JP3918141B2 - Image processing apparatus and image processing method - Google Patents

Description

【００５１】
のようなフィルタ行列を用いることができる。なお、シャープさを維持したまま雑音低減効果があり、わずかなぼかし処理として局所領域での中間値（メディアン）を出力するメディアンフィルタを利用するようにしてもよい。
【００５２】
ぼかしの強さについては、フィルタ行列要素の値を変えることで調節でき、数段階のぼかし強度に応じたフィルタ行列を設定しておけば、ユーザ指定に対応してぼかし強度を変えることができる。例えば、ぼけマスク領域内は、一様なボケ強度にしたり、主要部領域中心からの画面内距離に応じて変化する（距離が遠くなるほどぼかし強度が強くなる）ようにしてもよい。
【００５３】
なお、ぼかし処理のぼかし強度については、一定のぼかし強度であってもよいし、数段階のぼかし強度が設定可能にしてもよい。数段階のぼかし強度が設定可能とした場合、数段階のぼかし強度に応じたフィルタ行列を設定しておき、数段階のぼかし強度のうち、オペレータが選択して操作部５５にぼかし強度変更を表す情報を入力することによって、ぼかし強度を変更することが可能である。例えば、ぼかし強度選択スイッチ等を操作部５５に設けることでぼかし強度の変更が可能である。
【００５４】
次に本実施の形態における作用をぼかし処理のソフトウェアについて説明する。
【００５５】
オペレータが操作部５５を操作し、ぼかし処理を実行する情報を入力することによりぼかし処理が行われる。
【００５６】
次に、ＲＡＭ５２に一旦記憶された画像データをメインコントローラ４２に取り込み、取り込んだ画像データに対して自動的にぼかし処理を行う。なお、ぼかし処理が図４に示すフローチャートに従って行われる。以下、ぼかし処理について図４のフローチャート及び図５を参照して説明する。
【００５７】
図５（Ａ）には、ぼかし処理を行う前のバラの花を主要部領域の被写体としたオリジナル画像が示されている。操作部５５にぼかし処理を行う情報が入力されると、ステップ１００で領域分割手段７４により、図５（Ａ）に示すオリジナル画像の領域分割処理が行われ、図５（Ｂ）に示すような領域分割画像が作成される。
【００５８】
ステップ１０２では、連結拡張手段７６により図５（Ｂ）に示す画像の４隅の領域に隣接する領域が上述した何れかの条件を満たす場合に背景領域とし、背景領域を順次拡張連結することにより背景領域が推定される。そして、分離手段７８によって、連結拡張手段７６が背景領域として吸収せずに残った領域を主要部領域とし、画像を背景領域と主要部領域に２分して、主要部領域が抽出される（図５（Ｃ））。
【００５９】
ステップ１０４では、輪郭抽出手段８４により、図５（Ａ）のオリジナル画像に対する輪郭抽出が行われ、図５（Ｄ）に示す輪郭抽出画像が生成される。
【００６０】
続くステップ１０６では、分離手段７８により抽出された主要部領域と輪郭抽出手段８４により得られる輪郭抽出画像を重ねて、主要部領域の輪郭に一番近い輪郭線を輪郭抽出画像より選択することにより、主要部領域の輪郭が整えられる。そして、輪郭の整えられた主要部領域をマスクとしてぼけマスクが生成される（図５（Ｅ））。
【００６１】
ステップ１０８では、生成されたぼけマスクを用いてぼかし処理手段８２によりぼかし処理が行われ、図５（Ｆ）に示すような背景領域のみがぼけた画像を得ることができる。すなわち、ぼかし処理によりデジタルスチルカメラで撮影したパンフォーカス的に画面全体にピントが合ったような画像から、３５ｍｍ一眼レフカメラで絞り優先で被写体深度を浅くして撮影したような、主要部のみがくっきりして背景はぼかしたプリントを作成することができる。
【００６２】
このように、オペレータが主要部領域と背景領域との境界線を指定する煩雑な作業を行うことなく、オペレータが操作部５５にぼかし処理を行うか否か表す情報を入力するだけで、自動的にぼかし処理を行うことができる。
【００６３】
続いて、上述のぼかし処理に対するその他の構成について図６を参照して説明する。
【００６４】
図６に示すように、上述のぼかし処理と同様に、領域分割手段７４、連結拡張手段７６、輪郭強調手段８６、分離手段７８、マスク生成手段８０及びぼかし処理手段８２によって構成されている。
【００６５】
