reducing the retrieval range . Our experiment on 270 MRIs as image database shows that shows that such expectation can be got.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2109-2123
• /
• 2017

This paper presents a super-resolution reconstruction method based on sparse representation for two-dimensional bar code images. Considering the features of two-dimensional bar code images, Kirsch and LBP (local binary pattern) operators are used to extract the edge gradient and texture features. Feature extraction is constituted based on these two features and additional two second-order derivatives. By joint dictionary learning of the low-resolution and high-resolution image patch pairs, the sparse representation of corresponding patches is the same. In addition, the global constraint is exerted on the initial estimation of high-resolution image which makes the reconstructed result closer to the real one. The experimental results demonstrate the effectiveness of the proposed algorithm for two-dimensional bar code images by comparing with other reconstruction algorithms.

• Journal of Yeungnam Medical Science
• /
• 제21권2호
• /
• pp.224-230
• /
• 2004

유방암 검사와 함께 시행한 갑상선 선별 초음파 검사에서 나타난 전형적인 갑상선 유두암의 소견은 경계가 불분명한 고형의 저에코 결절로 나타나고 점상 혹은 미세석회화를 보일 수 있어 이러한 결절에서는 조직 검사를 통한 확진이 필요하다.

• 한국멀티미디어학회논문지
• /
• 제13권2호
• /
• pp.237-248
• /
• 2010

컴퓨터/로봇 비전 분야에서 실세계 장면들을 촬영할 때, 상당 부분의 텍스처 기반 패턴들이 발견되는데, 본 논문에서는 그런 다양한 패턴들을 적절하게 표현할 수 있는 수학적 모델(Gabor 함수)을 기반으로 한 특징 측정 좌표 체계를 소개한다. 그 체계를 통한 텍스처 패턴의 여러 특징들에 대한 측정값의 표현은 텍스처 패턴분류 작업을 수행하는데 보다 효율적인 성능을 가능케 한다. 또한 실험에 사용된 텍스처 이미지 데이터의 좌표 체계에서의 표현 정보가 추후 유사 연구들에 의해 활용될 수 있으며, 제안된 좌표 체계에서 표현된 패턴 데이터를 분류하는데 가장 적합한 의사결정나무 알고리듬을 사용한다. 최종적으로, 다양한 텍스처 패턴분류 실험을 통해 기존 연구 방법들에 비해 연구 결과의 개선이 있음을 보여준다.

• Korean Journal of Radiology
• /
• 제22권11호
• /
• pp.1797-1808
• /
• 2021

Objective: To determine whether volumetric CT texture analysis (CTTA) using fully automatic tumor segmentation can help predict recurrence-free survival (RFS) in patients with intrahepatic mass-forming cholangiocarcinomas (IMCCs) after surgical resection. Materials and Methods: This retrospective study analyzed the preoperative CT scans of 89 patients with IMCCs (64 male; 25 female; mean age, 62.1 years; range, 38-78 years) who underwent surgical resection between January 2005 and December 2016. Volumetric CTTA of IMCCs was performed in late arterial phase images using both fully automatic and semi-automatic liver tumor segmentation techniques. The time spent on segmentation and texture analysis was compared, and the first-order and second-order texture parameters and shape features were extracted. The reliability of CTTA parameters between the techniques was evaluated using intraclass correlation coefficients (ICCs). Intra- and interobserver reproducibility of volumetric CTTAs were also obtained using ICCs. Cox proportional hazard regression were used to predict RFS using CTTA parameters and clinicopathological parameters. Results: The time spent on fully automatic tumor segmentation and CTTA was significantly shorter than that for semi-automatic segmentation: mean ± standard deviation of 1 minutes 37 seconds ± 50 seconds vs. 10 minutes 48 seconds ± 13 minutes 44 seconds (p < 0.001). ICCs of the texture features between the two techniques ranged from 0.215 to 0.980. ICCs for the intraobserver and interobserver reproducibility using fully automatic segmentation were 0.601-0.997 and 0.177-0.984, respectively. Multivariable analysis identified lower first-order mean (hazard ratio [HR], 0.982; p = 0.010), larger pathologic tumor size (HR, 1.171; p < 0.001), and positive lymph node involvement (HR, 2.193; p = 0.014) as significant parameters for shorter RFS using fully automatic segmentation. Conclusion: Volumetric CTTA parameters obtained using fully automatic segmentation could be utilized as prognostic markers in patients with IMCC, with comparable reproducibility in significantly less time compared with semi-automatic segmentation.

• 한국산학기술학회논문지
• /
• 제14권2호
• /
• pp.885-892
• /
• 2013

본 논문에서는 3차원의 입체영상으로부터 질감과 깊이 특징을 활용하여 영상 내에 존재하는 문자를 효과적으로 분할하는 방법을 제안한다. 제안된 문자 분할 방법은 크게 후보 문자영역 추출 단계, 문자영역 지역화 단계, 문자와 배경영역 분리 단계, 그리고 후보 문자영역 검증 단계의 네 가지 단계로 구성된다. 후보 문자영역 추출 단계에서는 입력된 영상에서 질감 특징을 이용해 문자영역이 존재하는 후보 영역을 분할하고, 문자영역 지역화 단계에서는 후보 문자영역 중에서 문자열만을 형성하는 영역을 추출한다. 그리고 문자와 배경 분리 단계에서는 지역화된 문자영역을 문자와 배경으로 분리하며, 후보 문자영역 검증 단계에서는 거리 특징을 활용하여 추출된 문자영역이 비 문자영역을 포함하지 않고 문자영역만을 포함하고 있는지를 최종적으로 검증한다. 실험에서는 제안된 방법을 여러 가지 영상에 적용하여 테스트 해 보았으며, 제안된 방법이 기존의 방법에 비해 보다 정확하게 문자영역을 추출함을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제10권7호
• /
• pp.856-868
• /
• 2007

본 논문에서는 블록의 속성과 질감특징을 이용하여 효과적인 블록 분류 방법을 제안하였다. 제안한 방법에서는 먼저 명암도 문서영상을 이진화한 후, 평활화 기법을 적용하여 블록의 위치정보와 본 논문에서 사용할 특징 중에 하나인 각 블록의 내부에 있는 작은 블록들의 최대 높이 값을 구하였다. 이 위치정보들을 이용하여 문서영상을 각 블록으로 분할한다. 이 블록의 명암도 블록영상에서 문서의 속성이 잘 반영된 (0,1) 방향의 공간 명암도 의존 행렬을 구하여 7가지 질감특징을 구하였다. 먼저 블록의 속성을 최소거리 규칙(Nearest Neighbor Rule)에 입력하여 문자와 비문자 영역으로, 상세분류를 위하여 7가지 질감특징을 이용하여 큰 문자, 작은 문자, 표, 그래픽 및 사진 등으로 구분함으로써 문서인식을 위한 구조 해석뿐만 아니라 다양한 응용 분야에 효과적으로 이용될 수 있도록 하였다.