JP2001143074A - Image processor, image processing method and computer- readable recording medium in which image processing program is recorded - Google Patents

Abstract

PROBLEM TO BE SOLVED: To increase processing speed. SOLUTION: This image processor is provided with a size-detecting part 202 to detect size of inputted area data, a local area discriminating part 200 for detecting gradation to represent characteristics of an image, based on pixel values of the image and an attribute discriminating part 203 to decide an attribute corresponding to an image is decided among plural predetermined attributes according to size data to represent the size from the size detecting part 202 and the gradation from a featured value detecting part 201. Since the attribute is decided, based on the size and gradation of the area, execution time of the processing to be executed later is taken into consideration.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus, an image processing method, and a computer-readable recording medium on which an image processing program is recorded, and more particularly to an image processing apparatus for processing an image including a plurality of areas having different attributes for each area. The present invention relates to a computer-readable recording medium storing an image processing method and an image processing program.

[0002]

2. Description of the Related Art The nature of an image differs depending on the content of the image. An image in which a photograph is displayed has a property that the pixel value changes in a complicated manner with rich gradation. Further, an image in which a line drawing such as a graph or an illustration is represented has a property mainly composed of a monochromatic portion and a sharp edge. In the following, the properties of images are classified by image attributes, images representing photographs are referred to as photo attributes, images representing line drawings are referred to as line drawing attributes, and images representing characters are referred to as character attributes.

Generally, image data is subjected to correction processing as needed to improve image quality, and compression processing is performed to reduce the amount of data. However, it is desirable to apply a correction process or a compression process according to each attribute to images having different attributes in order to improve the image quality and the compression ratio.

As a correction process, there is a color reduction process performed on an image having a line drawing attribute. The color reduction processing is color reduction in which the number of colors is reduced so that the image has a small number of colors. Color reduction processing
The degree of color reduction indicating the number of colors to be reduced can be made different, and the higher the degree of color reduction, the smaller the number of colors included in the processed image. When the degree of color reduction is increased, the number of colors to be compared is reduced, so that the processing time is shortened. In the color reduction processing,
The larger the size of the image to be processed, the longer the processing time because the number of pixels to be processed increases.

[0005] An image having a photo attribute is subjected to a smoothing process or the like for removing noise to obtain a clear image. Excessive correction such as color reduction processing and edge emphasis on an image with a photo attribute is not preferable because it deteriorates image quality. Note that these correction processes also have a role of improving the compression ratio.

[0006] Regarding the compression processing, an image with the line drawing attribute is
P that can achieve high compression ratio when the number of colors is small
A compression method such as NG is used. For images with photo attributes, a compression method such as JPEG that can achieve a high compression ratio when the pixel value changes continuously is used.

An image including a plurality of regions having different image attributes requires a process of dividing the region for each image attribute. A technique for dividing this area is disclosed in Japanese Patent Laid-Open No. 8-5628.
No. 7 is described. Further, a technology relating to the color reduction processing in the correction processing is disclosed in Japanese Patent Application Laid-Open No. H10-74248,
JP-A-9-97323 and JP-A-8-317
241.

[0008]

However, in some cases, the line drawing attribute region and the photograph attribute region have similar characteristics such as gradation, and the attribute is accurately determined only from the characteristics obtained from the pixel data. Can be difficult to do.

[0009] When an area which is originally a photograph attribute is erroneously determined to be a line drawing attribute, the image quality is degraded if the color reduction processing performed on the image having the line drawing attribute is performed. This is because it is necessary to maintain the gradation of an image with a photo attribute, but this gradation is impaired by performing color reduction processing.

In the conventional color reduction processing, the degree of color reduction is determined based only on pixel values included in an image.
There is a problem that much time is spent depending on the image to be processed.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and an image processing apparatus having an improved processing speed.
A first object is to provide a computer-readable recording medium on which an image processing method and an image processing program are recorded. It is a second object of the present invention to provide an image processing apparatus, an image processing method, and a computer-readable recording medium on which an image processing program is recorded, capable of executing processing with a balance between processing speed and image quality.

[0012]

According to an aspect of the present invention, there is provided an image processing apparatus comprising: first detecting means for detecting a size of an input image; A second detecting means for detecting characteristic data representing the characteristic, a size data representing a size from the first detecting means, and a characteristic data from the second detecting means, among a plurality of predetermined attributes. Attribute determining means for determining an attribute corresponding to the image.

According to the present invention, the attribute corresponding to the image is determined from the plurality of predetermined attributes according to the size data representing the size from the first detecting means and the characteristic data from the second detecting means. It is determined. The processing to be performed on the image differs depending on the attribute of the image. The size of an image affects the execution time of processing performed on the image. Therefore, it is possible to determine the attribute in consideration of the execution time of the subsequent processing performed on the image, and to provide an image processing apparatus with an improved processing speed.

Preferably, the attribute determining means determines the attribute according to a reference value determined by the size of the size data and the feature data, and the reference value includes a reference value in which the sizes of the size data and the feature data are in a reciprocal relationship. It is characterized by the following.

