JP2011182094A - Image processor and image processing program - Google Patents

Image processor and image processing program Download PDF

Info

Publication number
JP2011182094A
JP2011182094A JP2010042639A JP2010042639A JP2011182094A JP 2011182094 A JP2011182094 A JP 2011182094A JP 2010042639 A JP2010042639 A JP 2010042639A JP 2010042639 A JP2010042639 A JP 2010042639A JP 2011182094 A JP2011182094 A JP 2011182094A
Authority
JP
Japan
Prior art keywords
component
image
enlarged
regularization
downsampling
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP2010042639A
Other languages
Japanese (ja)
Inventor
Yu Sakurai
優 櫻井
Tomiaki Goto
富朗 後藤
Akihiro Yoshikawa
明博 吉川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nagoya Institute of Technology NUC
Original Assignee
Nagoya Institute of Technology NUC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nagoya Institute of Technology NUC filed Critical Nagoya Institute of Technology NUC
Priority to JP2010042639A priority Critical patent/JP2011182094A/en
Publication of JP2011182094A publication Critical patent/JP2011182094A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Processing (AREA)
  • Editing Of Facsimile Originals (AREA)

Abstract

<P>PROBLEM TO BE SOLVED: To reduce the entire computing time in an image processor for magnifying an image by using a TV regularization method. <P>SOLUTION: The image processor includes: a TV regularization magnifier 5 for acquiring a magnified frame component from an input image; a downsampling part 7 for downsampling the magnified frame component acquired by the TV regularization magnifier to acquire a frame component to be an image of a sample number equal to that of the input image; a subtracting part 6 for subtracting the frame component acquired by the downsampling part 7 from the input image to obtain a texture component; a linear interpolation magnifier 8 for acquiring a magnified texture component from the texture component acquired by the subtracting part 6 by using linear interpolation; and a component combining part 9 for combining the magnified frame component acquired by the TV regularization magnifier 5 and the magnified texture component acquired by the linear interpolation magnifier 8 to acquire a magnified output image. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

本発明は、テレビジョン、デジタルカメラ、医療画像などの画像を処理する画像処理装置および画像処理プログラムに関し、特にTotal variation（以下、ＴＶと記す）正則化手法を用いて画像を拡大する装置に関する。   The present invention relates to an image processing apparatus and an image processing program for processing an image such as a television, a digital camera, and a medical image, and more particularly to an apparatus for enlarging an image using a total variation (hereinafter referred to as TV) regularization technique.

非特許文献１〜３にはＴＶ正則化手法を用いた画像拡大法が示されており、その方法はテレビジョンやカメラ画像などの超解像度拡大法として非常に有用である。   Non-Patent Documents 1 to 3 show an image enlargement method using a TV regularization method, and this method is very useful as a super-resolution enlargement method for television, camera images, and the like.

図４に、非特許文献１〜３に示された、ＴＶ正則化手法を用いて画像拡大を行う画像処理装置の構成を示す。入力画像はＴＶ正則化成分分離部１にて画像の骨格成分とテクスチャ成分に分離される。骨格成分はＴＶ正則化拡大部２にて拡大骨格成分となる。テクスチャ成分は線形補間拡大部３にて拡大テクスチャ成分となる。拡大骨格成分と拡大テクスチャ成分は成分合成部４にて合成され、最終拡大画像が得られる。   FIG. 4 illustrates a configuration of an image processing apparatus that performs image enlargement using the TV regularization method disclosed in Non-Patent Documents 1 to 3. The input image is separated into a skeleton component and a texture component of the image by the TV regularization component separation unit 1. The skeleton component becomes an enlarged skeleton component in the TV regularization enlargement unit 2. The texture component becomes an enlarged texture component in the linear interpolation enlargement unit 3. The enlarged skeleton component and the enlarged texture component are synthesized by the component synthesis unit 4 to obtain a final enlarged image.