上述のぼかし処理では、マスク生成手段によりぼかしマスクを生成する際にマスクの輪郭を整えるために輪郭抽出手段８４を設けたのに対して、領域分割する際の領域分割線を整えるため輪郭強調手段８６が設けられている。すなわち、原画像の輪郭強調を行い、輪郭強調された画像に対して領域分割を行う構成となっている。このようにすることにより、境界線が明確になり、領域分割した後の背景領域と主要部領域との境界線の精度を向上することができる。
【００６６】
次にこのように構成されたぼかし処理について、図６、図７のフローチャート及び図８を参照して説明する。
【００６７】
図８（Ａ）には、ぼかし処理を行う前の人物を主要部領域の被写体としたオリジナル画像が示されている。本フローチャートでは、操作部５５にぼかし処理を行う指令が入力されると、ステップ２００で輪郭強調手段８６により図８（Ａ）に示すオリジナル画像に対する輪郭強調が行われ、図８（Ｂ）に示す輪郭強調画像が生成される。
【００６８】
ステップ２０２では、輪郭強調手段８６により輪郭強調された輪郭線に基づいて、領域分割手段７４により行われる領域分割処理が行われ、図８（Ｃ）に示す領域分割画像が作成される。このように輪郭強調が行われた画像に対して領域分割処理が行われることにより、領域分割した後の背景領域と主要被写体領域との境界線の精度を向上することができる。
【００６９】
ステップ２０４では、領域分割画像（図８（Ｃ））に基づいて、原画像の中心を重心として、画像より小さい楕円外にある領域を背景領域とし、背景領域を順次連結拡張することにより背景領域が推定される。そして、背景領域として吸収されずに残った領域を主要部領域とし、領域分割画像を背景領域と主要部領域に２分することにより、主要部領域が抽出される（図８（Ｄ））。
【００７０】
ステップ２０６では、抽出された主要部領域をマスクとしてぼけマスクが生成される（図８（Ｅ））。
【００７１】
ステップ２０８では、生成されたぼけマスクを用いてぼかし処理が行われ、図８（Ｆ）に示すような背景領域のみがぼけた画像を得ることができる。
【００７２】
なお、上記では、背景領域を連結拡張して画像データから背景領域を分離することによって主要領域にマスクを生成するようにしたが、背景領域以外の主要部領域を連結拡張して主要部領域を生成し、生成された主要部領域からマスクを生成するようにしてもよい。
【００７３】
また、上記では、輝度信号Ｙと色差信号Ｃｂ、Ｃｒからなる信号を用いてぼかし処理を行う構成としたが、ＲＧＢ色信号を用いてぼかし処理を行う構成としてもよい。
【００７４】
更に、本実施の形態では、本発明をプリンタ１０を例に説明したが、プリンタ１０に限るものではなく、例えば、デジタルスチルカメラに本発明を適用してもよいし、写真感光材料などを処理してプリントを行うデジタルラボシステムに本発明を適用するようにしてもよい。
【００７５】
【発明の効果】
以上説明したように本発明によれば、オペレータが主要部と背景との境界線を指定する煩雑な作業を行うことなく、自動的に主要部と背景とを分離し、背景領域だけにぼかし処理を行うことができる画像処理装置及び画像処理方法を提供することができるという効果がある。
【図面の簡単な説明】
【図１】本発明の実施の形態に係るプリンタの概略図である。
【図２】本発明の実施の形態に係るプリンタの制御回路を示すブロック図である。
【図３】特殊画像処理におけるぼかし処理の構成を示すブロック図である。
【図４】ぼかし処理の流れの一例を示すフローチャートである。
【図５】ぼかし処理の一例の処理過程を示す図である。
【図６】ぼかし処理のその他の構成を示すブロック図である。
【図７】ぼかし処理のその他の例を示すフローチャートである。
【図８】ぼかし処理のその他の例の処理過程を示す図である。
【符号の説明】
１０ プリンタ
４２ メインコントローラ
７４ 領域分割手段
７６ 連結拡張手段
７８ 分離手段
８０ マスク生成手段
８２ ぼかし処理手段
８４ 輪郭抽出手段
８６ 輪郭強調手段[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing apparatus and an image processing method, and more particularly to an image processing apparatus and an image processing method in a digital photo print system or the like that performs image processing on an image photographed by a digital still camera or the like. .