According to the present invention, the attribute is determined according to the reference value determined by the size of the size data and the feature data, and the reference value includes a reference value in which the sizes of the size data and the feature data are in a reciprocal relationship. It is further possible to accurately determine the attributes of the image.

[0016] Preferably, the restriction processing means executes restriction processing for restricting a pixel value to the image, size data representing a size from the first detection means, and characteristic data from the second detection means. A degree determining unit that determines a degree of the limiting process corresponding to the image, wherein the limiting processing unit executes the limiting process according to the degree determined by the degree determining unit.

According to the present invention, the degree of the restriction processing corresponding to the image is determined according to the size data representing the size from the first detecting means and the characteristic data from the second detecting means, and the determined degree is determined. Is performed according to the following. The degree affects the image quality of the image on which the restriction processing has been executed. Therefore, it is possible to further execute the limiting process in consideration of the image quality of the image, and it is possible to provide an image processing apparatus capable of executing the process in which the processing speed and the image quality are balanced.

According to another aspect of the present invention, a restriction processing means for performing a restriction processing for restricting a pixel value to an input image, a first detection means for detecting an image size, A second detecting means for detecting feature data representing the feature of the image based on the pixel value of the image data, and a size corresponding to the image according to the size data representing the size from the first detecting means and the feature data from the second detecting means. And a degree determining means for determining a degree of the limiting processing to be performed, wherein the limiting processing means executes the limiting processing according to the degree determined by the degree determining means.

According to the present invention, the degree of the restriction processing corresponding to the image is determined according to the size data representing the size from the first detecting means and the characteristic data from the second detecting means, and the determined degree is determined. Is performed according to the following. The size of the image affects the execution time of the restriction process. The degree affects the image quality of the image on which the restriction processing has been executed. Therefore, it is possible to execute the limiting process in consideration of the execution time of the limiting process and the image quality of the image, and it is possible to provide an image processing apparatus capable of executing the process in which the processing speed and the image quality are balanced.

Preferably, the degree is determined to be larger as the size data is larger.

According to the present invention, the degree is more likely to be determined to be a larger value as the size data is larger, so that the larger the size of the image is, the more the influence on the image by the limiting process can be further increased.

Preferably, the degree is determined to be smaller as the size data is smaller.

According to the present invention, the degree is more likely to be determined to be smaller as the size data is smaller, so that the smaller the size of the image, the smaller the effect on the image by the limiting process.

According to yet another aspect of the invention,
Limiting processing means for performing a limiting process for limiting a pixel value to an input image; detecting means for detecting feature data representing a feature of the image based on the pixel value of the image; And a degree determining means for determining a degree of the limiting processing corresponding to the image, wherein the limiting processing means executes the limiting processing according to the degree determined by the degree determining means.

According to the present invention, the degree of the restriction processing corresponding to the image is determined according to the characteristic data from the detection means, and the restriction processing is executed according to the determined degree. The degree affects the image quality of the image on which the restriction processing has been executed. Therefore, it is possible to provide an image processing apparatus capable of executing the limiting process so as to obtain an image quality according to the characteristics of the image.

According to yet another aspect of the present invention,
A first detection step of detecting the size of the input image, a second detection step of detecting feature data representing a feature of the image based on the pixel value of the image, and a size detection process performed by the first detection step. An attribute determining step of determining an attribute corresponding to an image from among a plurality of predetermined attributes in accordance with the size data to be represented and the feature data detected by the second detecting step.

According to the present invention, the size data representing the size detected in the first detecting step and the second
The attribute corresponding to the image is determined from the plurality of predetermined attributes according to the characteristic data detected in the detecting step. Therefore, the attribute can be determined in consideration of the execution time of the processing performed on the image, and an image processing method with an improved processing speed can be provided.

According to yet another aspect of the present invention,
An image processing method for performing a restriction process for restricting a pixel value of an input image, the method including a first detection step of detecting a size of the image, and representing a feature of the image based on a pixel value of the image In accordance with a second detection step for detecting characteristic data, size data representing the size detected in the first detection step, and characteristic data detected in the second detection step, the degree of the restriction processing corresponding to the image is determined. It includes a degree determining step to be determined and a restriction processing step of executing a restriction process on the image according to the degree determined in the degree determining step.

According to the present invention, the size data representing the size detected in the first detecting step and the second
The degree of the restriction process corresponding to the image is determined according to the feature data detected in the detection step, and the restriction process is performed on the image according to the determined degree. Therefore, it is possible to execute the limiting process in consideration of the execution time of the limiting process and the image quality of the image, and it is possible to provide an image processing method capable of executing the process in which the processing speed and the image quality are balanced.

According to yet another aspect of the invention,
The recording medium on which the image processing program is recorded includes a first detection step of detecting a size of the input image, a second detection step of detecting feature data representing a feature of the image based on a pixel value of the image, An attribute determining step of determining an attribute corresponding to an image from a plurality of predetermined attributes according to size data representing the size detected by the first detection step and feature data detected by the second detection step; Is recorded on a computer to execute an image processing program.

