FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287377814> ?p ?o ?g. }

• W4287377814 endingPage "4571" @default.
• W4287377814 startingPage "4555" @default.
• W4287377814 abstract "Abstract Depth information is useful in many image processing applications. However, since taking a picture is a process of projection of a 3D scene onto a 2D imaging sensor, the depth information is embedded in the image. Extracting the depth information from the image is a challenging task. A guiding principle is that the level of blurriness due to defocus is related to the distance between the object and the focal plane. Based on this principle and the widely used assumption that Gaussian blur is a good model for defocus blur, we formulate the problem of estimating the spatially varying defocus blurriness as a Gaussian blur classification problem. We solve the problem by training a deep neural network to classify image patches into one of the 20 levels of blurriness. We have created a dataset of more than 500,000 image patches of size $$32times 32$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mn>32</mml:mn> <mml:mo>×</mml:mo> <mml:mn>32</mml:mn> </mml:mrow> </mml:math> which does not require human labelling. The dataset is used to train and test several well-known network models. We find that MobileNetV2 is suitable for this application due to its low memory requirement and high accuracy. The trained model is used to determine the patch blurriness which is then refined by applying an iterative weighted guided filter. The result is a defocus map that carries the information of the degree of blurriness for each pixel. We compare the proposed method with state-of-the-art techniques and we demonstrate its successful applications in adaptive image enhancement and defocus magnification limited to images that present a clear distinction between defocus levels." @default.
• W4287377814 created "2022-07-25" @default.
• W4287377814 creator A5005867720 @default.
• W4287377814 creator A5086801148 @default.
• W4287377814 date "2022-07-25" @default.
• W4287377814 modified "2023-10-14" @default.
• W4287377814 title "Single image defocus map estimation through patch blurriness classification and its applications" @default.
• W4287377814 cites W1916731006 @default.
• W4287377814 cites W1923779427 @default.
• W4287377814 cites W1964313029 @default.
• W4287377814 cites W1966058822 @default.
• W4287377814 cites W1975071260 @default.
• W4287377814 cites W1975912948 @default.
• W4287377814 cites W1977725648 @default.
• W4287377814 cites W1980343256 @default.
• W4287377814 cites W1982471090 @default.
• W4287377814 cites W1983389993 @default.
• W4287377814 cites W1997235063 @default.
• W4287377814 cites W1999671454 @default.
• W4287377814 cites W2014328540 @default.
• W4287377814 cites W2015043644 @default.
• W4287377814 cites W2030148064 @default.
• W4287377814 cites W2035773017 @default.
• W4287377814 cites W2046155154 @default.
• W4287377814 cites W2054203848 @default.
• W4287377814 cites W2054241121 @default.
• W4287377814 cites W2055399164 @default.
• W4287377814 cites W2056176311 @default.
• W4287377814 cites W2061042245 @default.
• W4287377814 cites W2087481065 @default.
• W4287377814 cites W2097966833 @default.
• W4287377814 cites W2113350594 @default.
• W4287377814 cites W2118246710 @default.
• W4287377814 cites W2121953511 @default.
• W4287377814 cites W2125188192 @default.
• W4287377814 cites W2128568805 @default.
• W4287377814 cites W2128597272 @default.
• W4287377814 cites W2134856340 @default.
• W4287377814 cites W2143789285 @default.
• W4287377814 cites W2144854495 @default.
• W4287377814 cites W2162692770 @default.
• W4287377814 cites W2166538457 @default.
• W4287377814 cites W2174865879 @default.
• W4287377814 cites W2233113827 @default.
• W4287377814 cites W2292934097 @default.
• W4287377814 cites W2295475768 @default.
• W4287377814 cites W2509911459 @default.
• W4287377814 cites W2511866412 @default.
• W4287377814 cites W2736613185 @default.
• W4287377814 cites W2741137940 @default.
• W4287377814 cites W2767829160 @default.
• W4287377814 cites W2803525890 @default.
• W4287377814 cites W2808434111 @default.
• W4287377814 cites W2883780447 @default.
• W4287377814 cites W2887695188 @default.
• W4287377814 cites W2896512449 @default.
• W4287377814 cites W2902747464 @default.
• W4287377814 cites W2912327653 @default.
• W4287377814 cites W2922112107 @default.
• W4287377814 cites W2925753896 @default.
• W4287377814 cites W2945926091 @default.
• W4287377814 cites W2962785365 @default.
• W4287377814 cites W2963163009 @default.
• W4287377814 cites W2963420948 @default.
• W4287377814 cites W2963446712 @default.
• W4287377814 cites W2963819848 @default.
• W4287377814 cites W2964081807 @default.
• W4287377814 cites W2969717429 @default.
• W4287377814 cites W2970435399 @default.
• W4287377814 cites W2971061988 @default.
• W4287377814 cites W3006528244 @default.
• W4287377814 cites W3015304398 @default.
• W4287377814 cites W3035712445 @default.
• W4287377814 cites W3113933322 @default.
• W4287377814 cites W3124083408 @default.
• W4287377814 cites W3203100337 @default.
• W4287377814 cites W4231972595 @default.
• W4287377814 cites W4247043502 @default.
• W4287377814 cites W639708223 @default.
• W4287377814 doi "https://doi.org/10.1007/s00371-022-02609-9" @default.
• W4287377814 hasPublicationYear "2022" @default.
• W4287377814 type Work @default.
• W4287377814 citedByCount "0" @default.
• W4287377814 crossrefType "journal-article" @default.
• W4287377814 hasAuthorship W4287377814A5005867720 @default.
• W4287377814 hasAuthorship W4287377814A5086801148 @default.
• W4287377814 hasBestOaLocation W42873778141 @default.
• W4287377814 hasConcept C11413529 @default.
• W4287377814 hasConcept C115961682 @default.
• W4287377814 hasConcept C121332964 @default.
• W4287377814 hasConcept C153180895 @default.
• W4287377814 hasConcept C154945302 @default.
• W4287377814 hasConcept C160633673 @default.
• W4287377814 hasConcept C163716315 @default.
• W4287377814 hasConcept C31972630 @default.
• W4287377814 hasConcept C41008148 @default.
• W4287377814 hasConcept C57493831 @default.
• W4287377814 hasConcept C62520636 @default.

• next