[0002]
[Prior art]
In general, the size of the light receiving surface of a CCD sensor, which is an image sensor of a digital still camera, is smaller than, for example, a 35 mm film for silver halide photography, and the lens focal length of a digital still camera is shorter than that of a 35 mm camera. Therefore, even when shooting with the same angle of view and the same aperture, the digital still camera has a greater depth of field than the 35 mm camera. In general, the aperture of a digital still camera has a narrow variable range, and the open F number is often darker than a 35 mm camera lens. Therefore, it is often impossible to reduce the depth of field by opening the aperture. As a result, especially scenes shot with a digital still camera tend to be pan-focused and the entire image is in focus.
[0003]
However, of course, depending on the scene, there may be a case where it is desired to make only the main subject stand out and blur the background around it. Therefore, even for images taken with a camera that cannot reduce the depth of field by adjusting the lens focal length and aperture of the camera, it is necessary to create a print that easily achieves such effects through image processing. It becomes.
[0004]
Therefore, Japanese Patent Laid-Open No. 10-65923 describes the following technique. First, the operator designates a temporary boundary between the main part and the background, performs an expansion / contraction process on the image data based on the specified temporary boundary, and includes an area including the main part, an area including only the background, and a main It is divided into three regions consisting of regions including the exact boundary between the part and the background. Then, for each pixel included in the area including the exact boundary between the main part and the background, whether the pixel belongs to the area including only the main part or the area including only the background, for example, color continuity Etc., and an accurate boundary line between the main part and the background is detected. Then, sharpness processing is applied to the digital image data in the main area and the area including the accurate boundary line between the main area and the background, and the edge of the accurate boundary line between the main area and the background is emphasized without a sense of incongruity. The In addition, a boundary line obtained by slightly expanding the exact boundary line between the main part and the background is calculated, and based on the expanded boundary line, the digital image data of the background region is subjected to interpolation processing, and the boundary line is calculated. Prevents bleeding from occurring in areas close to Thereafter, the background region is blurred using an IIR filter or the like. As described above, in the technique described in Japanese Patent Laid-Open No. 10-65923, even an image shot by a camera that cannot reduce the depth of field, the main subject can be easily made to stand out easily by image processing. The background can be blurred.
[0005]
[Problems to be solved by the invention]
However, in the technique described in Japanese Patent Laid-Open No. 10-65923, the operator needs to specify a temporary boundary between the main part and the background. The operation of specifying the temporary boundary is performed using a mouse or the like. There was a problem that it was a cumbersome work to specify.
[0006]
The present invention was made to solve the above problem, and the main part and the background are automatically separated without the operator having to perform a complicated operation of designating the boundary line between the main part and the background. An object of the present invention is to provide an image processing apparatus and an image processing method capable of performing a blurring process only on a region.
[0007]
[Means for Solving the Problems]
In order to achieve the above object, the present invention divides an image so that adjacent pixels whose pixel data difference is less than or equal to a threshold value are included in the same region, and average coordinates of the pixels in the divided region calculation means for de San positions for each of the regions, the average coordinate position, a region estimating means an area located in the region of the small circle or ellipse outside from the image relative to the center of the image shall be the background area, It is characterized in that from the whole image and a blurring processing means for performing mini blurring of the estimated background region by the region estimating means.