図５に、ＴＶ正則化成分分離部１の処理をフローチャートで示す。ステップ１０１で演算回数Ｎが０に初期設定された後、ステップ１０２でＴＶ正則化演算のための修正項αが図中の式のように計算される。ステップ１０３で画素値ｕ(N)が−εαによって新しい画素値ｕ(N+1)に更新される。そして、ステップ１０４で演算回数Ｎがインクリメントされ、ステップ１０５で予め定められた値ＮstopにＮが達したか否かが判定される。Ｎが値Ｎstopに達していない場合はステップ１０２に戻る。Ｎが値Ｎstopに達した場合は画素値ｕが最終骨格成分として出力され、またステップ１０６で入力画像ｆからｕが引き算されて、テクスチャ成分ｖが出力される。 FIG. 5 is a flowchart showing the process of the TV regularization component separation unit 1. After the number of calculations N is initially set to 0 in step 101, a correction term α for TV regularization calculation is calculated in step 102 as in the equation in the figure. In step 103, the pixel value u (N) is updated to a new pixel value u (N + 1) by -εα. In step 104, the number of operations N is incremented, and in step 105, it is determined whether or not N has reached a predetermined value Nstop. If N has not reached the value Nstop, the process returns to step 102. When N reaches the value Nstop, the pixel value u is output as the final skeleton component, and u is subtracted from the input image f at step 106 to output the texture component v.

齊藤隆弘: "1 枚の画像からの超解像度オーバーサンプリング"，映像メディア学会誌, Vol.62, No.2, pp.181-189, 2008Takahiro Saito: "Super-resolution oversampling from a single image", Journal of the Institute of Image Media Sciences, Vol.62, No.2, pp.181-189, 2008 石井勇樹，中川陽介，小松隆，斎藤隆弘: "乗算型骨格テクスチャ画像分離の画像処理への応用", 電子情報通信学会論文誌，Vol.J90-D, No.7, pp. 1682-1685, 2007Yuki Ishii, Yosuke Nakagawa, Takashi Komatsu, Takahiro Saito: "Application of Multiplicative Skeletal Texture Image Separation to Image Processing", IEICE Transactions, Vol.J90-D, No.7, pp. 1682-1685, 2007 T. Saito and T. Komatsu : "Image Processing Approach Based on Nonlinear Image-Decomposition"，IEICE Trans. Fundamentals, Vol.E92-A, NO.3, pp.696-707, March 2009T. Saito and T. Komatsu: "Image Processing Approach Based on Nonlinear Image-Decomposition", IEICE Trans. Fundamentals, Vol.E92-A, NO.3, pp.696-707, March 2009

非特許文献１〜３に示されたＴＶ正則化手法を用いた画像拡大法は、繰り返し演算にて膨大な計算時間のかかる、ＴＶ正則化演算処理部を２個有している。すなわち、ＴＶ正則化手法によって骨格成分とテクスチャ成分を分離するＴＶ正則化成分分離部１と、ＴＶ正則化手法によるＴＶ正則化拡大部２の２つである。したがって、この手法をテレビジョンのような動画像に用いる際には、その計算時間が問題となる。   The image enlarging method using the TV regularization method disclosed in Non-Patent Documents 1 to 3 has two TV regularization calculation processing units that require enormous calculation time by repeated calculation. That is, there are two parts: a TV regularization component separation unit 1 that separates a skeleton component and a texture component by a TV regularization method, and a TV regularization expansion unit 2 by a TV regularization method. Therefore, when this method is used for a moving image such as a television, the calculation time becomes a problem.

本発明は上記点に鑑みて、ＴＶ正則化手法を用いて画像拡大を行う画像処理装置において、全体の計算時間を削減することを目的とする。   In view of the above points, an object of the present invention is to reduce the overall calculation time in an image processing apparatus that performs image enlargement using a TV regularization method.

上記目的を達成するため、請求項１に記載の発明は、
入力画像から拡大骨格成分を得るＴＶ正則化拡大手段と、
前記拡大骨格成分をダウンサンプリングして、前記入力画像と同じサンプル数の画像となる骨格成分を得るダウンサンプリング手段と、
前記ダウンサンプリング手段にて得られた骨格成分を前記入力画像から減算してテクスチャ成分を得る減算手段と、
前記減算手段にて得られたテクスチャ成分から拡大テクスチャ成分を得る手段と、
この手段にて得られた拡大テクスチャ成分と前記ＴＶ正則化拡大手段にて得られた拡大骨格成分とを合成する成分合成手段と、を備えた画像処理装置ことを特徴とする。 In order to achieve the above object, the invention described in claim 1
TV regularization enlargement means for obtaining an enlarged skeleton component from an input image;
Downsampling means for downsampling the enlarged skeleton component to obtain a skeleton component that is an image having the same number of samples as the input image;
Subtracting means for subtracting the skeleton component obtained by the downsampling means from the input image to obtain a texture component;
Means for obtaining an enlarged texture component from the texture component obtained by the subtracting means;
An image processing apparatus comprising: a component synthesizing unit that synthesizes the enlarged texture component obtained by this means and the enlarged skeleton component obtained by the TV regularization enlarging unit.

