JP2009003858A - Image processing program and image processor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To blur a light source area in an image. <P>SOLUTION: A light source area specifying part 103a specifies the light source area including a light source in the image. A blur performing part 103c selects a filter used for blurring the light source area from a plurality of filters prepared in advance, and blurs the light source area by using the selected filter. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing program and an image processing apparatus.

  The following image conversion apparatus is known. This image conversion device calculates an exposure amount based on image data in order to reproduce a blur generated in an image taken out of focus, and based on the exposure amount, a bright part in the image is changed to a dark part. A blur that erodes is added (for example, Patent Document 1).

JP 2001-216513 A

  However, in the conventional image conversion device, the bright portion in the image is blurred so that the dark portion erodes, but the bright portion does not necessarily emit light such as a light source. The blur effect may be added to an unnatural position.

An image processing program according to the present invention specifies a light source region including a light source in an image, selects a filter to be used for adding a blurring effect to the light source region from a plurality of filters prepared in advance, and selects the selected filter Is used to add a blurring effect to the light source region.
In the present invention, based on at least one of color information in the light source region, the size of the light source region, the position of the light source region in the image, the brightness of the light source region, lens information at the time of image acquisition, and shooting date / time information. Then, the shape of the blur to be added to the light source region may be determined, and a filter corresponding to the determined blur shape may be selected.
The light source is based on at least one of color information in the light source region, the size of the light source region, the position of the light source region in the image, the brightness of the light source region, and the number of light source regions included in the image. The size of the blur to be added to the region may be determined, and a filter corresponding to the determined blur size may be selected.
A filter for adding a blur having a preset shape and size to the light source region may be selected.
When a plurality of light source areas are specified from the image, the first light source area and the second light source area may be switched based on an instruction from the user. At this time, when the size of the first light source region is different from the size of the second light source region, it is preferable to enlarge or reduce each according to the size of the replacement light source region.
A region having a luminance value greater than or equal to the first threshold is extracted from the image as a first region, and a region having a luminance value greater than or equal to the second threshold smaller than the first threshold is extracted from the image as a second region. The light source region may be specified based on the feature amounts of the first region and the second region. At this time, the ratio between the area of the second region and the area of the first region included in the second region, and the centroid of the second region and the centroid of the first region included in the second region Whether the second area is a light source area or not may be specified based on the positional relationship between
An image processing apparatus according to the present invention comprises an execution means for executing the image processing program.

  According to the present invention, it is possible to add a blurring effect to a light source position in an image.

  FIG. 1 is a block diagram showing a configuration of an embodiment of an image processing apparatus according to the present embodiment. The image processing apparatus 100 is, for example, a personal computer (PC), and includes an operation member 101, a connection IF (interface) 102, a control device 103, an HDD (hard disk drive) 104, and a monitor 105.

  The operation member 101 includes various devices operated by the user, such as a keyboard and a mouse. The connection IF 102 is an interface for connecting an external device such as a digital camera. For example, a USB interface for performing a wired connection with the digital camera, a wireless LAN module for performing a wireless connection, or the like is used. In the present embodiment, for example, image data is captured from a digital camera via the connection IF 102.

  The HDD 104 is a recording device for recording image data captured via the connection IF 102 and various programs executed by the control device 103. The monitor 105 is a liquid crystal monitor, for example, and displays various display data output from the control device 103.

  The control device 103 includes a CPU, a memory, and other peripheral circuits, and functionally includes a light source region specifying unit 103a, a light source color determination unit 103b, and a blurring process execution unit 103c. In the present embodiment, the light source area specifying unit 103a reads an image recorded in the HDD 104 and specifies an area (light source area) including a light source in the image. The light source color determination unit 103b determines the color of the light source based on the color of the light source region specified by the light source region specifying unit 103a. The blurring process execution unit 103b adds a blurring of a color corresponding to the light source color determined by the light primary color determination unit 103b to the light source region. In the following description, it is assumed that image data represented in the RGB color space is recorded in the HDD 104.

The light source region specifying unit 103a specifies a region including a light source in the image as a light source region. Specifically, the light source region specifying unit 103a extracts the light source region based on the luminance value Y of the image. For this purpose, the luminance value Y defined by the following equation (1) is calculated based on the pixel values (R, G, B) (0 ≦ R, G, B ≦ 255) of the image.
Y = 0.2990R + 0.5870G + 0.1140B (1)

  It seems that a light source region can be extracted by extracting a region composed of pixels having a luminance value Y calculated by the expression (1) of a predetermined value or more from the image. However, when there is a white wall in the image, the luminance value Y may also be a predetermined value or more in a region other than the light source region. Extraction does not necessarily include a light source in the area. Therefore, in the present embodiment, the following processing is performed in order to specify the light source region with high accuracy.