[0008]
According to the first aspect of the present invention, an image is generated so that adjacent pixels whose data between pixels (for example, color information, luminance information, and color difference information) are equal to or less than a threshold value are included in the same region by the calculation unit. It is divided into regions. Then, the average coordinates of the pixels in the region divided areas are de San for each of the regions.
In the case of a normal image, the main subject is located approximately at the center of the image. Therefore, the background region can be estimated by setting a region where the average coordinate position is located in a region outside the circle or ellipse smaller than the image relative to the center of the image as the background region.
[0009]
Further, based on the background area estimated by the area estimation means, the blurring processing unit, blurring processing is performed only on the estimated background area. That is, it is possible to automatically perform the blurring process only on the background area without designating the boundary line between the main part area and the background area.
[0010]
The invention according to claim 2, in the invention described in claim 1, wherein the blurring processing means, separating means for separating the whole image into realm excluding background and background regions, separated by the separation unit a mask generating means for generating a mask realm excluding the background area, and the features and processing means for performing blurring processing, that consists of the region other than the region of the mask generated by the mask generating means.
[0011]
According to the invention described in claim 2, in the invention described in claim 1, and the blurring processing unit separation means, the mask generating means, made from the processing unit, the background area estimated by the area estimation means separation by means, it is 2 minutes realm excluding background area and the background area. Then, the mask is generated by the mask generating means realm except the separated background area, based on the created mask, it is possible to perform the blurring process in a region other than the mask by the processing means.
[0018]
The invention according to claim 3, in the invention described in claim 2, wherein the mask generation unit extracts a contour of the image, by superimposing the extracted contour to the contour of the realm excluding the background area, It is characterized in that the contour of the mask is adjusted.
[0019]
According to a third aspect of the present invention, in the second aspect of the present invention, when a mask is generated in the main region for performing blurring processing by the mask generation means, a contour image is extracted. And the main part region separated by the separating means can be overlaid, the contour of the main part to be masked can be adjusted, and the main part mask can be surely performed when performing the blurring process on the background area. .
[0020]
According to a fourth aspect of the present invention, in the first or second aspect of the present invention, the calculation unit emphasizes a contour in the image and performs the region division based on the emphasized contour. It is characterized by.
[0021]
According to the invention of claim 4, in the invention of claim 1 or claim 2, the contour in the image is emphasized, and the area is divided by the calculation means based on the emphasized contour image. The boundary line of each area becomes clear. Therefore, the boundary line when the separation means separates the background area and the area excluding the background area, or the main area and the area excluding the main area is also clarified, and the accuracy of the boundary line between the background area and the main area is improved. Can be improved.
[0022]
The invention described in claim 5 is characterized in that in the invention described in any one of claims 1 to 4, the image processing apparatus further includes a blurring processing intensity specifying means for specifying the strength of the blurring process.
[0023]
According to the invention described in claim 5, in the invention described in any one of claims 1 to 4, further comprising a blur processing intensity specifying means, the strength of the blur processing performed by the blur processing means. Can be set.
[0024]
The invention described in claim 6 is characterized in that, in the invention described in any one of claims 1 to 5, switching means for switching whether to perform the blurring process is further provided.
[0025]
According to the invention described in claim 6, in the invention described in any one of claims 1 to 5, it is possible to select whether or not to perform the blurring process by further including a switching unit. It becomes.
[0026]
The invention according to claim 7 divides the image so that adjacent pixels whose data difference between the pixels is equal to or less than the threshold value are included in the same region, and calculates an average coordinate position of the pixels in the divided region. out calculated for each of the regions, the average coordinate position, a region located in the region of the small circle or ellipse outside from the image relative to the center of the image and background areas, mini blurring of the estimated background area from the entire image It is characterized by performing processing.
[0027]
According to the seventh aspect of the present invention, an image is divided into regions so that adjacent pixels whose pixel data (for example, color information, luminance information, and color difference information) are equal to or less than a threshold value are included in the same region. Then , the average coordinate position of the pixels in the divided area is calculated for each area .
