JP2007272457A - Image processing method and apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing method and apparatus capable of performing an appropriate vectorizing process matching the kind of image by determining whether or not a clip art image has features such as edges or gradations. <P>SOLUTION: A document image including a clip art image is input to the image processing apparatus via an input part 11 and vectorized. To do this, the input document image is divided into regions by a region separating part 12 and the clip art image is selected by a clip art image selecting part 13. Then a clip art image kind identifying part 14 identifies the kind of the clip art image according to whether or not there are edges or gradations, and a clip art image region dividing part 15 further divides the clip art image into regions according to the kind of the image identified. Then a clip art image vector converting part 16 converts the divided clip art image into vector data. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an image processing method and an image processing apparatus that divide an image obtained by scanning a paper document and vectorize the image for each region.

  In recent years, computerization of information has progressed, and systems that do not hold paper documents as they are, but store them electronically and transmit the electronic data to other devices have become widespread. Further, the documents to be digitized are not limited to black and white binary images, but are expanding to electronic documents such as full-color (multi-value) documents.

  Further, the target electronic document is not limited to a document obtained by scanning a document on paper with a scanner or the like into image data. For example, an electronic document is obtained by separating a region of a document image, performing character recognition processing on a character region and converting it into a character code string, converting a photo region into vector data of a contour line, etc. Data converted into more advanced information is included (see Patent Document 1).

Conventionally, image vectorization processing is performed as follows. First, an image input in full color is converted into a binary image, then a contour line and a center line are extracted from the binary image, and color information of the obtained line and the original image is converted into vector data.
JP 2004-265384 A

  On the other hand, among the vectorized images as described above, there are an image obtained by scanning an original image created by an illustration image or graphic creation software, even if it is a full-color image. These images have features such as clear outlines of objects and limited appearance colors compared to natural images such as photographs. Hereinafter, such an image is referred to as a “clip art image”. For such a clip art image, it is considered effective to perform a vectorization process based on a region division method according to the characteristics of the clip art image.

  However, none of the conventional techniques can perform vectorization processing by automatically determining the type of image (for example, whether there is a border or whether there is a gradation). Therefore, for example, if the same processing is applied to different types of images, an appropriate vectorization result cannot be obtained, and processing is wasted.

  The present invention has been made in view of such circumstances, and determines whether or not a clip art image has features such as edges and gradation, and performs appropriate vectorization processing according to the type of image. An object of the present invention is to provide an image processing method and an image processing apparatus.

In order to solve the above problems, the present invention is an image processing method in an image processing apparatus for inputting and vectorizing a document image including a clip art image,
A selection step of selecting the clipart image by dividing the document image into regions;
A discriminating step for discriminating the type of the clip art image;
An area dividing step of further dividing the clip art image according to the type of the determined image;
A conversion step of converting the segmented clip art image into vector data.

In order to solve the above problems, the present invention is an image processing apparatus for inputting and vectorizing a document image including a clip art image,
Selection means for selecting the clipart image by dividing the document image into regions;
Discriminating means for discriminating the type of the clip art image;
Area dividing means for further dividing the clip art image according to the determined type of image;
Converting means for converting the segmented clip art image into vector data.

  According to the present invention, it is possible to determine whether or not a clip art image has features such as edges and gradation, and to perform appropriate vectorization processing according to the type of image.

  Hereinafter, a vectorization process of image data using an image processing apparatus according to an embodiment of the present invention will be described in detail with reference to the drawings.

<Device configuration>
FIG. 1 is a block diagram showing a configuration of an image processing apparatus having a function of performing vectorization processing based on region division according to an embodiment of the present invention. In FIG. 1, an input unit 11 inputs paper information as a color document image by scanning. The area dividing unit 12 separates the color document image into a plurality of types of areas including a photographic area. Further, the clip art image selection unit 13 selects a clip art image from each of the separated areas. Furthermore, the clip art image type determination unit 14 determines the type of the clip art image. Furthermore, the clip art image area dividing unit 15 divides the clip art image area according to the discriminated image type. Furthermore, the clip art image vector conversion unit 16 converts the clip art image into vector data from the region division result in the clip art image region division unit 15.
Convert to data.

