• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.373-376
• /
• 2011

얼굴 영상에서 구성요소(눈썹, 눈, 코, 입 등)의 존재에 따라 보는 사람의 얼굴 인식 정확도는 큰 영향을 받는다. 이는 인간의 뇌에서 얼굴 정보를 처리하는 과정은 얼굴 전체 영역 뿐만 아니라, 부분적인 얼굴 구성요소의 특징들도 고려함을 말한다. 비음수 행렬 분해(NMF: Non-negative Matrix Factorization)는 이러한 얼굴 영역에서 부분적인 특징들을 잘 표현하는 기저영상들을 찾아내는데 효과적임을 보여주었으나, 각 기저영상들의 중요도는 알 수 없었다. 본 논문에서는 NMF로 찾아진 기저영상들에 대응되는 인코딩 정보를 SLR(Sparse Logistic Regression)을 이용하여 성별 인식에 중요한 부분 영역들을 찾고자 한다. 실험에서는 주성분분석(PCA)과 비교를 통해 NMF를 이용한 기저영상 및 특징 벡터 추출이 좋은 성능을 보여주고, 대표적 이진 분류 알고리즘인 SVM(Support Vector Machine)과 비교를 통해 SLR을 이용한 특징 벡터 선택이 나은 성능을 보여줌을 확인하였다. 또한 SLR로 확인된 각 기저영상에 대한 가중치를 통하여 인식 과정에서 중요한 얼굴 영역들을 확인할 수 있다.

• Korean Journal of Cognitive Science
• /
• v.22 no.4
• /
• pp.347-364
• /
• 2011

In this paper, we propose a automatic image bases extraction method for visual image reconstruction from brain activity using Non-negative Matrix Factorization (NMF). Image bases are basic elements to construct and present a visual image. Previous method used brain activity that evoked by predefined 361 image bases of four different sizes: $1{\times}1$, $2{\times}1$, $1{\times}2$, $2{\times}2$, and $2{\times}2$. Then the visual stimuli were reconstructed by linear combination of all the results from these image bases. While the previous method used 361 predefined image bases, the proposed method automatically extracts image bases which represent the image data efficiently. From the experiments, we found that the proposed method reconstructs the visual stimuli better than the previous method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.615-618
• /
• 2008

본 논문에서는 각 개인의 동작영상에 대한 국부고유공간에 바탕을 둔 기저영상을 이용한 효율적인 수화영상 인식 기법을 제안하였다. 여기서 국부고유공간의 추출은 주요성분분석을 이용한 것으로 동작영상의 국소특징을 더욱 더 잘 반영하기 위함이고, 기저영상의 추출은 독립성분분석을 이용한 것으로 수화영상 내에 포함된 고차원의 독립적인 특징들을 반영하여 보다 개선된 인식성능을 얻기 위함이다. 제안된 기법을 240*215 픽셀의 80(1명*5동물*16동작)개 동물을 표현하는 수화동작을 대상으로 Euclidean의 분류척도를 이용하여 실험한 결과, 단순 국부고유공간을 이용한 방법에 비해 우수한 인식성능이 있음을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.81-85
• /
• 1998

점확산 함수(point spread function; PSF)의 정확한 추정은 복원결과가 원 영상에 얼마나 근접할 수 있는가를 결정한다는 점에서 영상처리의 중요한 연구 주제중의 하나가 된다. 본 논문에서는 PSF를 추정하기 위한 알고리즘을 제안하고, 이를 영상복원에 적용한 후 이를 기반으로 디지털 자동초점시스템을 제안한다. 초점불안전 열화시스템을 구현하기 위한 과정은 두 단계로 구성되어 있는데, 즉 입력 영상에서 에지분류를 통한 PSF 추정과, 이를 이용한 영상복원이다. 보다 구체적으로, 입력 영상에 특정 에지가 있는 임의의 크기의 블록을 선정해부면, 그 블록으로부터 자동으로 에지방향이 기저영상을 이용해서 구해지며 확산원의 크기를 추정하여 1차원 단위 계단응답과 영역을 구하여 평균한 후, 2차원 등방성 PSF를 추정한다. 마지막으로 추정된 PSF를 사용하여 복원을 수행함으로써 초점이 맞는 영상을 구한다.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.7-14
• /
• 2006

This paper presents an efficient face recognition method using both first moment of image and basis images. First moment which is a method for finding centroid of image, is applied to exclude the needless backgrounds in the face recognitions by shifting to the centroid of face image. Basis images which are the face features, are respectively extracted by principal component analysis(PCA) and fixed-point independent component analysis(FP-ICA). This is to improve the recognition performance by excluding the redundancy considering to second- and higher-order statistics of face image. The proposed methods has been applied to the problem for recognizing the 48 face images(12 persons*4 scenes) of 64*64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed methods has a superior recognition performances(speed, rate) than conventional PCA and FP-ICA without preprocessing, the proposed FP-ICA has also better performance than the proposed PCA. The city-block has been relatively achieved more an accurate similarity than Euclidean or negative angle.