Source region specifying unit 103a, the formula (1) luminance value Y calculated in the predetermined luminance value _{Y 1} or more _(e.g., Y 1 = 250) extracts an area formed by the pixel is. Here, when the luminance value Y is more regions composed of pixels having a predetermined luminance value Y ₁ or more in the image, a plurality of regions are extracted. Note that the region extracted here is referred to as a first extraction region in order to distinguish from the region described later.

  The light source region specifying unit 103a calculates the area and the barycentric position of each extracted first extraction region. The barycentric position is calculated, for example, as coordinate values (x coordinate value and y coordinate value) when the entire image is expressed in the XY coordinate system. Further, the light source region specifying unit 103a specifies, for each of the first extraction regions, an outer shape frame that is in contact with the outer shape of the region, and a coordinate value (x coordinate value and y of the contact point between the first extraction region and the outer shape frame). (Coordinate value) is calculated. For example, when the first extraction region 2a is extracted as shown in FIG. 2, the light source region specifying unit 103a specifies the outline frame 2b, and the coordinate values of the contact points 2c to 2f of the region and the contact point. Is calculated.

Further, as shown in FIG. 3, the light source region specifying unit 103a has distances a _i (i = 1 to 1) from the center of gravity 3a of the first extraction region to the edge of the region in eight directions, up and down, left and right, and diagonal directions. 8) is calculated. Then, the light source region specifying unit 103a holds the calculated area of the region, the coordinate value of the center of gravity position, the coordinate value of the contact point between the region and the outer frame, and the distance from the center of gravity to the edge of the region in the memory.

Next, the light source region specifying unit 103a extracts a region composed of pixels in which the luminance value Y calculated by Expression (1) is equal to or higher than a predetermined luminance value Y ₂ (for example, Y ₂ = 240). Here, when the luminance value Y is more regions composed of pixels having a predetermined luminance value Y ₂ or more in the image, a plurality of regions are extracted. The region extracted here is referred to as a second extraction region in order to distinguish it from the first extraction region described above.

The light source region specifying unit 103a calculates the area value of the extracted second extraction region and the coordinate value (x coordinate value and y coordinate value) of the barycentric position. Further, the light source region specifying unit 103a extends from the center of gravity of the second extraction region to the edge of the region in the eight directions of up, down, left, right, and diagonal directions as in the case of the first extraction region described above with reference to FIG. The distance b _i (i = 1 to 8) is calculated. The light source region specifying unit 103a holds the calculated area of the region, the coordinate value of the center of gravity position, and the distance from the center of gravity to the edge of the region in the memory.

As described above, when the second extraction region is extracted with Y ₁ > Y _2, as shown in FIG. 4A, one first extraction region 2 a is included in the second extraction region 4 a. In some cases, as shown in FIG. 4B, the second extraction region 4a includes a plurality of first extraction regions 2a. In the present embodiment, the light source region specifying unit 103a specifies the light source region in a case where one second extraction region 4a is included in the second extraction region 4a and a case where a plurality of first extraction regions 2a are included. .

  As described above, a plurality of second extraction regions may be extracted from the image. In the present embodiment, one of the second extraction regions 4a is used as a light source. An example of determining whether to specify a region will be described. That is, when there are a plurality of second extraction areas 4a, if the processing described below is performed for each second extraction area, each second extraction area 4a is a light source area. It is possible to determine whether or not.

(A) When one first extraction region 2a is included in the second extraction region 4a In this case, since the second extraction region can be determined to be highly independent as a light source region, the shape of the region If it is not distorted, the area is regarded as the light source area. For this reason, the light source region specifying unit 103a specifies the second extraction region as the light source region by the following equations (2) and (3) using the above-described eight-direction distance b _i from the center of gravity to the edge of the region. It is determined whether or not to do. In the following expressions (2) and (3), maxb _i represents the maximum value among b _{1 to} b ₈ , and minb _i represents the minimum value among b _{1 to} b ₈ .
maxb _i / minb _i ≦ 3.0 → specified as a light source region (2)
maxb _i / minb _i > 3.0 → not specified as light source region (3)

  When the second extraction area is specified as the light source area, the light source area specifying unit 103a specifies the barycentric position of the first light source area included therein as the light source position.