  FIG. 14 is a block diagram showing a main part configuration of a digital multi-function peripheral (MFP) which is an embodiment realizing the image processing apparatus shown in FIG. In this embodiment, a digital multifunction peripheral (MFP) having a scanner function and a printer function is used as the image processing apparatus. However, a system in which a general-purpose scanner and a personal computer are connected is used as the image processing apparatus. Also good.

  As shown in FIG. 14, the MFP includes a controller unit 2000 that functions as an image processing apparatus. The controller unit 2000 connects a scanner 2070 as an image input device and a printer 2095 as an image output device. Then, control is performed to realize a copy function in which image data read from the original image by the scanner 2070 is printed out by the printer 2095. Further, the controller unit 2000 performs control for inputting / outputting pattern images, device information, and the like to / from other apparatuses via the LAN 1006 and the public line (WAN) 1008.

  As shown in FIG. 14, the controller unit 2000 has a CPU 2001. The CPU 2001 starts up an operation system (OS) by a boot program stored in the ROM 2003. Various processes are executed by executing application programs stored in an HDD (Hard Disk Drive) 2004 on the OS. A RAM 2002 is used as a work area for the CPU 2001. The RAM 2002 provides not only a work area for the CPU 2001 but also an image memory area for temporarily storing image data. The HDD 2004 stores image data together with the application program.

  A ROM 2003 and a RAM 2002 are connected to the CPU 2001 via a system bus 2007. Further, an operation unit I / F (operation unit interface) 2006, a network I / F (network interface) 2010, a modem 2050, and an image bus I / F (image bus interface) 2005 are connected.

  An operation unit I / F 2006 is an interface with an operation unit 2012 having a touch panel, and outputs image data to be displayed on the operation unit 2012 to the operation unit 2012. Further, the operation unit I / F 2006 sends information input by the user through the operation unit 2012 to the CPU 2001.

  The network I / F 2010 is connected to the LAN 1006 and inputs / outputs information to / from each device connected to the LAN 1006 via the LAN 1006. The modem 2050 is connected to the public line 1008 and inputs / outputs information to / from other devices via the public line 1008.

  An image bus I / F 2005 is a bus bridge for connecting a system bus 2007 and an image bus 2008 for transferring image data at high speed and converting a data structure. The image bus 2008 includes a PCI bus or IEEE1394. On the image bus 2008, a raster image processor (RIP) 2060, a device I / F 2020, a scanner image processing unit 2080, a printer image processing unit 2090, an image rotation unit 2030, a thumbnail creation unit 2035, and an image compression unit 2040 are provided. Yes.

  The RIP 2060 is a processor that develops a PDL code into a bitmap image. A scanner 2070 and a printer 2095 are connected to the device I / F 2020 and perform synchronous / asynchronous conversion of image data. A scanner image processing unit 2080 performs correction, processing, and editing processing on input image data. A printer image processing unit 2090 performs printer correction, resolution conversion, and the like on print output image data. The image rotation unit 2030 rotates image data. The image compression unit 2040 compresses the multi-value image data into JPEG data and the binary image data into data such as JBIG, MMR, and MH, and also performs decompression processing.

<Outline of vectorization processing based on area division>
FIG. 2 is a flowchart for explaining an outline of vectorization processing based on clip art region segmentation according to an embodiment of the present invention.

  First, paper information is input from the scanner at the input unit 11 to obtain color document image data (step S11). Next, the area separation unit 12 converts the input color document image into binary image data, and the binary image data is separated into a plurality of types of areas such as characters, photographs, and tables (step S12). As an example of realizing this region separation processing, the region division technique described in US Pat. No. 5,680,478 can be used. In this publication, “Method and Apparatus for character recognition (Shin-YwanWang et al./Canon K.K.)” is described. Further, the clip art image selection unit 13 selects a clip art image from the region separated in the previous process (step S13).

