Deep Learning Based Low-light Enhancement and Noise Suppression in USV Imaging System

AbstractPolarization-sensitive optical coherence tomography (PS-OCT) is a high-resolution label-free optical biomedical imaging modality that is sensitive to the microstructural architecture in tissue that gives rise to form birefringence, such as collagen or muscle fibers. To enable polarization sensitivity in an OCT system, however, requires additional hardware and complexity. We developed a deep-learning method to synthesize PS-OCT images by training a generative adversarial network (GAN) on OCT intensity and PS-OCT images. The synthesis accuracy was first evaluated by the structural similarity index (SSIM) between the synthetic and real PS-OCT images. Furthermore, the effectiveness of the computational PS-OCT images was validated by separately training two image classifiers using the real and synthetic PS-OCT images for cancer/normal classification. The similar classification results of the two trained classifiers demonstrate that the predicted PS-OCT images can be potentially used interchangeably in cancer diagnosis applications. In addition, we applied the trained GAN models on OCT images collected from a separate OCT imaging system, and the synthetic PS-OCT images correlate well with the real PS-OCT image collected from the same sample sites using the PS-OCT imaging system. This computational PS-OCT imaging method has the potential to reduce the cost, complexity, and need for hardware-based PS-OCT imaging systems.

Download Full-text

Low Light Image Enhancement in USV Imaging System Via U-Net and Attention Mechanism

2021 13th International Conference on Machine Learning and Computing ◽

10.1145/3457682.3457729 ◽

2021 ◽

Author(s):

Sheng Zhang ◽

Tianxiao Cai ◽

Yihang Chen

Keyword(s):

Image Enhancement ◽

Imaging System ◽

Attention Mechanism ◽

Low Light ◽

Light Image

Download Full-text

An Improved White-RGB Color Filter Array Based CMOS Imaging System for Cell Phones in Low-Light Environments

IEICE Transactions on Information and Systems ◽

10.1587/transinf.e97.d.1386 ◽

2014 ◽

Vol E97.D (5) ◽

pp. 1386-1389 ◽

Cited By ~ 5

Author(s):

Chang-shuai WANG ◽

Jong-wha CHONG

Keyword(s):

Imaging System ◽

Cell Phones ◽

Color Filter ◽

Low Light ◽

Color Filter Array ◽

Filter Array

Download Full-text

Study on Light Interference Simulation and Performance Evaluation of Low light Imaging System

Journal of Chemical Biological and Physical Sciences ◽

10.24214/jcbps.c.8.1.02836 ◽

2018 ◽

Vol 8 (1) ◽

Keyword(s):

Performance Evaluation ◽

Imaging System ◽

Low Light ◽

Light Interference ◽

And Performance

Download Full-text

Perceptual Quality Assessment of Low-light Image Enhancement

ACM Transactions on Multimedia Computing Communications and Applications ◽

10.1145/3457905 ◽

2021 ◽

Vol 17 (4) ◽

pp. 1-24

Author(s):

Guangtao Zhai ◽

Wei Sun ◽

Xiongkuo Min ◽

Jiantao Zhou

Keyword(s):

Image Quality ◽

Quality Assessment ◽

Image Enhancement ◽

Dynamic Range ◽

State Of The Art ◽

Perceptual Quality ◽

Low Light ◽

Light Image ◽

Light Enhancement

Low-light image enhancement algorithms (LIEA) can light up images captured in dark or back-lighting conditions. However, LIEA may introduce various distortions such as structure damage, color shift, and noise into the enhanced images. Despite various LIEAs proposed in the literature, few efforts have been made to study the quality evaluation of low-light enhancement. In this article, we make one of the first attempts to investigate the quality assessment problem of low-light image enhancement. To facilitate the study of objective image quality assessment (IQA), we first build a large-scale low-light image enhancement quality (LIEQ) database. The LIEQ database includes 1,000 light-enhanced images, which are generated from 100 low-light images using 10 LIEAs. Rather than evaluating the quality of light-enhanced images directly, which is more difficult, we propose to use the multi-exposure fused (MEF) image and stack-based high dynamic range (HDR) image as a reference and evaluate the quality of low-light enhancement following a full-reference (FR) quality assessment routine. We observe that distortions introduced in low-light enhancement are significantly different from distortions considered in traditional image IQA databases that are well-studied, and the current state-of-the-art FR IQA models are also not suitable for evaluating their quality. Therefore, we propose a new FR low-light image enhancement quality assessment (LIEQA) index by evaluating the image quality from four aspects: luminance enhancement, color rendition, noise evaluation, and structure preserving, which have captured the most key aspects of low-light enhancement. Experimental results on the LIEQ database show that the proposed LIEQA index outperforms the state-of-the-art FR IQA models. LIEQA can act as an evaluator for various low-light enhancement algorithms and systems. To the best of our knowledge, this article is the first of its kind comprehensive low-light image enhancement quality assessment study.

Download Full-text