According to the present invention, the size data representing the size detected in the first detection step and the second
The attribute corresponding to the image is determined from the plurality of predetermined attributes according to the characteristic data detected in the detecting step. Therefore, the attribute can be determined in consideration of the execution time of the processing to be performed on the image, and a computer-readable recording medium that records an image processing program with an improved processing speed can be provided.

According to yet another aspect of the invention,
The computer-readable recording medium on which the image processing program is recorded is a computer-readable recording medium on which an image processing program for executing a restriction process for restricting a pixel value on an image is stored. A first detection step of detecting the size of the image, a second detection step of detecting characteristic data representing the characteristics of the image based on the pixel values of the image, and size data representing the size detected by the first detection step. In accordance with the feature data detected in the second detection step, a degree determination step for determining the degree of the restriction processing corresponding to the image, and the restriction processing is performed on the image in accordance with the degree determined in the degree determination step. And a restriction processing step.
An image processing program to be executed by a computer is recorded.

According to the present invention, the size data representing the size detected in the first detecting step and the second
The degree of the restriction process corresponding to the image is determined according to the feature data detected in the detection step, and the restriction process is performed on the image according to the determined degree. Therefore, it is possible to execute the limiting process in consideration of the execution time of the limiting process and the image quality of the image, and to perform a computer-readable recording in which an image processing program capable of executing the process with a balance between the processing speed and the image quality is recorded. A medium can be provided.

[0034]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a digital camera provided with an image processing device according to an embodiment of the present invention will be described with reference to the drawings. The same reference numerals in the drawings denote the same or corresponding members, and description thereof will not be repeated.

FIG. 1 is a diagram showing a relationship between a digital camera 1 and an original 2 to be imaged according to one embodiment of the present invention. FIG. 2 is a perspective view of the digital camera 1 as viewed from the lens side. Referring to the figure, digital camera 1
Has a shooting button 3, a shooting lens unit 4, and a card insertion slot 5.

The result of photographing by the digital camera 1 is stored as electronic data on a hard disk card (not shown) existing inside the digital camera 1. Here, the hard disk card is a recording medium for image data. For example, a hard disk card conforming to PCMCIA may be used, or a memory card may be used instead. Further, a mini disc (MD) may be used as a recording medium. Further, instead of using a card as a recording medium, the digital camera 1 may be directly connected to a printer or the like by, for example, a SCSI cable or the like.

The digital camera 1 according to the present embodiment can improve the image quality and compression ratio when saving paper documents such as materials, catalogs, magazines, and research records distributed at conferences and the like as electronic data. .

FIG. 3 is a block diagram showing a circuit configuration of the digital camera 1. Referring to FIG. 3, digital camera 1 has a CPU 10 that controls the entire digital camera 1.
0, a CCD 104 for taking an image, a display unit 106 for displaying the taken image, a RAM 108 for temporarily storing an image from the CCD 104, an area dividing unit 110 for dividing the taken image into regions, Region determining unit 112 for determining the attribute of the region for each of the selected regions, an adaptive correcting unit 114 for performing a correction process suitable for the determined attribute for each region, and for each region divided by region dividing unit 110 A compression unit 116 for performing compression, an image synthesis unit 118 for integrating and outputting the compressed images,
Card memory unit 120 for recording images, CPU
100 for storing a program to be executed by
OM102.

An external storage device 122 is connected to the CPU 100 of the digital camera 1 and the digital camera 1 is stored in the CD-ROM 124 or a floppy (registered trademark) disk.
May be read.

Next, the actual shooting will be described with reference to the block diagram shown in FIG. In FIG. 3, thick arrows indicate the flow of images, and thin arrows indicate the flow of control data. When the user turns on the power of the camera, the scene captured by the imaging lens unit 4 is displayed on the display unit 106 via the CCD 104.

When the CPU 100 detects that the photographing button 3 has been turned ON, the CPU 100 instructs the CCD 104 to integrate the CCD.
Dump to 108. Then, the image is displayed on the display unit 106 (freeze display).

The image from the CCD 104 is stored in a RAM 108
Is stored. When the image is stored in the RAM 108 from the CCD 104, the area dividing unit 110, the area determining unit 112,
The processing is sequentially performed by each of the adaptive correction unit 114, the compression unit 116, and the image synthesis unit 118, and the card memory unit 120
Stores image compression data compressed by a compression method such as JPEG or PNG.

The card memory unit 120 may be a hard disk or the like, or an external storage device or terminal. In addition, image data can be output to a printer or monitor without performing compression. Further, the area dividing unit 11
0, area determination unit 112, adaptive correction unit 114, compression unit 11
6. The processing performed by each of the image synthesis units 118 is as follows.
The processing may be performed inside the digital camera 1 or may be performed by transferring data to another camera connected to the digital camera 1 or a terminal such as a personal computer.