  Next, the clipart image type discriminating unit 14 discriminates the type of the clip art image, for example, whether there is an edge or whether there is a gradation (step S14). The details of the clipart image type discrimination process will be described later.

  Next, the clipart image region dividing unit 15 determines the type of region division for an image determined with or without a border based on the determination result of the type of clip art image (step S15). As a result, when it is determined that the clip art image has no border (Yes), the clip art image without border is divided (step S16).

  On the other hand, if it is determined in step S15 that there is an edge (No), it is determined whether or not the clip art image is an image having no further gradation (step S17). As a result, if it is determined that there is no gradation (Yes), the clip art image with a bordered gradation is divided into regions. The details of the area dividing process of the clip art image without borders (step S16), the area dividing process of the clip art image with edges (step S18), and the area dividing process of the clip art image with gradation (step S19) will be described later.

  After the region dividing process in steps S16, S18, and S19, the vectorization unit 16 converts each divided region into vector data based on the outline and the color inside the region (step S20). As a technique for realizing this vectorization processing, for example, there is a technique of vectorizing by tracing the contour line of a binary image of Japanese Patent No. 2885999 and selecting its coordinate vector. Note that this technique is also used for vectorization processing in the present embodiment.

<Clip art image selection example>
FIG. 3 is a diagram showing an example in which a clip art image is selected from a document image in image processing according to an embodiment of the present invention. FIG. 3 shows a state in which a photographic area 31, a text area 32, and a clipart area 33 are separated as rectangular areas from one document image by using the area separation method described above.

<Image type discrimination processing>
FIG. 4 is a flowchart for explaining details of the determination processing for determining whether or not the image has a border in step S14 of FIG.

  First, an edge is extracted from the clip art image (step S1401). Then, a histogram distribution of edge strength is obtained (step S1402). In the present embodiment, as an example, when the threshold value of edge strength is 0, 40, 80, 120, or 160, the number of pixels having edge strengths equal to or higher than the threshold value is statistically represented as a representative value. Then, it is determined whether or not the histogram distribution is gradually decreasing (step S1403). As a result, when the number of pixels having edge strength equal to or higher than the threshold value gradually decreases as the edge strength threshold value is increased (Yes), it is determined that there is an edge (step S1404). On the other hand, when it decreases suddenly (No), it is determined that there is no edge (step S1405).

  FIG. 5 is a flowchart for explaining the details of the determination processing for determining whether or not there is a gradation in the image in step S14 of FIG.

  First, color conversion from the RGB color space to the HSV color space is performed (step S1411). Next, the number of H values is statistics (step S1412), and the number of S values is statistics (step S1413). Then, it is determined whether the number of H values is small and the number of S values is large (step S1414). As a result, when the number of H values is small and the number of S values is large (Yes), it is determined that there is a gradation (step S1415). On the other hand, in other cases (No), it is determined that there is no gradation (step S1416).

<Area segmentation processing for borderless clip art images>
FIG. 6 is a flowchart for explaining details of the region dividing process of the borderless clipart image in step S16 of FIG.

  First, clustering processing is performed based on the color characteristics of the pixels, and the image is divided into clusters (step S1601). Specifically, the first cluster is generated from the start pixel subjected to raster scanning. Then, the similarity between all the clusters is obtained for the next pixel. The higher the similarity, the shorter the distance between the pixel and the cluster, that is, the closer the feature. Here, RGB values are used for similar calculations, but information on other color spaces or information other than color can also be used as feature amounts. Then, the highest similarity and the cluster number corresponding to this similarity are recorded, and this similarity is compared with a preset threshold. If the result is higher than the threshold value, the target pixel belongs to the recorded cluster. On the other hand, if it is lower than the threshold, a new cluster is generated by the target pixel. When the above processing is completed for all pixels, the region division processing is terminated.