請求項２に記載の発明は、
コンピュータを、
入力画像から拡大骨格成分を得るＴＶ正則化拡大手段と、
前記拡大骨格成分をダウンサンプリングして、前記入力画像と同じサンプル数の画像となる骨格成分を得るダウンサンプリング手段と、
前記ダウンサンプリング手段にて得られた骨格成分を前記入力画像から減算してテクスチャ成分を得る減算手段と、
前記減算手段にて得られたテクスチャ成分から拡大テクスチャ成分を得る手段と、
この手段にて得られた拡大テクスチャ成分と前記ＴＶ正則化拡大手段にて得られた拡大骨格成分とを合成する成分合成手段として機能させる画像処理プログラムを特徴とする。 The invention described in claim 2
Computer
TV regularization enlargement means for obtaining an enlarged skeleton component from an input image;
Downsampling means for downsampling the enlarged skeleton component to obtain a skeleton component that is an image having the same number of samples as the input image;
Subtracting means for subtracting the skeleton component obtained by the downsampling means from the input image to obtain a texture component;
Means for obtaining an enlarged texture component from the texture component obtained by the subtracting means;
An image processing program that functions as a component synthesizing unit that synthesizes the enlarged texture component obtained by this means and the enlarged skeleton component obtained by the TV regularization enlarging unit.

本発明の一実施形態に係る画像処理装置の構成を示す図である。It is a figure which shows the structure of the image processing apparatus which concerns on one Embodiment of this invention. ダウンサンプリングを説明するための図である。It is a figure for demonstrating downsampling. 図１中のＴＶ正則化拡大部５の処理を示すフローチャートである。It is a flowchart which shows the process of the TV regularization expansion part 5 in FIG. 従来例の画像処理装置の全体構成を示す図である。It is a figure which shows the whole structure of the image processing apparatus of a prior art example. 図４中のＴＶ正則化成分分離部１の処理を示すフローチャートである。It is a flowchart which shows the process of the TV regularization component separation part 1 in FIG.

以下、本発明を図に示す実施形態について説明する。図１に、本発明の一実施形態に係る画像処理装置の構成を示す。
この画像処理装置は、入力画像から拡大骨格成分を得るＴＶ正則化拡大部５と、このＴＶ正則化拡大部５で得られた拡大骨格成分をダウンサンプリングして、入力画像と同じサンプル数の画像となる骨格成分を得るダウンサンプリング部７と、ダウンサンプリング部７にて得られた骨格成分を入力画像から減算してテクスチャ成分を得る減算部６と、減算部６にて得られたテクスチャ成分から線形補間を用いて拡大テクスチャ成分を得る線形補間拡大部８と、ＴＶ正則化拡大部５にて得られた拡大骨格成分と線形補間拡大部８にて得られた拡大テクスチャ成分とを合成し拡大出力画像を得る成分合成部９と、を備えている。なお、線形補間拡大部８と成分合成部９は、図４に示す従来のものと同じである。 DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments shown in the drawings will be described below. FIG. 1 shows a configuration of an image processing apparatus according to an embodiment of the present invention.
This image processing apparatus includes a TV regularization enlargement unit 5 that obtains an enlarged skeleton component from an input image, and an image having the same number of samples as the input image by downsampling the enlarged skeleton component obtained by the TV regularization enlargement unit From the downsampling unit 7 for obtaining the skeleton component, the subtraction unit 6 for subtracting the skeleton component obtained by the downsampling unit 7 from the input image, and obtaining the texture component, and the texture component obtained by the subtraction unit 6 The linear interpolation enlargement unit 8 that obtains an enlarged texture component using linear interpolation, the enlarged skeleton component obtained by the TV regularization enlargement unit 5 and the enlarged texture component obtained by the linear interpolation enlargement unit 8 are combined and enlarged. And a component synthesis unit 9 for obtaining an output image. The linear interpolation enlargement unit 8 and the component synthesis unit 9 are the same as the conventional one shown in FIG.