Next, the flow of processing performed by the digital camera 1 when an image is stored in the RAM 108 will be described. FIG. 4 is a flowchart illustrating a flow of image processing performed by the digital camera 1. Referring to FIG.
The image captured by the CCD 104 is stored in the RAM, so that the image is input to the digital camera 1 (step S01). The area dividing unit 110 performs an area dividing process on the image stored in the RAM 108 (step S02).

Then, local area determination is performed for each of the divided areas (step S03). The local region determination is a process of obtaining the properties of the local region in a local region included in the region, for example, in a pixel unit or a block unit configured by a plurality of pixels. The properties of the local region refer to the properties of the image with the photo attribute and the properties of the image with the line drawing attribute.

An attribute discriminating process for discriminating the attribute of the region is performed based on the property determined for each local region in the local region discrimination in step S03 (step S04). As a result, the image is divided into a character area having a character attribute, a line drawing area having a line drawing attribute, or a photograph area having a photograph attribute.

Generally, the input document 2 includes a character area, a line drawing area, a photograph area, and the like. Here, the character area indicates a rectangular area composed of only characters on a black background. The line drawing area indicates a rectangular area mainly composed of a single color area and an edge area, such as a graph or a solid image. Further, the photo region indicates a rectangular region including many portions where the gradation changes, and paintings, illustrations, textures, and the like are also included in the photo region. Note that the line drawing area and the photograph area may have similar image characteristics, and it may be difficult to clearly distinguish the line drawing area and the photograph area from only the pixel data of the image.

The correction processing in the adaptive correction unit 114 and the compression in the compression unit 11 are performed for each area based on the determined attribute.
6 is performed (step S0).
5). In the correction processing performed by the adaptive correction unit 114, color reduction processing for preventing image quality deterioration due to noise and improving the compression ratio is performed on the area with the line drawing attribute.
Smoothing is performed on a region with a photo attribute in order to prevent image quality deterioration and compression ratio deterioration due to noise. Processing such as resolution conversion, character correction, and binarization is performed on the character attribute area.

The compression processing in the compression section 116 is performed on the area subjected to the correction processing in the adaptive correction section 116. The area having the line drawing attribute is compressed by a compression method such as PNG. The area of the photograph area is compressed by a compression method such as JPEG. Binary compression is applied to the character attribute area. Note that the OCR is
May be performed to convert the character code.

The data compressed for each area is stored in the image forming unit 1.
At 18, they are integrated and output to the card memory unit 120.

In the present embodiment, the process of discriminating between a line drawing area and a photograph area by the area discriminating section 112 will be described. However, it is easy to discriminate a character area from a line drawing area and a photograph area. Can be determined using a known technique. Regarding this, the description is omitted here, and the discrimination between the line drawing area and the photograph area will be described.

Next, the area dividing process performed by the area dividing section 110 will be described. FIG. 5 is a flowchart showing step S in FIG.
9 is a flowchart showing a flow of a region dividing process performed in 02. Referring to FIG. 5, in the area dividing process, an image is expanded (step S11), and the image is divided into rectangular areas by rectangularizing the expanded image (step S12). This region division processing will be described with a specific example. FIG. 6 is a diagram illustrating an example of an image stored in the RAM 108. Referring to FIG. 6, an image 150 includes an image 151 representing a photograph,
An image 152 representing a bar graph, an image 153 representing a pie graph, and images 154 and 15 representing characters.
5 is included. The image expansion processing performed in step S11 of the area division processing is, for example, processing for converting a thin line into a thick line. Specifically, a pixel value around a certain pixel is set to be the same as a pixel value of a certain pixel. As a result, the black character becomes a black lump, and the image 154 in which the character is represented by being combined with the adjacent character becomes one black lump.

FIG. 7 is a view showing an expanded image obtained by expanding the image 150. The expanded image 160 includes an image 161 obtained by expanding the image 151 representing a photograph, an image 162 obtained by expanding the image 152, and an image 163 obtained by expanding the image 153.
And images 164 and 165 obtained by expanding the images 154 and 155 in which characters are displayed.

In addition, separately from the image expansion processing,
A process of reducing the image may be used together with the expansion process.

Then, the circumscribed rectangle is formed on the expanded image 160. FIG. 8 is a diagram illustrating a state where the circumscribed rectangle processing is performed on the expanded image 160. The circumscribed rectangle is generated by moving a horizontal straight line in the expanded image 160 in the vertical direction to extract a straight line that is in contact with any contour of the regions 161 to 165, and moving the vertical straight line in the horizontal direction. A straight line tangent to any one of the contours of the regions 161 to 165 is extracted. Then, of the extracted straight lines, an area 171 surrounded by two horizontal straight lines and two vertical straight lines
~ 175. By this circumscribed rectangle processing, as shown in FIG.
The areas 171 to 175 are divided.