In the case of a normal image, the main subject is located approximately at the center of the image. Therefore, the background region can be estimated by setting a region where the average coordinate position is located in a region outside the circle or ellipse smaller than the image relative to the center of the image as the background region.
[0028]
Then, based on the estimated background area, it performs the blurring process only the background area. By performing the blurring process in this way, it is possible to automatically perform the blurring process only on the background area without specifying the boundary line between the main part area and the background area.
[0029]
DETAILED DESCRIPTION OF THE INVENTION
In the following, an embodiment in which the present invention is applied to a multicolor thermal printer that records an image on a multicolor thermal sheet will be described in detail with reference to the drawings.
[0030]
As shown in FIG. 1, the printer 10 is a device that thermally records a color image on a substantially rectangular multicolor thermal recording sheet 12 and fixes the recorded image with light to form an image. It is stored in.
[0031]
An insertion port 18 for the multicolor thermal recording sheet 12 to which the mounting table 16 is attached is provided on one side surface of the casing 14, and a multicolor to which the mounting table 20 is mounted on the other side surface of the casing 14. A discharge port 22 for the thermal recording sheet 12 is provided. Between the insertion port 18 and the discharge port 22, a transport device that transports the multicolor thermosensitive recording sheet 12 in the direction of the insertion port 18 or the discharge port 22 is disposed.
[0032]
The transport apparatus includes a pair of transport rollers 24 provided in the vicinity of the insertion port 18 and a pair of transport rollers 32 provided in the vicinity of the discharge port 22. A guide plate 26 is provided on the downstream side of the transport roller 24 in the transport direction, and a guide plate 38 is provided on the upstream side of the transport roller 32 in the transport direction.
[0033]
Between the guide plates 26 and 38, a thermal head 28 and a platen roller 30 as thermal recording means are provided facing each other. A sensor 27 and a light source 34 for detecting the front and back of the multicolor thermal recording sheet 12 are disposed on the side of the thermal roller 28 on the conveying roller 24 side. As the light source 34, an LED can be used, and the multicolor thermosensitive recording sheet 12 to be conveyed is irradiated with light having a wavelength of 300 to 450 nm, preferably 420 nm, and used for detection of the multicolor thermosensitive recording sheet 12. At the same time, it is also used as a fixing light source for fixing each coloring layer.
[0034]
A control circuit 40 shown in FIG. The control circuit 40 includes a main controller 42 that is configured by a microcomputer and to which a signal processing unit 44 is connected. The signal processing unit includes a signal converter 50 having a function of converting image data composed of RGB (red, green, blue) color signals into image data composed of a luminance signal Y and color difference signals Cb and Cr, and a signal. A RAM 52 is provided for temporarily storing the image data output from the converter 50.
[0035]
A digital camera 46 or a computer 48 is selectively connected to the signal processing unit 44, and natural image digital image data composed of a luminance signal Y and color difference signals Cb and Cr is input from the digital camera 46. From 48, a computer graphics (CG) image composed of RGB color signals generated by a computer, a composite image composed of a CG image and a natural image, a composite image composed of a text image and a natural image, and a template image Any digital image data of a composite image in which a natural image and a natural image are combined is input. Note that the text image and the template image can be composed of CG images.
[0036]
When image data composed of RGB color signals is input from the computer 48, the signal processing unit 44 converts the image data into luminance signal Y and color difference signals Cb and Cr. When image data including image data including Cb, Cr, and Y signals input from a digital camera is input, the image data is temporarily stored in the RAM 52 without being converted into Cb, Cr, and Y signals.
[0037]
The main controller 42 is provided with an operation unit 55 for operating the printer 10, and is configured to control the operation of the printer 10 when an operator inputs an operation to the operation unit 55. A thermal head is connected to the output side of the main controller 42 via a switch 58 and a line buffer 60 for selecting any one of Y, M, and C color data based on a signal from the main controller. A driver 62 that drives the rotary drive source 64 for rotating the platen roller 30, and a sensor 27 that receives reflected light of the light emitted from the light source 34. A driver 68 for driving the light source 34 and the fixing light source 36 is connected.
