• Journal of the Optical Society of Korea
• /
• 제14권4호
• /
• pp.388-394
• /
• 2010

In this paper the object recognition performance of a photon counting integral imaging system is quantitatively compared with that of a conventional gray scale imaging system. For 3D imaging of objects with a small number of photons, the elemental image set of a 3D scene is obtained using the integral imaging set up. We assume that the elemental image detection follows a Poisson distribution. Computational geometrical ray back propagation algorithm and parametric maximum likelihood estimator are applied to the photon counting elemental image set in order to reconstruct the original 3D scene. To evaluate the photon counting object recognition performance, the normalized correlation peaks between the reconstructed 3D scenes are calculated for the varied and fixed total number of photons in the reconstructed sectional image changing the total number of image channels in the integral imaging system. It is quantitatively illustrated that the recognition performance of the photon counting integral imaging system can be similar to that of a conventional gray scale imaging system as the number of image viewing channels in the photon counting integral imaging (PCII) system is increased up to the threshold point. Also, we present experiments to find the threshold point on the total number of image channels in the PCII system which can guarantee a comparable recognition performance with a gray scale imaging system. To the best of our knowledge, this is the first report on comparisons of object recognition performance with 3D photon counting & gray scale images.

• Journal of the Optical Society of Korea
• /
• 제12권2호
• /
• pp.88-92
• /
• 2008

This paper discusses a photon-counting linear discriminant analysis (LDA) with computational integral imaging (II). The computational II method reconstructs three-dimensional (3D) objects on the reconstruction planes located at arbitrary depth-levels. A maximum likelihood estimation (MLE) can be used to estimate the Poisson parameters of photon counts in the reconstruction space. The photon-counting LDA combined with the computational II method is developed in order to classify partially occluded objects with photon-limited images. Unknown targets are classified with the estimated Poisson parameters while reconstructed irradiance images are trained. It is shown that a low number of photons are sufficient to classify occluded objects with the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권3호
• /
• pp.250-255
• /
• 2012

Face recognition has wide applications in security and surveillance systems as well as in robot vision and machine interfaces. Conventional challenges in face recognition include pose, illumination, and expression, and face recognition at a distance involves additional challenges because long-distance images are often degraded due to poor focusing and motion blurring. This study investigates the effectiveness of applying photon-counting linear discriminant analysis (Pc-LDA) to face recognition in harsh environments. A related technique, Fisher linear discriminant analysis, has been found to be optimal, but it often suffers from the singularity problem because the number of available training images is generally much smaller than the number of pixels. Pc-LDA, on the other hand, realizes the Fisher criterion in high-dimensional space without any dimensionality reduction. Therefore, it provides more invariant solutions to image recognition under distortion and degradation. Two decision rules are employed: one is based on Euclidean distance; the other, on normalized correlation. In the experiments, the asymptotic equivalence of the photon-counting method to the Fisher method is verified with simulated data. Degraded facial images are employed to demonstrate the robustness of the photon-counting classifier in harsh environments. Four types of blurring point spread functions are applied to the test images in order to simulate long-distance acquisition. The results are compared with those of conventional Eigen face and Fisher face methods. The results indicate that Pc-LDA is better than conventional facial recognition techniques.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2008년도 International Meeting on Information Display
• /
• pp.1131-1134
• /
• 2008

In this invited paper, numerical reconstruction and pattern recognition using integral imaging are overviewed. The computational integral imaging method reconstructs three-dimensional information at arbitrary depth-levels. Photon-counting nonlinear matched filtering combined with the computational reconstruction provides promising results for the application of low-light level recognition.

• 대한전자공학회논문지SP
• /
• 제45권6호
• /
• pp.64-69
• /
• 2008

얼굴영상의 인식 기술은 보안과 감시를 비롯하여 머신 인터페이스와 콘텐츠 검색 등에서 활용이 광범위 하다. 그러나 주로 고해상도 영상이 연구의 대상이었고 원거리에서 획득된 저해상도 표적에 대하여 상대적으로 드물게 연구가 이루어졌다. 본 논문에서는 포톤 카운팅(Photon-counting) 선형판별법을 이용하여 저해상도 환경에서 얼굴영상의 인식을 수행한다. 포톤 카운팅 선형판별법은 Fisher 선형 판별법에서 발생하는 특이행렬 문제없이 Fisher의 최적화 기준을 실현한다. 즉, 차원의 축소나 특징 추출 과정 없이 고차원 공간에서 최적화된 투영을 위한 선형판별함수를 구성하고 이를 이용하여 판정하므로 저해상도 환경을 비롯한 얼굴영상의 왜곡의 극복에 효과적이다. 실험 결과는 제안한 방법이 주성분 분석을 활용하는 Eigen face 또는 주성분 분석과 Fisher 선형판별법이 결합된 Fisher face보다 우수하다는 것을 보여준다.