(B) In the case where a plurality of first extraction regions 2a are included in the second extraction region 4a In this case, the extracted second extraction region 4a is represented by B, and is included in the second extraction region 4a. One or a plurality (n) of first extraction regions 2a are represented as A _i (i = 1, 2,... N). The center of gravity of _B is expressed as g _B , and the center of gravity of A _i (i = 1, 2,... N) is expressed as g _i (i = 1, 2,... N), respectively.

Here, consider the reason why a plurality of first extraction regions 2a (A _i ) are included in the second extraction region 4a (B). As described above, this phenomenon occurs when the reference value (threshold value) of the luminance value Y used when extracting the region is slightly reduced from Y ₁ (for example, 250) to Y ₂ (for example, 240). Because of this, there are two possible reasons. Cause 1: In the first place, the large area B is not a light source area, and each A _i is only a part thereof.
Cause 2: Although the large area B is the light source area, only a plurality of A _i appear in the area B depending on how the reference value Y ₁ is selected.

In both cases of cause 1 and cause 2, it may be determined that most of A _i is not the light source region, and if B is the light source region as in cause 2, when drawing a cross, which will be described later, It is sufficient to generate a cross from the centroid g _{B of B} or the centroid g _i (i = 1, 2,..., N) of A _i close to g _B to some extent. In consideration of this point, the light source region specifying unit 103a performs the following process to determine whether or not the second extraction region 4a, that is, B is a light source region.

First, the light source region specifying unit 103a is present at a position closest to the centroid g _{B of} the B among the centroids g _i (i = 1, 2,..., N) of the plurality of A _i included in the B. Is extracted as the center of gravity G. In this embodiment, when B is determined to be a light source area, to identify the center of gravity G as a light source position, so as to generate only the cross from the center of gravity G, the cross from another center of gravity g _i It shall not be generated.

Here, when B is a light source region, the position of the center of gravity g _B of _{B and} the position of the extracted center of gravity G should not greatly differ as shown in FIG. If it is not the light source region, the position between the two will be greatly different as shown in FIG. Therefore, in the present embodiment, in consideration of this, it is determined whether B is appropriate as the light source region. Specifically, the light source region specifying unit 103a determines that B is inappropriate as the light source region when the distance between G and g _B is larger than the allowable range. On the other hand, if the distance between G and g _B is within the allowable range, it is determined that B is appropriate as the light source region.

For example, the light source region specifying unit 103a determines whether or not B is appropriate as the light source region by the following equation (4). That is, the light source region specifying unit 103a determines that B is inappropriate as the light source region when the distance between G and g _B satisfies the condition shown in the following expression (4), and when the distance is not satisfied Is determined to be appropriate.
Distance between G and g _B > 2 × mina _i (4)

If the light source region specifying unit 103a determines that B is appropriate as the light source region as a result of the determination using the equation (4), the light source region specifying unit 103a further uses the following equations (5) and (6) as a light source. It is determined whether or not the area is specified. That is, the light source area specifying unit 103a determines that B is inappropriate as the light source area when either one of the following expressions (5) and (6) is satisfied, and B is used as the light source area. Do not specify. On the other hand, if neither of the conditions shown in the following equations (5) and (6) is satisfied, the light source region specifying unit 103a determines that B is appropriate as the light source region and specifies B as the light source region.
maxb _i / minb _i > 3.0 (5)
_Area> 1.0+ area _{A i} including the area / G region _{B (Y 1 / Y 2)} ··· (6)

When the light source area specifying unit 103a specifies B as the light source area, the center of gravity g of B out of the centers of gravity g _i (i = 1, 2,..., N) of A _i included in B is included. _The center of gravity G present at the position closest to _B is specified as the light source position. Through the above processing, the light source region specifying unit 103a can specify the light source region and the light source position in the image with high accuracy.

  The light source color specifying unit 103b determines the color of the light source included in the light source region based on the color information in the light source region specified by the processing by the light source region specifying unit 103a described above. At the center of the light source in the image, the color is white regardless of the color of the light source, so the values of R, G, B at that position are all close to 255, and the color of the light source is determined. It is unsuitable for use as information. In the present embodiment, the color of the light source is determined based on the color information of the outer portion in the identified light source region, that is, a point that is a predetermined distance away from the center of gravity. For example, in the light source region 6a shown in FIG. 6, the light primary color determination unit 103b determines the light source color by using the color information of the points in the region 6c outside the central region 6b.