[0038]
The thermal head 28 is provided with a heating element 70 connected to a power source 72 in the vicinity of the platen roller 30.
[0039]
Further, the main controller 42 is configured to be able to perform a blurring process that blurs only the background area on the input image (described later). Note that whether or not to perform the blurring process is given by inputting information indicating whether or not the operator performs the blurring process to the operation unit 55. For example, it is possible to select whether or not to perform the blurring process by providing a blurring process switching switch in the operation unit 55 and switching the switch.
[0040]
Next, the background blur process described above will be described.
[0041]
The blurring process described above is executed by the main controller 42 by software to be described later. When this blurring process is represented by functional blocks, as shown in FIG. 3, area dividing means 74, connection expanding means 76, contour extracting means 84 are provided. , Separating means 78, mask generating means 80, and blurring processing means 82. The region dividing unit 74 and the connection expanding unit 76 correspond to the calculating unit and the region estimating unit of the present invention, respectively.
[0042]
Assuming that image data representing an image is given by the luminance signal Y and the color difference signals Cb and Cr, the area dividing unit 74 performs a raster scan of the two-dimensional data of the luminance signal Y and determines a luminance difference between adjacent pixels. When the hue (Cb, Cr distance (ΔC) or Cb, Cr hue angle difference (ΔH)) is equal to or less than a predetermined threshold when the threshold value (ΔY) is not more than, this condition is integrated. If the condition is not satisfied, the area is divided by setting a new area. Then, such processing is sequentially performed, and region division is performed while labeling each region. Note that R, G, and B may be used instead of the luminance signal Y and the color difference signals Cb and Cr.
[0043]
Furthermore, area dividing means 74, after area division, the average coordinates for each of the regions which are distinguished by the labels (average X, average Y) out calculate the, with areas divided image data, the average coordinates It outputs to the connection expansion means 76.
[0044]
Coupling expansion means 76, in the region segmentation image by the area dividing unit 74, as the centroid of the center of the original image, and the background area of the region of the smaller elliptical outer than the image.
[0045]
Then, the connection expansion unit 76 expands the region satisfying the above condition as a background region, and outputs it to the separation unit.
[0046]
The contour extracting unit 84 extracts a contour line of the original image using the original image and creates a contour extracted image. In contour extraction, contour enhancement can be performed by a general differential filter such as first-order differentiation (gradient) and second-order differentiation (Laplacian). It is possible to create a contour extraction image in which is thinned.
[0047]
The separating unit 78 divides the entire image into a background region and a main part region by making the region remaining without being absorbed in the background region by the connecting and expanding unit 76 as a main part region.
[0048]
The mask generation unit 80 adjusts the outline of the main part region by superimposing the main part region separated by the separation unit 78 and the contour extraction image obtained by the contour extraction unit 84. Then, an image mask that overlaps the main area is generated.
[0049]
The blurring processing unit 82 performs blurring processing on an area other than the above-described mask. As the blurring process, a low-pass filter for noise reduction is suitable. As the simplest smoothing filter, the value of a predetermined pixel is replaced with a calculated value using a filter matrix for the values of surrounding 3 × 3 pixels. Processing can be used. For example,
[0050]
[Expression 1]

[0051]
A filter matrix such as can be used. Note that a median filter that has a noise reduction effect while maintaining sharpness and outputs an intermediate value (median) in a local region may be used as a slight blurring process.
[0052]
The blur strength can be adjusted by changing the value of the filter matrix element. If a filter matrix corresponding to several stages of blur strength is set, the blur strength can be changed according to the user designation. For example, the blur mask area may have a uniform blur intensity or change according to the distance in the screen from the center of the main area (the blur intensity increases as the distance increases).
[0053]
Note that the blur intensity of the blur process may be a constant blur intensity, or may be set at several stages. When several stages of blur intensity can be set, a filter matrix corresponding to several stages of blur intensity is set, and the operator selects and displays the blur intensity change in the operation unit 55 among the several stages of blur intensity. It is possible to change the blur intensity by inputting information. For example, the blur intensity can be changed by providing the operation unit 55 with a blur intensity selection switch or the like.