• 한국정보통신학회논문지
• /
• 제19권5호
• /
• pp.1207-1212
• /
• 2015

본 논문에서는 광자 계수 집적 영상 현미경을 사용하여 광자가 희박한 조건에서 마이크로 물체의 3차원 시각화와 인식에 대한 기술을 제안한다. 제안하는 방법에서는 고해상도의 서로 다른 원근감을 가지는 2차원 영상을 획득하기 위해 합성조리개 집적 영상을 사용한다. 그리고 영상으로부터 광자를 추출하기 위해 광자계수 영상 시스템의 수학적 모델인 포아송 분포를 사용하며 통계적 추정법으로 부터 3차원 영상을 추정한다. 따라서, 광자가 희박한 조건에서 마이크로 물체가 손상되지 않으면서 그에 대한 3차원 영상을 획득하고 시각화할 수 있다. 추가적으로, 비선형 상관 필터를 사용하여 3차원 물체의 인식도 가능하다. 본 기술의 유용성을 증명하기 위해, 광학적 실험을 수행하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• 대한전자공학회논문지SP
• /
• 제49권4호
• /
• pp.77-84
• /
• 2012

얼굴인식 기술은 지능형 보안, 웹에서 콘텐츠 검색, 지능로봇의 시각부분, 머신인터페이스 등, 활용이 광범위 하다. 그러나 일반적으로 대상자의 표정과 포즈 변화, 주변의 조명 환경과 같은 문제가 있으며 이와 더불어 원거리에서 획득한 영상의 경우 저해상도를 비롯하여 블러와 잡음에 의한 영상의 열화 등의 여러 가지 어려움이 발생한다. 본 논문에서는 포톤 카운팅(Photon-counting) 선형판별법(Linear Discriminant Analysis)을 이용한 다중 분류기(Classifier)에 의한 판정을 융합하여 얼굴 영상 인식을 수행한다. Fisher 선형판별법은 집단 간 분산을 최대로 하고 집단 내 분산을 최소로 하는 공간으로 선형 투영하는 방법으로, 학습영상의 수가 적을 경우 특이행렬 문제가 발생하지만 포톤카운팅 선형 판별법은 이러한 문제가 없으므로 차원축소를 위한 전 처리 과정이 필요 없다. 본 논문의 다중 분류기는 포톤 카운팅 선형판별법의 유클리드 거리(Euclidean Distance) 또는 정규화된 상관(Normalized Correlation)을 적용하는 판정규칙에 따라 구성된다. 다중분류기의 판정의 융합은 각 분류기 cost의 정규화(Normalization), 유효화(Validation), 그리고 융합규칙(Fusion Rule)으로 구성된다. 각 분류기에서 도출된 cost는 같은 범위로 정규화된 후 유효화 과정에서 선별되고 Minimum, 또는 Average, 또는 Majority-voting의 융합규칙에 의하여 융합된다. 실험에서는 원거리에서 획득한 효과를 구현하기 위하여 고해상도 데이터베이스 영상을 인위적으로 Unfocusing과 Motion 블러를 이용하여 열화하여 테스트하였다. 실험 결과는 다중분류기 융합결과의 인식률은 단일분류기보다 높다는 것을 보여준다.

• Current Optics and Photonics
• /
• 제3권5호
• /
• pp.390-400
• /
• 2019

Encrypted images obtained through double random phase-encoding (DRPE) occupy considerable storage space. We propose efficient compression schemes to reduce the size of the encrypted data. In the proposed schemes, two state-of-art compression methods of JPEG and JP2K are applied to the quantized encrypted phase images obtained by combining the DRPE algorithm with the virtual photon counting imaging technique. We compute the nonlinear cross-correlation between the registered reference images and the compressed input images to verify the performance of the compression of double random phase-encoded images. We show quantitatively through experiments that considerable compression of the encrypted image data can be achieved while security and authentication factors are completely preserved.