Retinex theory represents the human visual system by showing the relative reflectance of an object under various illumination conditions. A feature of this human visual system is color constancy, and the Retinex theory is designed in consideration of this feature. The Retinex algorithms have been popularly used to effectively decompose the illumination and reflectance of an object. The main aim of this paper is to study image enhancement using convolution sparse coding and sparse representations of the reflectance component in the Retinex model over a learned dictionary. To realize this, we use the convolutional sparse coding model to represent the reflectance component in detail. In addition, we propose that the reflectance component can be reconstructed using a trained general dictionary by using convolutional sparse coding from a large dataset. We use singular value decomposition in limited memory to construct a best reflectance dictionary. This allows the reflectance component to provide improved visual quality over conventional methods, as shown in the experimental results. Consequently, we can reduce the difference in perception between humans and machines through the proposed Retinex-based image enhancement.

Color constancy is the feature of the human vision system (HVS) that ensures the relative constancy of the perceived color of objects under varying illumination conditions. The Retinex theory of machine vision systems is based on the HVS. Among Retinex algorithms, the physics-based algorithms are efficient; however, they generally do not satisfy the local characteristics of the original Retinex theory because they eliminate global illumination from their optimization. We apply the sparse source separation technique to the Retinex theory to present a physics-based algorithm that satisfies the locality characteristic of the original Retinex theory. Previous Retinex algorithms have limited use in image enhancement because the total variation Retinex results in an overly enhanced image and the sparse source separation Retinex cannot completely restore the original image. In contrast, our proposed method preserves the image edge and can very nearly replicate the original image without any special operation.

Color constancy is a feature of the human visual system, which detects the relative inconsistency of the perceived color of an object so that the perceived color may not be changed under various illumination conditions, even when the conditions for observing color are changed. Thus, the Retinex theory was designed in consideration of this color constancy. The physics based Retinex algorithms have been popularly used to effectively decompose the illumination and reflectance of the object. However, if there are many detail areas in the image or the illumination changes rapidly, the illumination and reflectance may not be decomposed properly, because of the violation of the smoothness constraint on illumination. In this paper, we use the convolutional sparse coding model to represent the reflectance in more detail. This allows the reflectance component to provide improved visual quality over conventional methods, as shown in experimental results. Consequently, we can decompose Retinex based illumination and reflectance more precisely, then, reduce the perception gap between humans and machines.

Nystrom 방법은 Symmetric Positive -Semidefinite (SPSD) 행렬의 열들을 균등하게 샘플링하여 SPSD 행렬의 저-랭크 성분을 예측하는 방법이다. 그러나, 정확한 복원을 위해서는 선택된 열들로 이뤄진 집합의 행렬이 풀-랭크의 성질을 만족해야 하는 강력한 전제조건이 수반되는데, 실제로 이러한 조건을 만족시키는 샘플링 방법을 찾기는 매우 어렵다. 본 논문에서는 원래의 SPSD 행렬로부터 가능한 한 정보를 많이 가진 열들을 획득하기 위하여 간접적으로 기하학적 Coherence 값을 활용하는 방법을 새롭게 제안하였다. 또한, 제안하는 방법에서는, Coherence 값을 적절한 레벨로 맞추고 이를 통해 성공적인 SPSD 행렬의 저-랭크 성분 예측을 가능케 하기 위하여 극 희귀 랜덤 투사법을 활용하였다. 결과적으로 제안하는 기법은 기존의 Nystrom 샘플링 방법들에 비하여, 계산량은 현격히 줄고 성능은 one-shot 기법과 같은 최상위 기법에 근접하는 효율적인 기법임을 실험을 통하여 검증하였다.

단일 영상 내 반사 영역 제거는 영상처리 및 컴퓨터 비전에서 중요한 문제이다. 이 문제를 해결하기 위해 본 논문은 해당 문제를 영상데이터 간 전환 문제로 정의한다. 다양한 영상데이터 간 전환 문제에서 조건부 적대적 생성신경망은 높은 성능을 달성하였으며, 이에 본 논문 또한 공간 적응적 비 정규화 기법을 활용한 조건부 적대적 생성신경망을 활용하여 단일 영상 내 반사 영역 제거방법을 제안한다. 반사 영역 제거와 관련된 공인 데이터 세트를 활용한 실험에서 제안된 방법은 기존 방법보다 높은 성능을 가지는 것을 확인할 수 있다.