Next, the area determining unit 112 will be described.
FIG. 9 is a block diagram illustrating a detailed configuration of the area determination unit 112. Referring to FIG. 9, region data indicating a region image is input to region determination unit 112 for each region divided by region division unit 110. Therefore, the area determining unit 1
At 12, processing is performed for each region.

The area dividing section 112 includes a local area determining section 200 for determining the property of each local area of the input area data, and a feature quantity for detecting the feature of the area based on the property determined for each local area. A detection unit 201, a size detection unit 202 for detecting the size of the region from the input region data, and a feature amount detected by the feature amount detection unit 201 and a size detected by the size detection unit 202. Attribute determining unit 203 for determining the attribute of the area. If the determined attribute is a line drawing area, the attribute determining unit 203 determines the degree of a color reduction process described later. The area determination unit 112 is controlled by a control signal from the CPU 100 (not shown).

FIG. 10 is a flowchart showing the flow of the local area discriminating process performed in step S03 of FIG. Referring to FIG. 10, local region determining section 200 determines a local region for each image in the input region data. The area determination unit 200 calculates the difference between the luminance value of the processing target pixel and the luminance value of a pixel adjacent to the processing target pixel, and calculates the maximum value M of the calculated difference. The pixel adjacent to the processing target pixel corresponds to, for example, eight adjacent pixels in a 3 × 3 block centered on the processing target pixel. The difference in the luminance value between the processing target pixel and the adjacent pixel means a change in the luminance between the processing target pixel and the adjacent pixel.

The obtained maximum value M is compared with a predetermined threshold value TH1 (step S22). If the maximum value M is larger than the threshold value TH1, the process proceeds to step S23,
If not, the process proceeds to step S24. Step S
At 23, the process ends with the pixel attribute of the processing target pixel set to “edge”.

In step S24, the maximum value M is compared with a predetermined threshold value TH2 (step S24).
If the maximum value M is larger than the threshold value TH2, the process proceeds to step S25; otherwise, the process proceeds to step S26. In step S25, the pixel attribute of the processing target pixel is set to “gradation”, and the process ends. In step S26, the pixel characteristic of the processing target pixel is set to “monochromatic”, and the process ends. In this way, a pixel attribute is determined for each pixel included in the region.

Here, the gradation pixel whose pixel attribute is “gradation” is a pixel that is included in a lot of photographs and gradations.
A pixel whose pixel value changes gradually in the periphery.
A single-color pixel having a pixel attribute of “single color” is a pixel that is largely included in a line drawing, and is a pixel whose pixel value hardly changes in the periphery.

Although the local area determination processing is performed to obtain the pixel attribute for each pixel, the attribute of the block may be determined in units of blocks such as 3 × 3. In this case, by replacing the average value of the pixels included in the block with the above-described luminance value, the flowchart shown in FIG. 10 can be applied as it is.

The relationship between threshold values TH1 and TH2 is that threshold value TH1> TH2. Therefore, a pixel whose pixel attribute is determined to be “edge” has a larger amount of change in luminance between adjacent pixels than a pixel whose pixel attribute is determined to be “gradation”. Similarly, the amount of change in luminance between a pixel whose pixel attribute is determined to be “gradation” and an adjacent pixel is larger than the amount of change in luminance of a pixel whose pixel attribute is determined to be “monochrome”.

In the local area discriminating process according to the present embodiment, discrimination is performed using the maximum value of a change in luminance value (change in pixel value) between a pixel to be processed and an adjacent pixel. The maximum value of the color distance of the pixel may be used.
As the color distance, a distance in an arbitrary color space such as an RGB space, a Lab space, and an HSL space can be used. Further, instead of using the maximum value of the amount of change in luminance or the color distance, another method can be used as long as it can detect pixels that are often included in a photograph and pixels that are often included in a line drawing.

Next, the attribute determination processing will be described. FIG.
FIG. 1 is a flowchart showing the flow of the attribute determination process performed in step S04 of FIG. Referring to FIG. 11, the number of gradation pixels Pa whose pixel attribute is “gradation” included in the area is counted (step S31), and the number Pb of single-color pixels whose image attribute is “monochrome” included in the area is counted. (Step S32).

Then, the number Pa of gradation pixels and the number Pb of single-color pixels
Is used to calculate the gradient T (step S33).
The gradation is a value that increases as the ratio of the gradation pixel to the entire region increases and as the ratio of the monochrome pixel to the entire region decreases. The gradient T is calculated based on the following equation.

Gradient T = (K1 × Pa−K2 × Pb) /
Total number of pixels in area S Here, K1 and K2 are predetermined constants. The formula for calculating the gradation T is not limited to this, and the higher the ratio of the number Pa of gradation pixels included in the region and the smaller the ratio of the number Pb of single color pixels included in the region, the higher the value may be. This gradient T is
This is a value indicating the feature of the region.

Next, a threshold value for determining the attribute of the area is determined by the following formula (step S34).