[0054]
Next, the software for blurring the operation of the present embodiment will be described.
[0055]
The blurring process is performed when the operator operates the operation unit 55 and inputs information for executing the blurring process.
[0056]
Next, the image data once stored in the RAM 52 is taken into the main controller 42, and the fetched image data is automatically blurred. The blurring process is performed according to the flowchart shown in FIG. Hereinafter, the blurring process will be described with reference to the flowchart of FIG. 4 and FIG.
[0057]
FIG. 5A shows an original image in which a rose flower before performing the blurring process is a subject in the main area. When information for performing blurring processing is input to the operation unit 55, the region dividing unit 74 performs region dividing processing of the original image shown in FIG. 5A in step 100, as shown in FIG. 5B. A region-divided image is created.
[0058]
In step 102, when the region adjacent to the four corner regions of the image shown in FIG. 5B satisfies the above-described conditions by the connecting and expanding means 76, the background region is sequentially expanded and connected. A background region is estimated. Then, the separation means 78 extracts the main area by dividing the image into the background area and the main area by dividing the area that the connection expansion means 76 did not absorb as the background area into the main area. FIG. 5C).
[0059]
In step 104, the contour extracting unit 84 performs contour extraction on the original image of FIG. 5A, and generates a contour extracted image shown in FIG.
[0060]
In the following step 106, the main part region extracted by the separating means 78 and the contour extraction image obtained by the contour extraction means 84 are overlapped, and the contour line closest to the outline of the main part region is selected from the contour extraction image. The outline of the main part region is adjusted. Then, a blur mask is generated with the contoured main part region as a mask (FIG. 5E).
[0061]
In step 108, blur processing is performed by the blur processing unit 82 using the generated blur mask, and an image in which only the background region is blurred as shown in FIG. 5F can be obtained. In other words, only the main part, such as a 35mm single-lens reflex camera with a shallow aperture and a shallow subject depth, was taken from an image that was shot with a digital still camera and focused on the entire screen in a pan-focus manner. You can create a print with a sharp and blurred background.
[0062]
As described above, the operator can input the information indicating whether or not to perform the blurring process to the operation unit 55 without performing the complicated work of designating the boundary line between the main region and the background region. Blur processing can be performed.
[0063]
Next, another configuration for the above-described blur processing will be described with reference to FIG.
[0064]
As shown in FIG. 6, similarly to the above-described blurring process, the area dividing unit 74, the connection expanding unit 76, the contour emphasizing unit 86, the separating unit 78, the mask generating unit 80, and the blurring processing unit 82 are configured.
[0065]
In the blurring process described above, the contour extracting unit 84 is provided for adjusting the contour of the mask when the mask generating unit generates the blur mask, whereas the contour emphasizing unit is used for adjusting the region dividing line when the region is divided. 86 is provided. In other words, the contour enhancement of the original image is performed, and the region division is performed on the contour-enhanced image. By doing so, the boundary line becomes clear, and the accuracy of the boundary line between the background region and the main region after the region division can be improved.
[0066]
Next, the blurring process configured as described above will be described with reference to the flowcharts of FIGS. 6 and 7 and FIG.
[0067]
FIG. 8A shows an original image in which the person before performing the blurring process is a subject in the main area. In this flowchart, when a command for performing blurring processing is input to the operation unit 55, the contour emphasizing unit 86 performs contour emphasis on the original image shown in FIG. 8A in step 200, as shown in FIG. 8B. A contour-enhanced image is generated.
[0068]
In step 202, the region dividing process performed by the region dividing unit 74 is performed based on the contour line emphasized by the contour enhancing unit 86, and the region divided image shown in FIG. 8C is created. By performing region division processing on an image that has been subjected to contour enhancement in this way, it is possible to improve the accuracy of the boundary line between the background region and the main subject region after region division.
