Low-Light Image Enhancement Using Adaptive Digital  Pixel Binning

Yoo, Yoonjong; Im, Jaehyun; Paik, Joonki

doi:10.3390/s150714917

Cited by 30 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of the lowest examined MGD (1.62 mGy), the DE images of the inhomogeneous breast phantom were further processed and the DE CNR was recalculated. Hardware pixel binning (on-chip) is designed to increase the sensitivity of an image sensor by combining multiple pixels into one larger pixel in the expense of spatial resolution loss [48]. On the other hand, software pixel binning (off-chip)…”

Section: Cnrmentioning

confidence: 99%

See 1 more Smart Citation

Dual energy subtraction method for breast calcification imaging

Koukou

Martini

Fountos

et al. 2017

Nuclear Instruments and Methods in Physics Research Section A:

View full text Add to dashboard Cite

The aim of this work was to present an experimental dual energy (DE) method for the visualization of microcalcifications (Cs ). A modified radiographic X-ray tube combined with a high resolution complementary metal-oxide-semiconductor (CMOS) active pixel sensor (APS) X-ray detector was used. A 40/70 kV spectral combination was filtered with 100 m  cadmium (Cd) and 1000 m  copper (Cu) for the low/highenergy combination. Homogenous and inhomogeneous breast phantoms and two calcification phantoms were constructed with various calcification thicknesses, ranging from 16 to 152 m . Contrast-to-noise ratio (CNR) was calculated from the DE subtracted images for various entrance surface doses. A calcification thickness of 152 m  was visible, with mean glandular doses (MGD) in the acceptable levels (below 3 mGy). Additional post-processing on the DE images of the inhomogeneous breast phantom resulted in a minimum visible calcification thickness of 93 m  (MGD=1.62 mGy). The proposed DE method could potentially improve calcification visibility in DE breast calcification imaging.

show abstract

Section: Cnrmentioning

confidence: 99%

“…combines multiple pixel values after the signal read out. The result of the off-chip pixel binning can be considered as a filtered version of the input image where the details are smoothed [48]. Between the two methods, there is a slight difference in the image quality, however the spatial resolution of the off-chip method is better [49].…”

Section: Cnrmentioning

confidence: 99%

Dual energy subtraction method for breast calcification imaging

Koukou

Martini

Fountos

et al. 2017

Nuclear Instruments and Methods in Physics Research Section A:

View full text Add to dashboard Cite

show abstract

“…Additionally, the number and variations of datasets used to build a model cannot represent the real world [ 1 ]. Other problems arise when the document is digitalized using a device with low sensor sensitivity and/or under poor illumination conditions [ 2 , 3 , 4 ]. Here, the digitalization may generate additional, frequently heavy noise on the document.…”

Section: Introductionmentioning

confidence: 99%

DCNet: Noise-Robust Convolutional Neural Networks for Degradation Classification on Ancient Documents

2021

View full text Add to dashboard Cite

Analysis of degraded ancient documents is challenging due to the severity and combination of degradation present in a single image. Ancient documents also suffer from additional noise during the digitalization process, particularly when digitalization is done using low-specification devices and/or under poor illumination conditions. The noises over the degraded ancient documents certainly cause a troublesome document analysis. In this paper, we propose a new noise-robust convolutional neural network (CNN) architecture for degradation classification of noisy ancient documents, which is called a degradation classification network (DCNet). DCNet was constructed based on the ResNet101, MobileNetV2, and ShuffleNet architectures. Furthermore, we propose a new self-transition layer following DCNet. We trained the DCNet using (1) noise-free document images and (2) heavy-noise (zero mean Gaussian noise (ZMGN) and speckle) document images. Then, we tested the resulted models with document images containing different levels of ZMGN and speckle noise. We compared our results to three CNN benchmarking architectures, namely MobileNet, ShuffleNet, and ResNet101. In general, the proposed architecture performed better than MobileNet, ShuffleNet, ResNet101, and conventional machine learning (support vector machine and random forest), particularly for documents with heavy noise.

show abstract

“…This produces results similar to that of the preceding theory. Yoo et al proposed a novel digital binning algorithm of image enhancement for low-light scenes in an environment with insufficient illusion (Yoo et al 2015). It can easily be built into an existing image signal processor since the proposed algorithm does not use an iterative computation.…”

Section: Introductionmentioning

confidence: 99%

A knowledge based infrared camera system for invisible gas detection utilizing image processing techniques

Kim

2019

J Ambient Intell Human Comput

View full text Add to dashboard Cite

An infrared camera system for real-time monitoring of invisible methane gas leakages is proposed, which can be used in production, transportation, and gas plants. Instead of using conventional lasers, a medium wavelength light-emitting diode (LED) with a center wavelength of approximately 3300 nm is used for the light source of the gas detector. We achieve compact cooling with low power consumption by using a small electronic part with a Peltier element instead of a larger cooling unit. We also propose an algorithm based on adaptive average method and adaptive histogram equalization process to extract the background efficiently. This knowledge based infrared camera system effectively detects the leakage of invisible gas. Preliminary experimental results confirm the potential and effectiveness of the developed equipment to be commercialized for use in real-time gas monitoring systems. We aim to eventually develop an image analysis system that combines image processing and knowledge engineering techniques.

show abstract

Low-Light Image Enhancement Using Adaptive Digital Pixel Binning

Cited by 30 publications

References 9 publications

Dual energy subtraction method for breast calcification imaging

Dual energy subtraction method for breast calcification imaging

DCNet: Noise-Robust Convolutional Neural Networks for Degradation Classification on Ancient Documents

A knowledge based infrared camera system for invisible gas detection utilizing image processing techniques

Contact Info

Product

Resources

About