THA = A1 / (S + A2) (1) THB = THA × (1-A3 / (S + A3)) (2) THC = THA × (1-A4 / (S + A4)) (3) S is the total number of pixels in the area, A1 to A4 are predetermined constants, and A3 <A4. THA, THB,
THC is a threshold value for distinguishing between a photograph attribute and a weakly-colored line image, a weakly-colored line image and a middle-colored line image, and a threshold value for distinguishing between a middle-colored line image and a strongly-decreased color line image, and THA>THB> THC.

Then, the gradient T is compared with the threshold value THA (step S35). The gradient T is the threshold value THA
If it is larger, the process proceeds to step S36; otherwise, the process proceeds to step S37. In step S36, the process is terminated with the attribute of the area as "photograph".

In step S37, the gradient T is compared with a threshold value THB. If the gradient T is larger than the threshold value THB, the process proceeds to step S38; otherwise, the process proceeds to step S39. In step S38, the area attribute is set to "lightly reduced color line drawing", and the process ends.

In step S39, the gradient T is compared with a threshold value THC. If the gradient T is larger than the threshold value THC, the process proceeds to step S40; otherwise, the process proceeds to step S41. In step S40, the area attribute is set to “medium-colored line drawing”, and the process ends. In step S41, the area attribute is set to "strongly reduced color line drawing", and the process ends.

The processing from step S31 to step S33 is performed by the feature amount detection unit 201, and the processing in step S34
The processing from step S41 to step S41 is performed by the attribute determining unit 203.

Here, the weakly-colored line drawing, the medium-colored line drawing, and the strongly-colored line drawing are all included in the line drawing attribute, but the degree of the color reduction processing performed by the adaptive correction section 114 is different. The image having the line drawing attribute is subjected to the color reduction processing by the adaptive correction unit 114, and the color reduction processing is performed by changing the degree of the color reduction among the line drawing attributes. That is, an image having a line drawing attribute whose area attribute is set to a weakly reduced color line drawing is subjected to the color reduction processing at a low degree of the color reduction processing. An image having a line drawing attribute whose region attribute is a strongly reduced color line drawing is subjected to a color reduction process with a high degree of the color reduction process. In this case, the number of colors to be reduced increases.

FIG. 12 is a first diagram showing the relationship between the area size and the gradient and the area attribute. Referring to FIG. 12, the horizontal axis represents the size of the region, and the vertical axis represents the gradient. THA is represented by a line where the gradient decreases as the region size increases. The area above the threshold value THA is a photograph attribute, and the area below the threshold value THA is a line drawing attribute. Therefore, the larger the area size, the more easily it is determined to be a photograph attribute. This is because if the gradation is high and the region size is large, it is highly possible that the attribute is a photograph attribute.

In a portion below the THA, the distance between the THB and the THB increases as the region size decreases. Therefore, a region having the line drawing attribute is more likely to be determined as a weakly reduced line drawing as the region size becomes smaller. Also,
The weakly colored line drawing area is provided immediately below the photographic area. This is because it is preferable in terms of image quality to set the color reduction degree as low as possible when the gradation of the line image attribute area is high.

As for the threshold value THC, the ratio of the distance between the X-axis and THC to the distance between the X-axis and THA increases as the region size increases. Therefore, a region determined to be a line drawing attribute other than a photograph attribute is more likely to be determined as a strongly reduced color line drawing as the region size increases. This is for the following reason. When the area size is large, a lot of time is required to perform the color reduction processing. In this case, if the number of colors included in the processed image is large, more time is required. Therefore, if the color reduction processing is performed, it is desirable to increase the degree of color reduction and coarsely reduce the color in order to improve the processing speed. . By doing so, the time of the color reduction processing can be shortened.

FIG. 13 is a flowchart showing a flow of the image processing for each area performed in step S05 of FIG. Referring to FIG. 13, in the image processing for each area, it is determined whether or not the area attribute is “photo” (step S51). If the area attribute is a photograph, the process proceeds to step S52; otherwise, the process proceeds to step S53. Step S52
Then, the compression process is performed by the JPEG method on the region of the photograph attribute whose region attribute is set to “photo”, and the process ends.

In the step S53, it is determined whether or not the area attribute is "lightly reduced color line drawing". If it is determined that the area attribute is “weakly-colored line drawing”, the process proceeds to step S54; otherwise, the process proceeds to step S55. In step S54,
The color reduction processing is performed by reducing the degree of color reduction and increasing the number of colors of the processed image. Then, the process proceeds to step S58.

In step S55, it is determined whether or not the area attribute is "middle-colored line image". Area attribute is `` Medium color line drawing ''
If determined to be, the process proceeds to step S56; otherwise, the process proceeds to step S57. In step S56, a color reduction process is performed in which the number of colors of the image after the color reduction is set to a medium level with the color reduction degree being set to a medium level. Then, the process proceeds to step S58.

In step S57, color reduction processing is performed to reduce the number of colors of the image after the color reduction processing with the color reduction degree increased. Then, the process proceeds to step S58. Step S58
Then, the image that has been subjected to the color reduction processing is compressed by the PNG method,
The process ends.