[0069]
In step 204, based on the region-divided image (FIG. 8 (C)), as the centroid of the center of the original image, a region located outside the smaller than the image ellipse and background areas, background by sequentially connecting extends background area Region is estimated. Then, the main region is extracted by dividing the region-divided image into the background region and the main region by dividing the region remaining without being absorbed as the background region into the main region (FIG. 8D).
[0070]
In step 206, a blur mask is generated using the extracted main region as a mask (FIG. 8E).
[0071]
In step 208, blur processing is performed using the generated blur mask, and an image in which only the background region is blurred as shown in FIG. 8F can be obtained.
[0072]
In the above, the background area is connected and expanded to generate a mask in the main area by separating the background area from the image data, but the main area other than the background area is connected and expanded to The mask may be generated from the generated main part region.
[0073]
In the above description, the blurring process is performed using the signal including the luminance signal Y and the color difference signals Cb and Cr. However, the blurring process may be performed using the RGB color signal.
[0074]
Further, in the present embodiment, the present invention has been described by taking the printer 10 as an example. However, the present invention is not limited to the printer 10. For example, the present invention may be applied to a digital still camera or a photographic photosensitive material may be processed. Thus, the present invention may be applied to a digital laboratory system that performs printing.
[0075]
【The invention's effect】
As described above, according to the present invention, the main part and the background are automatically separated without performing a complicated operation for the operator to specify the boundary line between the main part and the background, and only the background region is blurred. There is an effect that it is possible to provide an image processing apparatus and an image processing method capable of performing the above.
[Brief description of the drawings]
FIG. 1 is a schematic diagram of a printer according to an embodiment of the present invention.
FIG. 2 is a block diagram showing a control circuit of the printer according to the embodiment of the present invention.
FIG. 3 is a block diagram illustrating a configuration of blurring processing in special image processing.
FIG. 4 is a flowchart illustrating an example of a flow of blurring processing.
FIG. 5 is a diagram illustrating a process of an example of blur processing.
FIG. 6 is a block diagram showing another configuration of blur processing.
FIG. 7 is a flowchart illustrating another example of blur processing.
FIG. 8 is a diagram illustrating a process of another example of blur processing.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 10 Printer 42 Main controller 74 Area division means 76 Connection expansion means 78 Separation means 80 Mask generation means 82 Blur processing means 84 Contour extraction means 86 Contour emphasis means

Claims (7)

Calculation means the difference data between the pixel image divided into regions as Fukumaru the pixels the same area adjacent below the threshold, to leave calculate the average coordinates of the pixels in the region divided areas in each area When,
The average coordinate position, a region estimating means you a region located in the region of a small circle or ellipse outside from the image relative to the center of the image and background areas,
A blurring processing means for performing mini blurring of the estimated background region by the region estimating means from the entire image,
An image processing apparatus comprising: The blurring processing means, separating means for separating the whole image into realm excluding background and background regions, and the mask generating means for generating a mask realm except the separated background region by the separating means, said mask The image processing apparatus according to claim 1, further comprising a processing unit that performs a blurring process on a region other than the mask region generated by the generation unit. The mask generating unit extracts a contour of the image, by superimposing the extracted contour to the contour of the realm excluding the background area, the image according to claim 2, characterized in that arranging the outline of the mask Processing equipment. The calculation unit emphasizes the contours in the image, based on the emphasized contour, the image processing apparatus according to claim 1 or claim 2, characterized in that the region division. The image processing apparatus according to any one of claims 1 to 4, further comprising a blurring intensity specifying means for specifying the intensity of the blurring process. The image processing apparatus according to any one of claims 1 to 5, characterized by further comprising a switching means for switching whether to perform the blurring process. And region dividing an image so that the pixel difference data adjacent below the threshold between pixels are in the same area, out calculate the average coordinates of the pixels in the region divided areas in each area,
A region where the average coordinate position is located in a region outside the circle or ellipse smaller than the image based on the center of the image as a background region,
Image processing method, which comprises carrying out the mini-blurring of the background area that is estimated from the entire image.

Images