この画像処理装置は、次のように作動する。入力画像はＴＶ正則化拡大部５で拡大骨格成分となる。拡大骨格成分はダウンサンプリング部７で図２に示すように画素数が間引きされてもとの入力画像と同じサンプル数の画像となる。例えば、図の左側に示す６×６の拡大画像について、ダウンサンプリングを行うことにより、図中の黒丸を削除して、３×３の半分のサイズの画像を作成する。このダウンサンプリングにより得られた骨格成分は入力画像から減算されてテクスチャ成分となる。テクスチャ成分は線形補間拡大部８にて拡大テクスチャ成分となる。拡大骨格成分と拡大テクスチャ成分は成分合成部９にて合成されて最終拡大画像となる。   This image processing apparatus operates as follows. The input image becomes an enlarged skeleton component in the TV regularization enlargement unit 5. The enlarged skeleton component becomes an image having the same number of samples as the input image even when the number of pixels is thinned out by the downsampling unit 7 as shown in FIG. For example, by performing downsampling on the 6 × 6 enlarged image shown on the left side of the figure, the black circle in the figure is deleted and an image having a half size of 3 × 3 is created. The skeleton component obtained by this downsampling is subtracted from the input image to become a texture component. The texture component becomes an enlarged texture component in the linear interpolation enlargement unit 8. The enlarged skeleton component and the enlarged texture component are synthesized by the component synthesis unit 9 to become a final enlarged image.

図３に、ＴＶ正則化拡大部５での処理を示す。このＴＶ正則化拡大部５では、拡大演算を行うため、例えば、ｉ，ｊそれぞれを２倍にして、ｕの画素数を入力画像の画素数の４倍とするような演算を行う。なお、このような拡大演算は、従来（例えば、図４に示すＴＶ正則化拡大部２）と同様のものである。具体的には、その拡大演算は次の通りである。   FIG. 3 shows processing in the TV regularization enlargement unit 5. In the TV regularization enlargement unit 5, in order to perform the enlargement calculation, for example, the calculation is performed such that each of i and j is doubled and the number of pixels of u is four times the number of pixels of the input image. Note that such enlargement calculation is the same as that in the past (for example, the TV regularization enlargement unit 2 shown in FIG. 4). Specifically, the enlargement calculation is as follows.

まず、ステップ２０１で演算回数Ｎが０に初期設定された後、ステップ２０２でＴＶ正則化演算のための修正項αが図中の式のように計算される。ただしここでは、拡大演算をしているので、ｕの画素数は入力画像の画素数をｎ×ｎ倍（例えば、２×２＝４倍）したものとなっている。このため、ステップ２０２では、右辺第２項のｕ＊（Ｎ）を例えば図２のようにダウンサンプルしたものとし、入力画像ｆと画素数が同じになるようにしている。ステップ２０３で画素値ｕ(N)が−εαによって新しい画素値ｕ(N+1)に更新される。そして、ステップ２０４で演算回数Ｎがインクリメントされ、ステップ２０５で予め定められた値ＮstopにＮが達したか否かが判定される。Ｎが値Ｎstopに達していない場合はステップ２０２に戻る。Ｎが値Ｎstopに達した場合は画素値ｕが最終骨格成分として出力される。 First, after the number of computations N is initially set to 0 in step 201, a correction term α for TV regularization computation is calculated in step 202 as shown in the equation in the figure. However, since the enlargement calculation is performed here, the number of pixels of u is the number of pixels of the input image multiplied by n × n (for example, 2 × 2 = 4 times). For this reason, in step 202, u * (N) of the second term on the right side is down-sampled as shown in FIG. 2, for example, so that the number of pixels is the same as that of the input image f. In step 203, the pixel value u (N) is updated to a new pixel value u (N + 1) by -εα. In step 204, the number of operations N is incremented, and in step 205, it is determined whether or not N has reached a predetermined value Nstop. If N has not reached the value Nstop, the process returns to step 202. When N reaches the value Nstop, the pixel value u is output as the final skeleton component.

この実施形態によれば、図４に示す従来の画像処理装置と比べ、計算時間のかかる、ＴＶ正則化成分分離部１が削除されているので、計算量を大幅に減らし、全体の計算時間を削減（例えば、半減）することができる。   According to this embodiment, since the TV regularization component separation unit 1 which requires a calculation time is deleted compared with the conventional image processing apparatus shown in FIG. 4, the calculation amount is greatly reduced, and the entire calculation time is reduced. It can be reduced (for example, halved).