Specifically, the light primary color determination unit 103b performs processing as follows. First, light primary color determination unit 103b, in order to obtain color information of a point in the outer regions 6c, the center of gravity of light source areas, that is, the second vertical and horizontal and 8 directions of the oblique direction from the center of gravity g _B of the extraction area above Are scanned for points satisfying either of the following formulas (7) or (8), and the points satisfying the condition are extracted one by one from each direction, that is, eight points.
max (R, G, B) -min (R, G, B)> 140 (7)
Y <100 (8)

  The light primary color determination unit 103b examines the distribution of the angle of the hue circle with respect to the extracted eight points, and excludes points that are greatly deviated from the distribution. Then, the light primary color determination unit 103b determines the color of the light source (Init_R, Init_G, Init_B) based on the average of the hue ring angles of the remaining points.

  First, the blurring processing execution unit 103c determines the shape of blurring to be added to the light source region in the image according to the color of the light source determined by the light primary color determination unit 103b, that is, the color information in the light source region. For example, when the light source color is red, the blur shape is circular, when the light source color is blue, the blur shape is diamond, and the light source color is orange. In this case, the blur shape is determined as a hexagon, and if the light source is pink, the blur shape is determined as a heart.

  Next, the blurring processing execution unit 103c selects and reads a filter corresponding to the determined blurring shape from filters prepared in advance for each blurring shape and recorded in the memory. For example, when the color of the light source is blue and the blurring shape is determined to be a rhombus, the blurring processing execution unit 103c selects a filter for blurring the light source region into a rhombus as illustrated in FIG. A plurality of sizes of filters are prepared so that the filters of each shape can be selected according to the size of the light source region.

  The blurring process execution unit 103c selects and reads a filter that matches the size of the light source region from among a plurality of sizes of filters according to the light primary color, and generates a template that reflects the determined light source color. To do. For example, a template is created by applying a light source color to each element value of the filter. In the example shown in FIG. 7, when the light primary color is (255, 0, 0), the light source color (255, 0, 0) is applied to the element value 1 for the element 7a in the filter.

The blurring processing execution unit 103c adds a blurring effect to the light source region in the image by blending the created template with the pixel values of the light source region. The blending can be performed by the following equation (9) when the pixel value of each pixel in the light source region is go, the pixel value of each pixel of the template is gt, and the pixel value after blending is gb. .
gb = max (go, gt) (9)

  FIG. 8 is a flowchart showing processing of the image processing apparatus 100 according to the present embodiment. The processing shown in FIG. 8 is executed by the control device 103 as a program that starts when the user instructs the user to add a blurring effect to the light source region. Note that the processing target image is selected in advance by the user, and the control apparatus 103 reads the selected image from the memory card into the memory.

  In step S10, the light source region specifying unit 103a performs the above-described processing on the processing target image, and specifies a region including the light source in the image as the light source region. Thereafter, the process proceeds to step S20, and the light source color specifying unit 103b determines whether the light source region is specified by the light source region specifying unit 103a, that is, whether or not the light source region exists in the image. If a negative determination is made, the process is terminated as it is. On the other hand, if a positive determination is made, the process proceeds to step S30.

  In step S30, as described above, the light source color specifying unit 103b determines the color of the light source included in the light source region based on the color information of the outer portion in the light source region specified by the light source region specifying unit 103a. . Thereafter, the process proceeds to step S40, and the blurring process execution unit 103c determines the blurring shape to be added to the light source region in the image according to the color of the light source determined by the light primary color determination unit 103b, and then proceeds to step S50. .

  In step S50, the blurring process execution unit 103c selects and reads a filter corresponding to the determined blurring shape and the size of the light source region. Thereafter, the process proceeds to step S60, and the blurring process execution unit 103c generates a template reflecting the color of the light source using the read filter as described above, and then proceeds to step S70. In step S70, the blurring process execution unit 103c adds a blurring effect to the light source region in the image by blending the created template and the pixel value of the light source region according to Expression (9). Thereafter, the process ends.

According to the present embodiment described above, the following operational effects can be obtained.
(1) The light source region specifying unit 103a specifies a light source region including a light source in the image, and the blurring processing execution unit 103c is for adding a blurring effect to the light source region from among a plurality of filters prepared in advance. A filter to be used was selected, and a blurring effect was added to the light source region using the selected filter. As a result, a blurring effect can be automatically added to the light source region.