For the color reduction processing, the existing first color reduction method for equally dividing the RGB space is used. In this color reduction processing, the degree of the color reduction processing is changed, and in order to perform the strong color reduction processing with a large degree, the medium color reduction processing with a medium degree, and the weak color reduction processing with a small degree, the number of divisions into which the RGB space is equally divided is determined. Strong color reduction processing that increases the number of divisions by changing
It is possible to perform reduced weak color reduction processing and intermediate color reduction processing with an intermediate number between them. In the color reduction processing, there is a second color reduction method in which color assignment is changed according to the frequency of each pixel value using a histogram. In the second color reduction method, the degree of the color reduction processing is changed by changing the number of colors to be assigned, so that the number of allocated colors is reduced, the number of allocated colors is reduced, the number of colors is reduced, and the number of colors is reduced. Processing can be performed.

The degree of the color reduction processing may be changed in accordance with the above-mentioned gradation. In this case, the number of divisions of the color space in the first color reduction method, the number of colors to be allocated in the second color reduction method, or a threshold value for grouping close colors in the color space, etc., are used as a function of the gradient. Continuously change the degree of color reduction. When the color reduction degree is changed in accordance with the gradation in this way, it is not necessary to determine whether the attribute of the area is a photograph, a weakly-colored line drawing, a medium-colored line drawing, or a strongly-colored line drawing. When the degree of color reduction is 0, it can be determined as a photograph attribute. When the degree of color reduction is not 0, color reduction processing may be performed according to the degree of color reduction.

FIG. 14 is a second diagram showing the relationship between the area size and the gradient and the area attribute. Referring to FIG. 14, in a region having a region attribute of “photo”, the larger the region size, the larger the possible value of the gradient is. Therefore, as the region size increases, the region attribute is more likely to be determined as a photograph.

In a region of a weakly-colored line image having a region attribute, the smaller the region size, the larger the value that the gradient can take.
Therefore, of the regions whose attributes are determined to be line drawing attributes,
The smaller the area size, the easier it is to discriminate a weak color-reduced line image in which the degree of color reduction is reduced.

Further, in a strongly reduced color line drawing in a region having a line drawing attribute in which a region attribute is a combination of a strongly reduced color drawing, a middle reduced color drawing, and a weakly reduced color drawing, the proportion of the gradient increases as the region size increases. Accordingly, a region whose region attribute is the line drawing attribute is likely to be determined as a strongly reduced color line drawing as the region size increases.

As described above, in the digital camera 1 according to the present embodiment, since the attribute of the area is determined based on the area size and the gradient, the line drawing area requiring the color reduction processing and the color reduction processing are not required. The determination as to the photographic area can be made in consideration of the processing speed of the color reduction processing. As a result, the digital camera 1 with an improved processing speed can be provided.

Further, even when the area attribute is determined to be a line drawing attribute requiring color reduction processing, the color reduction degree indicating the degree of the color reduction processing is changed according to the area size and the gradation. In the color reduction processing, the processing speed increases as the degree of color reduction increases, and the processing speed decreases as the degree of color reduction decreases. The larger the degree of color reduction, the greater the effect on image quality, and the smaller the degree of color reduction, the smaller the effect on image quality. In particular, in an area in which the gradation changes gradually but it is difficult to determine whether the attribute is a photograph attribute or a line drawing attribute, when the area is determined to be a line drawing attribute, the degree of color reduction is reduced. It can be prevented from lowering. Also,
The larger the area size, the greater the ratio of being determined to be a strongly reduced color line drawing with a large degree of color reduction, so that even when the area attribute is determined to be a line drawing attribute, the time of the color reduction processing performed on the area is reduced. . As a result, the degree of color reduction when performing the color reduction processing can be determined in consideration of the time of the color reduction processing and the image quality of the image after the color reduction processing.

In the present embodiment, the color reduction processing is performed by the hardware configuration shown in FIG. 3. However, the flowcharts shown in FIGS. 4, 5, 11, and 13 are described in a program, and The program may be executed by the CPU 100. In this case, the program is stored in the CD-ROM 124, and the stored program is read by the external storage device 122.

The embodiments disclosed this time are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a relationship between a digital camera 1 and a document 2 to be imaged according to one embodiment of the present invention.

FIG. 2 is a perspective view of the digital camera 1 as viewed from a lens side.

FIG. 3 is a block diagram showing a circuit configuration of the digital camera 1.

FIG. 4 is a flowchart showing a flow of image processing performed by the digital camera 1.

FIG. 5 is a flowchart showing a flow of a region dividing process performed in step S02 of FIG. 4;

FIG. 6 is a diagram showing an example of an image stored in a RAM 108.

FIG. 7 is a diagram showing an expanded image 160 obtained by expanding the image 150.

FIG. 8 is a diagram showing a state where circumscribed rectangle processing is performed on an expanded image 160;

FIG. 9 is a block diagram illustrating a detailed configuration of an area determination unit 112.