なお、図１に示す画像処理装置は、コンピュータを用いたソフトウェアにより実現することができる。その場合、図１に示す各構成部は、それぞれの機能を実現するための手段として把握され、それらにより画像処理プログラムが構成される。つまり、入力画像から拡大骨格成分を得るＴＶ正則化拡大手段と、拡大骨格成分をダウンサンプリングして、入力画像と同じサンプル数の画像となる骨格成分を得るダウンサンプリング手段と、ダウンサンプリング手段にて得られた骨格成分を入力画像から減算してテクスチャ成分を得る減算手段と、減算手段にて得られたテクスチャ成分から線形補間を用いて拡大テクスチャ成分を得る線形補間拡大手段と、ＴＶ正則化拡大手段にて得られた拡大骨格成分と線形補間拡大手段にて得られた拡大テクスチャ成分とを合成する成分合成手段として、コンピュータを機能させる画像処理プログラムとして構成される。   The image processing apparatus shown in FIG. 1 can be realized by software using a computer. In that case, each component shown in FIG. 1 is grasped as a means for realizing each function, and an image processing program is constituted by them. That is, a TV regularization enlargement unit that obtains an enlarged skeleton component from an input image, a downsampling unit that downsamples the enlarged skeleton component to obtain an image of the same number of samples as the input image, and a downsampling unit Subtraction means for subtracting the obtained skeleton component from the input image to obtain a texture component, linear interpolation enlargement means for obtaining an enlarged texture component from the texture component obtained by the subtraction means using linear interpolation, and TV regularization enlargement An image processing program for causing a computer to function as component synthesizing means for synthesizing the enlarged skeleton component obtained by the means and the enlarged texture component obtained by the linear interpolation enlarging means.

また、本発明は上記した実施形態に限定されるものではない。例えば、減算部にて得られたテクスチャ成分から拡大テクスチャ成分を得る手段としては、拡大骨格成分と同様の拡大を行った拡大テクスチャ成分を得るものであれば、線形補間拡大部８以外のものを用いてもよい。   Further, the present invention is not limited to the above-described embodiment. For example, as a means for obtaining the enlarged texture component from the texture component obtained by the subtracting unit, any means other than the linear interpolation enlarging unit 8 can be used as long as it obtains an enlarged texture component that has been enlarged in the same manner as the enlarged skeleton component. It may be used.

５ ＴＶ正則化拡大部
６ 減算部
７ ダウンサンプリング部
８ 線形補間拡大部
９ 成分合成部 5 TV regularization expansion unit 6 Subtraction unit 7 Downsampling unit 8 Linear interpolation expansion unit 9 Component synthesis unit

Claims (2)

入力画像から拡大骨格成分を得るＴＶ正則化拡大手段と、
前記拡大骨格成分をダウンサンプリングして、前記入力画像と同じサンプル数の画像となる骨格成分を得るダウンサンプリング手段と、
前記ダウンサンプリング手段にて得られた骨格成分を前記入力画像から減算してテクスチャ成分を得る減算手段と、
前記減算手段にて得られたテクスチャ成分から拡大テクスチャ成分を得る手段と、
この手段にて得られた拡大テクスチャ成分と前記ＴＶ正則化拡大手段にて得られた拡大骨格成分とを合成する成分合成手段と、を備えたことを特徴とする画像処理装置。 TV regularization enlargement means for obtaining an enlarged skeleton component from an input image;
Downsampling means for downsampling the enlarged skeleton component to obtain a skeleton component that is an image having the same number of samples as the input image;
Subtracting means for subtracting the skeleton component obtained by the downsampling means from the input image to obtain a texture component;
Means for obtaining an enlarged texture component from the texture component obtained by the subtracting means;
An image processing apparatus comprising: a component synthesizing unit that synthesizes the enlarged texture component obtained by this means and the enlarged skeleton component obtained by the TV regularization enlarging unit. コンピュータを、
入力画像から拡大骨格成分を得るＴＶ正則化拡大手段と、
前記拡大骨格成分をダウンサンプリングして、前記入力画像と同じサンプル数の画像となる骨格成分を得るダウンサンプリング手段と、
前記ダウンサンプリング手段にて得られた骨格成分を前記入力画像から減算してテクスチャ成分を得る減算手段と、
前記減算手段にて得られたテクスチャ成分から拡大テクスチャ成分を得る手段と、
この手段にて得られた拡大テクスチャ成分と前記ＴＶ正則化拡大手段にて得られた拡大骨格成分とを合成する成分合成手段として機能させることを特徴とする画像処理プログラム。 Computer
TV regularization enlargement means for obtaining an enlarged skeleton component from an input image;
Downsampling means for downsampling the enlarged skeleton component to obtain a skeleton component that is an image having the same number of samples as the input image;
Subtracting means for subtracting the skeleton component obtained by the downsampling means from the input image to obtain a texture component;
Means for obtaining an enlarged texture component from the texture component obtained by the subtracting means;
An image processing program that functions as a component synthesis unit that synthesizes an enlarged texture component obtained by this means and an enlarged skeleton component obtained by the TV regularization enlargement unit.
JP2010042639A 2010-02-26 2010-02-26 Image processor and image processing program Pending JP2011182094A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2010042639A JP2011182094A (en) 2010-02-26 2010-02-26 Image processor and image processing program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2010042639A JP2011182094A (en) 2010-02-26 2010-02-26 Image processor and image processing program