(2) The blurring processing execution unit 103c determines a blurring shape to be added to the light source region based on the color information in the light source region, and selects a filter according to the determined blurring shape. Accordingly, it is possible to add a blur of a shape that matches the color image of the light source region to the light source region.

(3) The blurring processing execution unit 103c determines the size of the blurring effect to be added to the light source region based on the size of the light source region, and selects a filter corresponding to the determined blurring size. Accordingly, it is possible to add a blur of a size suitable for the size of the light source region to the light source region.
(4) light source region identifying unit 103a, the luminance value Y from the image extracts a predetermined luminance value Y ₁ or more regions as a first extraction region, from the image luminance value Y is smaller predetermined than Y ₁ extracting the luminance value Y ₂ or more regions as a second extraction region based on the feature amount of the first extraction region and a second extraction region, and to identify the source region including a light source in an image. As a result, the light source identification accuracy can be improved as compared with the case where the light source is identified using one luminance value.

(5) The light source region specifying unit 103a includes the ratio between the area of the second extraction region and the area of the first extraction region included in the second extraction region, the center of gravity of the second extraction region, and the second Whether or not the second extraction region is a light source region is specified based on a positional relationship with the center of gravity of the first extraction region included in the extraction region. That is, the area and the center of gravity are used as the feature amounts of the first extraction region and the second extraction region. Thereby, the light source region in the image can be specified with high accuracy.

-Modification-
The image processing apparatus according to the above-described embodiment can be modified as follows.
(1) In the above-described embodiment, an example in which the blurring processing execution unit 103c determines the shape of blurring to be added to the light source region in the image according to the color of the light source determined by the light primary color determination unit 103b. did. However, the lens information at the time of shooting and the shooting date and time may be recorded in association with the image, and the blurring processing execution unit 103c may determine the blurring shape to be added to the light source region based on these information. For example, the lens used may be specified based on the recorded lens information, and the shape of the aperture of the lens may be a blurred shape. Alternatively, the season may be specified based on the shooting date and time, and the blur shape may be adapted to the season. Here, as a blurred shape suitable for the season, for example, in the case of spring, the shape of a petal may be a blurred shape. As a result, it is possible to add blurring of the shape reflecting the situation at the time of shooting to the light source region.

  Alternatively, the blurring processing execution unit 103c may determine the blurring shape based on the size and brightness of the light source region. For example, some threshold values may be provided for the size and brightness of the light source region, and the blurring shape may be determined based on a comparison result with each threshold value. The blur shape may be determined depending on the position where the light source exists in the image. For example, the image is divided into 16 and a blur shape is assigned to each area. Then, the blurring shape may be determined depending on in which region the light source region exists. As a result, an optimum blur effect corresponding to the light source region can be added. Note that the blurring process execution unit 103c combines the elements of the light source color, lens information at the time of shooting, the shooting date and time, the size of the light source region, the light source region brightness, and the location of the light source region in the image, The blur shape may be determined.

(2) In the above-described embodiment, the example in which the blurring process execution unit 103c selects the size of the filter used when creating the template according to the size of the light source region has been described. However, the size of the filter may be determined based on the color of the light source region and the brightness of the light source region. For example, the size of the filter to be used may be determined according to the hue of the light source region, or may be determined according to the luminance level of the light source. Further, as in the case of determining the blur shape described in the modification (2), it may be determined based on the position of the light source region in the image. As a result, an optimum blur effect corresponding to the light source region can be added.

  Alternatively, the blurring process execution unit 103c may determine the size of the filter according to the number of light source regions specified in the image. If there are a large number of light source regions in the image, a smaller filter may be used, and if there are fewer light source regions, a larger filter may be used. When a large filter is used when there are many light source areas in the image, there is a high possibility that the blur to be added to the light source area will be overlapped. It can be avoided. The blurring process execution unit 103c combines the elements of the size of the light source region, the number of light source regions in the image, the color of the light source region, the brightness of the light source region, and the location of the light source region in the image. The size of the filter to be used may be determined.

(3) In the above-described embodiment, the example in which the blurring process execution unit 103c automatically determines the shape and size of the filter to be used based on the information on the light source region and generates the template has been described. That is, the blurring process execution unit 103c determines a blurring shape according to the color of the light source, selects a filter according to the size of the light source region, blends the selected filter and the light source color, and sets the color of the light source. The reflected template was generated. However, the user may make these settings in advance. For example, the user can preliminarily set the color of the light source as blue for all the light source regions in the image and set the filter shape to be a hexagon, and the blurring process execution unit 103c sets this setting. A template may be generated based on the above. Accordingly, the user can add a blurring effect using a filter having a desired shape and size to the light source region.

