Interpolation using neural networks for digital still cameras

Go, Jinwook; Sohn, Kwanghoon; Lee, Chulhee

doi:10.1109/30.883419

Cited by 46 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gupta et al [31] propose to apply median filtering, with the vectors composed of the three colors' neighboring pixels. Other authors [32][33][34][35] have employed this paradigm in more sophisticated ways. Jinwo ok et al [34] propose the use of neural networks.…”

Section: A State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Linear demosaicing inspired by the human visual system

Alleysson

Süsstrunk

Hérault

2005

IEEE Trans. on Image Process.

295

281

View full text Add to dashboard Cite

Abstract-There is an analogy between single-chip color cameras and the human visual system in that these two systems acquire only one limited wavelength sensitivity band per spatial location. We have exploited this analogy, defining a model that characterizes a one-color per spatial position image as a coding into luminance and chrominance of the corresponding three-colors per spatial position image. Luminance is defined with full spatial resolution while chrominance contains sub-sampled opponent colors. Moreover, luminance and chrominance follow a particular arrangement in the Fourier domain, allowing for demosaicing by spatial frequency filtering. This model shows that visual artifacts after demosaicing are due to aliasing between luminance and chrominance and could be solved using a pre-processing filter. This approach also gives new insights for the representation of single-color pe r spatial location images and enables formal and controllable procedures to design demosaicing algorithms that perform well compared to concurrent approaches, as demonstrated by experiments.

show abstract

Section: A State Of the Artmentioning

confidence: 99%

“…Other authors [32][33][34][35] have employed this paradigm in more sophisticated ways. Jinwo ok et al [34] propose the use of neural networks. Trussel et al [33] use optimal wiener filtering.…”

Section: A State Of the Artmentioning

confidence: 99%

Linear demosaicing inspired by the human visual system

Alleysson

Süsstrunk

Hérault

2005

IEEE Trans. on Image Process.

295

281

View full text Add to dashboard Cite

show abstract

TV Display Technology and Video Processing

Bellers

Haan

2015

Handbook of Digital Imaging

View full text Add to dashboard Cite

Video processing demands are strongly influenced by the display device. The revolution in television displays from the Cathode Ray Tubes (CRTs) to modern flat panel displays, like the Plasma Display Panel (PDP) and Liquid Crystal Display (LCD), has accelerated the innovation in video processing. The larger screen sizes and increased brightness, but also the increased diversity in content quality, along with the transition to High Definition television (HDTV) and beyond, has profoundly increased our picture quality expectations. New challenges had to be overcome with video processing, as the new display technologies have some very good, but often also some unfavorable properties. Therefore, new video processing algorithms were necessary to provide adequate solutions. It is fair to say that the display revolution along with the advances in video sources has made video processing an interesting field for many researchers during the last few decades. This chapter briefly reviews the characteristics of the Human Visual System that impact the system design, followed by a review of a number of modern display technologies. Some of the characteristics that negatively affect our perception will be discussed. It will appear that none of the modern displays is ideal for rendering video, and video processing technologies which alleviate the impact from these flaws will be presented.

show abstract

Scanned images resolution improvement using neural networks

Panagiotopoulou

Anastassopoulos

2007

Neural Comput & Applic

View full text Add to dashboard Cite

A novel method of improving the spatial resolution of scanned images, by means of neural networks, is presented in this paper. Images of different resolution, originating from scanner, successively train a neural network, which learns to improve resolution from 25 to 50 pixels-per-inch (ppi), then from 100 to 200 ppi and finally, from 50 to 100 ppi. Thus, the network is provided with consistent knowledge regarding the point spread function (PSF) of the scanner, whilst it gains the generalization ability to reconstruct finer resolution images unfamiliar to it. The novelty of the proposed image-resolutionenhancement technique lies in the successive training of the neural structure with images of increasing resolution. Comparisons with the image scanned at 400 ppi demonstrate the superiority of our method to conventional interpolation techniques.

show abstract

Interpolation using neural networks for digital still cameras

Cited by 46 publications

References 9 publications

Linear demosaicing inspired by the human visual system

Linear demosaicing inspired by the human visual system

TV Display Technology and Video Processing

Scanned images resolution improvement using neural networks

Contact Info

Product

Resources

About