FIG. 10 is a flowchart showing the flow of a local area determination process performed in step S03 of FIG.

FIG. 11 is a flowchart showing a flow of an attribute determination process performed in step S04 of FIG.

FIG. 12 is a first diagram illustrating a relationship between a region size and a gradient and a region attribute.

FIG. 13 is a flowchart showing a flow of region-based image processing performed in step S05 of FIG. 4;

FIG. 14 is a second diagram illustrating a relationship between a region size and a gradient and a region attribute.

[Explanation of symbols]

1 digital camera, 100 CPU, 104 CC
D, 108 RAM, 110 area dividing section, 112 area determining section, 114 adaptive correcting section, 116 compressing section, 11
8 Image synthesis section, 120 card memory section, 122 external storage device, 124 CD-ROM.

Continued on the front page F term (reference) 5B057 AA20 CA01 CC01 CE11 DA08 DA20 DB05 DB06 DC04 DC23 5C077 LL18 LL19 MP08 PP27 PP28 PP32 PP37 PP47 PP60 PP65 PQ08 PQ20 RR21 TT09 5L096 AA02 BA07 CA02 EA02 EA13 FA19 FA44 GA45 FA45 9A001 HH23 KK42

Claims (11)

[Claims] 1. A first method for detecting a size of an input image.
Detection means, second detection means for detecting feature data representing characteristics of the image based on pixel values of the image, size data representing the size from the first detection means, and the second detection means And an attribute determining means for determining an attribute corresponding to the image from among a plurality of predetermined attributes according to the characteristic data from the image processing apparatus. 2. The attribute determining means determines the attribute according to a reference value determined by the size of the size data and the feature data, and the reference value is a reciprocal relation between the size of the size data and the size of the feature data. 2. The image processing apparatus according to claim 1, wherein the image processing apparatus includes a reference value. 3. Limiting means for executing limiting processing for limiting a pixel value to the image, and size data representing a size from the first detecting means and feature data from the second detecting means. Therefore, the image processing apparatus further comprises a degree determination unit that determines a degree of the restriction processing corresponding to the image, wherein the restriction processing unit executes the restriction processing according to the degree determined by the degree determination unit. The image processing apparatus according to claim 1. 4. A restriction processing unit for performing a restriction process for restricting a pixel value for an input image, a first detection unit for detecting a size of the image, and the image based on a pixel value of the image. Second detecting means for detecting characteristic data representing the characteristic of the image, and the size corresponding to the image in accordance with the size data representing the size from the first detecting means and the characteristic data from the second detecting means. An image processing apparatus comprising: a degree determination unit that determines a degree of processing; wherein the restriction processing unit executes the restriction processing according to the degree determined by the degree determination unit. 5. The image processing apparatus according to claim 3, wherein the degree is easily determined to be a larger value as the size data is larger. 6. The image processing apparatus according to claim 3, wherein the degree is determined to be smaller as the size data is smaller. 7. A restriction processing unit for performing a restriction process for restricting a pixel value for an input image; a detection unit for detecting characteristic data representing a characteristic of the image based on a pixel value of the image; And a degree determining unit that determines a degree of the limiting process corresponding to the image according to the characteristic data from the detecting unit, wherein the limiting processing unit performs the limiting process according to the degree determined by the degree determining unit. And an image processing device. 8. A first method for detecting a size of an input image.
A second detection step of detecting feature data representing a feature of the image based on a pixel value of the image; a size data representing a size detected by the first detection step; An attribute determining step of determining an attribute corresponding to the image from among a plurality of predetermined attributes according to the feature data detected by the detecting step. 9. An image processing method for executing a restriction process for restricting a pixel value for an input image, comprising: a first detection step of detecting a size of the image; and a pixel value of the image. A second detection step of detecting feature data representing a feature of the image based on the size data representing the size detected by the first detection step and the feature data detected by the second detection step. A degree determination step of determining a degree of the restriction processing corresponding to the image; and a restriction processing step of executing the restriction processing on the image according to the degree determined by the degree determination step. Processing method. 10. A first detection step for detecting a size of an input image, a second detection step for detecting feature data representing a feature of the image based on a pixel value of the image, and the first detection step. An attribute determining step of determining an attribute corresponding to the image from among a plurality of predetermined attributes in accordance with size data representing the size detected by the detecting step and feature data detected by the second detecting step; And a computer-readable recording medium storing an image processing program for causing a computer to execute the program. 11. A computer-readable recording medium recording an image processing program for executing a restriction process for restricting a pixel value to an image, wherein a first detection for detecting a size of the input image is performed. A second detection step of detecting feature data representing a feature of the image based on pixel values of the image; a size data representing a size detected by the first detection step; and the second detection step Determining a degree of the restriction processing corresponding to the image according to the characteristic data detected by the step (c), and executing the restriction processing on the image according to the degree determined by the degree determination step. Computer-readable recording of an image processing program for causing a computer to execute the restriction processing step Capacity recording medium.