(4) Furthermore, when a plurality of light source regions are specified in the image, the specification result may be presented to the user so that the user can arbitrarily replace each light source region. For example, the light source area specifying unit 103a displays an image clearly shown by surrounding the specified light source area with a frame on the monitor 105 and presents it to the user. Then, the replacement of the light source region from the user is accepted. The user can instruct replacement by clicking each of the two light source regions to be replaced with the mouse included in the operation member 101. When the user detects that any two light source areas on the image are clicked by the user, the light source area specifying unit 103a replaces the respective light source areas and displays them on the image.

  At this time, if the sizes of the respective light source regions are different, it is necessary to adjust the size by enlarging or reducing the light source region so as to match the size of the replacement light source region. Further, the color of the light source region may be replaced while retaining the color of the light source region before replacement, or may be replaced after changing to the color of the light source region of the replacement destination. Thereby, the user can arbitrarily change the position of the light source region.

  Note that the present invention is not limited to the configurations in the above-described embodiments as long as the characteristic functions of the present invention are not impaired.

It is a block diagram which shows the structure of one Embodiment of an image processing apparatus. It is a figure which shows the specific example of the contact of a 1st extraction area | region and an external shape frame. It is a figure which shows the specific example of the distance of 8 directions from the gravity center of a 1st extraction area | region to the edge of an area | region. It is a figure which shows the specific example of the 1st extraction area | region contained in a 2nd extraction area | region. It is a figure which shows the specific example in the case where the 2nd extraction area | region is a light source area, and the case where it is not so. It is a figure which shows the specific example of the area | region of the center part of a light source, and the area | region of an outer part. It is a figure which shows the specific example of a rhombus filter. 3 is a flowchart showing processing of the image processing apparatus 100. FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Image evaluation apparatus, 101 Operation member, 102 Connection IF, 103 Control apparatus, 103a Light source area specific | specification part, 103b Light source color determination part, 103c Blur process execution part, 104 HDD, 105 monitor

Claims (9)

A light source region specifying procedure in which a computer specifies a light source region including a light source in an image;
A filter selection procedure in which the computer selects a filter to be used for adding a blurring effect to the light source region from among a plurality of filters prepared in advance;
An image processing program for causing the computer to execute a blurring effect adding procedure in which the computer adds a blurring effect to the light source region using the filter selected in the filter selection procedure. In the image processing program according to claim 1,
In the filter selection procedure, the computer performs color information in the light source region, a size of the light source region, a position of the light source region in an image, brightness of the light source region, lens information at the time of image acquisition, and photographing. An image processing program characterized by determining a blurring shape to be added to the light source region based on at least one of the date and time information, and selecting the filter according to the determined blurring shape. The image processing program according to claim 1 or 2,
In the filter selection procedure, the computer performs color information in the light source region, the size of the light source region, the position of the light source region in the image, the brightness of the light source region, and the light source region included in the image. An image processing program characterized by determining a blur size to be added to the light source region based on at least one of the numbers and selecting the filter according to the determined blur size. In the image processing program according to claim 1,
In the filter selection procedure, the computer selects the filter for adding a blur having a preset shape and size to the light source region. In the image processing program according to any one of claims 1 to 4,
When the plurality of light source areas are specified from the image in the light source area specifying procedure, the computer replaces the first light source area and the second light source area based on an instruction from the user. An image processing program further comprising a procedure. The image processing program according to claim 5,
In the light source region replacement procedure, when the size of the first light source region is different from the size of the second light source region, the computer enlarges each according to the size of the replacement light source region. An image processing program characterized by reducing. In the image processing program according to any one of claims 1 to 6,
In the light source region specifying procedure, the computer extracts a region having a luminance value equal to or higher than a first threshold value from the image as a first region, and a second luminance value from the image is smaller than the first threshold value. An image processing program characterized in that an area equal to or greater than a threshold is extracted as a second area, and the light source area is specified based on feature amounts of the first area and the second area. The image processing program according to claim 7,
In the light source region specifying procedure, the computer has a ratio between an area of the second region and an area of the first region included in the second region, a center of gravity of the second region, and the first region. An image processing program that specifies whether or not the second area is the light source area based on a positional relationship with the center of gravity of the first area included in the second area.   An image processing apparatus comprising an execution unit for executing the image processing program according to claim 1.

Images