Publications (1)

Publication Number Publication Date
JP2011182094A true JP2011182094A (en) 2011-09-15

Family

ID=44693162

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2010042639A Pending JP2011182094A (en) 2010-02-26 2010-02-26 Image processor and image processing program

Country Status (1)

Country Link
JP (1) JP2011182094A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102378014A (en) * 2011-09-28 2012-03-14 福建华映显示科技有限公司 Device and method for improving image resolution of display panel
US8515197B2 (en) 2011-09-05 2013-08-20 Chunghwa Picture Tubes, Ltd. Image resolution enhancing device and method for display panel
CN104853059A (en) * 2014-02-17 2015-08-19 台达电子工业股份有限公司 Super-resolution image processing method and device

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8515197B2 (en) 2011-09-05 2013-08-20 Chunghwa Picture Tubes, Ltd. Image resolution enhancing device and method for display panel
CN102378014A (en) * 2011-09-28 2012-03-14 福建华映显示科技有限公司 Device and method for improving image resolution of display panel
CN104853059A (en) * 2014-02-17 2015-08-19 台达电子工业股份有限公司 Super-resolution image processing method and device
CN104853059B (en) * 2014-02-17 2018-12-18 台达电子工业股份有限公司 Super-resolution image processing method and its device

Similar Documents

Publication Publication Date Title
JP5385969B2 (en) Method and apparatus for super-resolution of images
US9609181B2 (en) Image signal processor and method for synthesizing super-resolution images from non-linear distorted images
JP4018601B2 (en) Digital image scaling method for embedded system
WO2011111819A1 (en) Image processing device, image processing program, and method for generating images
JP4915317B2 (en) Image processing apparatus, image processing method, and computer program
JP2011180798A (en) Image processing apparatus, image processing method, and program
JP2011237998A (en) Image processing device, and image processing method and program
JP2008091979A (en) Image quality improving device, method thereof, and image display device
Yoshikawa et al. Super resolution image reconstruction using total variation regularization and learning-based method
Jeong et al. Multi-frame example-based super-resolution using locally directional self-similarity
Qin et al. Video superresolution reconstruction based on subpixel registration and iterative back projection
KR20140081481A (en) Block based image Registration for Super Resolution Image Reconstruction Method and Apparatus
JP2011182094A (en) Image processor and image processing program
WO2007071882A2 (en) Method for providing data to a digital processing means
Liu et al. Directional fractional-order total variation hybrid regularization for image deblurring
JP2008293388A (en) Image processing method, image processor, and electronic equipment comprising image processor
Yau et al. Robust deep learning-based multi-image super-resolution using inpainting
JP5181345B2 (en) Image processing apparatus and image processing method
Joshi et al. Simultaneous estimation of super-resolved depth map and intensity field using photometric cue
JP2013152583A (en) Image processing apparatus
Su et al. Adaptive incremental video super-resolution with temporal consistency
JP5327176B2 (en) Image processing method and image processing apparatus
Sriram et al. A FPGA implementation of variable kernel convolution
Watanabe et al. Super-resolution image processing with total variation regularization and shock filters
Yousef et al. Mathematical model development of super-resolution image Wiener restoration