Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Sakari Alenius"'
In this paper, we propose two contributions to neural network based denoising. First, we propose applying separate convolutional layers to each sub-band of discrete wavelet transform (DWT) as opposed to the common usage of DWT which concatenates all
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ea99c56360c7bd6cab452a9f6d7b4e5
Publikováno v:
International Journal of Imaging Systems and Technology. 17:105-122
Conventional single-chip digital cameras use color filter arrays (CFA) to sample different spectral components. Demosaicing algorithms interpolate these data to complete red, green, and blue values for each image pixel, to produce an RGB image. In th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b83f95832fb3e26014e564530df740a
https://doi.org/10.1002/ima.20109
https://doi.org/10.1002/ima.20109
Publikováno v:
Tampere University
Quantitative PET studies require the computation of the attenuation correction factors (ACFs) for compensating the body attenuation effect in the emission data. Short acquisition times for transmission are desired, because of patient comfort and move
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3db1d01bfcf7d357b2c905fcb296d07
https://doi.org/10.1109/23.775593
https://doi.org/10.1109/23.775593
Autor:
Ulla Ruotsalainen, Sakari Alenius
Publikováno v:
Tampere University
The aim of the present study was to investigate a new type of Bayesian one-step late reconstruction method which utilizes a median root prior (MRP). The method favours images which have locally monotonous radioactivity concentrations. The new reconst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c84868edde784705c066227a49b65c18
https://doi.org/10.1007/bf01728761
https://doi.org/10.1007/bf01728761
Publikováno v:
SPIE Proceedings.
Since more processing power, new sensing and display technologies are already available in mobile devices, there has been increased interest in building systems to communicate via different modalities such as speech, gesture, expression, and touch. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::441aa76c276e1498195bf632f37c141b
https://doi.org/10.1117/12.839449
https://doi.org/10.1117/12.839449
Publikováno v:
ICIP
Digital cameras often suffer from limited depth-of-field which results in blurring parts of the captured image. While, in some applications, partial blurring of the scene might be desired, capturing all-in-focus images is usually of main interest. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8de2ea8201d2cd5d11dfac866824dff
https://doi.org/10.1109/icip.2009.5413627
https://doi.org/10.1109/icip.2009.5413627
Publikováno v:
DPS
In this paper we present a new DCT-based method for combined de-noising and sharpening of color images. Our solution combines alpha-rooting and thresholding the DCT coefficients to achieve both sharpening and noise reduction. In our approach, sharpen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aab6b6a2e23a1fa185930de251c06d3d
https://doi.org/10.1109/icdsp.2009.5201097
https://doi.org/10.1109/icdsp.2009.5201097
Publikováno v:
Microprocessing and Microprogramming. 32:447-452
This paper presents a fast and efficient approach to picture segmentation using morphological filters for industrial applications. Using a priori information of the texture, pictures are preprocessed and segmented by thresholding. The statistical mor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7d6cd607d866e1ac5e28296e808b747
https://doi.org/10.1016/0165-6074(91)90384-6
https://doi.org/10.1016/0165-6074(91)90384-6
Publikováno v:
IPAS
In this paper we propose a novel color demosaicing algorithm for noisy data. It is assumed that the data is given according to the Bayer pattern and corrupted by signal-dependant noise which is common for CCD and CMOS digital image sensors. Demosaici
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e353c28baf5c869ef085112b75a69747
https://doi.org/10.1117/12.713595
https://doi.org/10.1117/12.713595
Publikováno v:
ISSPA
The Landweber algorithm is probably one of the simplest iterative method for image restoration which makes it a good choice for practical implementations. In this paper, we introduce a novel Landweber method that uses an adaptive step-size to improve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0262cd4b39c3c0870501f58ccea6486
https://doi.org/10.1109/isspa.2007.4555321
https://doi.org/10.1109/isspa.2007.4555321