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.481-488
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization) and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architectureII, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortions.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.266-274
• /
• 2007

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on top-down machine learning and recursive error back-projection. A face is represented by a linear combination of prototypes of shape and that of texture. With the shape and texture information of each pixel in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those that of texture by solving least square minimizations. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. In addition, a recursive error back-projection procedure is applied to improve the reconstruction accuracy of high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution images captured at a distance.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.3
• /
• pp.102-109
• /
• 2009

Purpose: Flash 3D (pixon(R) method; 3D OSEM) was developed as a software program to shorten exam time and improve image quality through reconstruction, it is an image processing method that usefully be applied to nuclear medicine tomography. If perfoming brain diamox perfusion scan by reconstructing subtracted images by Flash 3D with shortened image acquisition time, there was a problem that SNR of subtracted image is lower than basal image. To increase SNR of subtracted image, we use LEAP collimators, and we emphasized on sensitivity of vessel dilatation than resolution of brain vessel. In this study, our purpose is to confirm possibility of application of LEAP collimators at brain diamox perfusion tomography, identify proper reconstruction factors by using Flash 3D. Materials and methods: (1) The evaluation of phantom: We used Hoffman 3D Brain Phantom with $^{99m}Tc$. We obtained images by LEAP and LEHR collimators (diamox image) and after 6 hours (the half life of $^{99m}Tc$: 6 hours), we use obtained second image (basal image) by same method. Also, we acquired SNR and ratio of white matters/gray matters of each basal image and subtracted image. (2) The evaluation of patient's image: We quantitatively analyzed patients who were examined by LEAP collimators then was classified as a normal group and who were examined by LEHR collimators then was classified as a normal group from 2008. 05 to 2009. 01. We evaluate the results from phantom by substituting factors. We used one-day protocol and injected $^{99m}Tc$-ECD 925 MBq at both basal image acquisition and diamox image acquisition. Results: (1) The evaluation of phantom: After measuring counts from each detector, at basal image 41~46 kcount, stress image 79~90 kcount, subtraction image 40~47 kcount were detected. LEAP was about 102~113 kcount at basal image, 188~210 kcount at stress image and 94~103 at subtraction image kcount were detected. The SNR of LEHR subtraction image was decreased than LEHR basal image about 37%, the SNR of LEAP subtraction image was decreased than LEAP basal image about 17%. The ratio of gray matter versus white matter is 2.2:1 at LEHR basal image and 1.9:1 at subtraction, and at LEAP basal image was 2.4:1 and subtraction image was 2:1. (2) The evaluation of patient's image: the counts acquired by LEHR collimators are about 40~60 kcounts at basal image, and 80~100 kcount at stress image. It was proper to set FWHM as 7 mm at basal and stress image and 11mm at subtraction image. LEAP was about 80~100 kcount at basal image and 180~200 kcount at stress image. LEAP images could reduce blurring by setting FWHM as 5 mm at basal and stress images and 7 mm at subtraction image. At basal and stress image, LEHR image was superior than LEAP image. But in case of subtraction image like a phantom experiment, it showed rough image because SNR of LEHR image was decreased. On the other hand, in case of subtraction LEAP image was better than LEHR image in SNR and sensitivity. In all LEHR and LEAP collimator images, proper subset and iteration frequency was 8 times. Conclusions: We could archive more clear and high SNR subtraction image by using proper filter with LEAP collimator. In case of applying one day protocol and reconstructing by Flash 3D, we could consider application of LEAP collimator to acquire better subtraction image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.759-761
• /
• 2010

In this paper, we propose a video encryption method using pseudo-random numbers based on MLCA(Maximal length Cellular Automata). Firstly, we generate a basis image which is composed with pseudo-random numbers, using MLCA. Futhermore, The original video is encrypted by computing XOR operation between the basis image and each frame of original video. The video encryption is conducted in accordance with one or two rules, and is evaluated.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.303-308
• /
• 2004

The Gabor cosine and sine transform can be applied to image and video compression algorithm by representing image frequency components locally The computational complexity of forward and inverse matrix transforms used in the compression and decompression requires O($N^3$)operations. In this paper, the length of basis functions is truncated to produce a sparse basis matrix, and the computational burden of transforms reduces to deal with image compression and reconstruction in a real-time processing. As the length of basis functions is decreased, the truncation effects to the energy of basis functions are examined and the change in various Qualify measures is evaluated. Experiment results show that 11 times fewer multiplication/addition operations are achieved with less than 1% performance change.