  In step S1602, the clusters divided in step S1601 are integrated based on similarity. Specifically, first, a target value for the number of regions to be separated is input. This target value is a measure of how many colors are separated in this embodiment. Then, the number of current clusters is counted and compared with the target value of the number of regions. As a result, if the number of clusters is greater than the target value, cluster integration is performed. For the integration, the similarity between the clusters is calculated, and the two clusters having the highest similarity are integrated into one. This cluster integration process is executed until the number of clusters becomes smaller than the target value.

  In step S1603, the result of region integration is labeled to determine the noise region. In step S1604, it is determined whether the area is a noise area based on the size of each label area. As a result, if the label area is small to some extent (Yes), it is determined as a noise area and the process proceeds to step S1605. In step S1605, a clustering process is performed in which the noise pixels included in the noise region determined in step S1604 are reassigned to the region with the highest similarity based on the similarity between adjacent regions, and step S1606 is performed. move on. On the other hand, if it is determined in step S1604 that the region is not a noise region (No), the process proceeds to step S1606.

  In step S1606, it is determined whether or not processing is completed for all label regions. If there is an object to be processed (No), the process returns to step S1604 to repeat the noise area determination process and the noise area reprocessing. On the other hand, if there is no processing target (Yes), the noise processing is terminated.

<Example of noise>
FIG. 7 is a diagram illustrating an example of noise handled in image processing according to an embodiment of the present invention. In FIG. 7, a cluster 61 and a cluster 62 are two examples of clusters selected as representatives from the clusters after the area division process (step S1601) and the area integration process (step S1602). The noise in these clusters shown in FIG. 7 is dealt with by the above noise determination processing and noise reprocessing.

<Example of vectorization based on area division of borderless clip art image>
FIG. 8 is a diagram illustrating an example of vectorization by a series of processes of area division, area integration, noise area determination, and noise area reprocessing for a borderless clipart image according to an embodiment of the present invention. In FIG. 8, 81 is a clip art image divided into regions. Reference numeral 82 denotes an example of a region division result. That is, the clip art image 81 is displayed in the region division result 82 when the target value of the number of regions to be divided is set to 16, for example, by the above-described series of processing of region division, region integration, noise determination, and noise removal. The cluster is divided into 16 clusters as shown.

  As examples of cluster outlines and internal color information necessary for vectorization processing, FIG. 8 shows a cluster 83, outline 84, and internal color information 85. A result of converting the region division result 82 into vector data based on the above information is a vector image 86. Since the file size of the vector image 86 is 24 Kbytes, and the file size of the original clip art image 81 is 2739 Kbytes, it is reduced to 1/100 or less by vectorization. This can cope with noise. Further, processing such as painting of the internal color of each cluster can be performed using each cluster 82 of the vector image 86 as a component.

<Division processing of clip art image with border>
FIG. 9 is a flowchart for explaining the details of the region dividing process of the clipped image with the border in step S18 of FIG.

  First, an edge is extracted from the edge clip art image (step S1801), and then an edge cluster is formed by pixels whose edge strength is equal to or greater than a set threshold value (step S1802).

  Then, the pixels other than the edge cluster are processed in the same manner as the processing of the borderless clipart image. That is, a series of processes including an area division process (S1601), an area integration process (S1602), a labeling process (S1603), a noise area determination process (S1604), and a noise area reprocessing (S1605) are performed.

  In step S1803, an edge cluster determination process is performed to determine whether there is a cluster including edge information other than the edge cluster formed first. In this process, for each cluster other than the first edge cluster, the edge ratio, that is, the ratio of the number of pixels whose edge intensity is not 0 to the number of pixels in the cluster is calculated for each cluster. As a result, when the edge rate is high to some extent, the cluster is determined as an edge cluster. In step S1804, this cluster and the first formed edge cluster are integrated.

<Example of edge cluster>
FIG. 10 is a diagram illustrating an example in which a divided cluster is integrated into an edge cluster determined as an edge cluster according to an embodiment of the present invention. In FIG. 10, reference numeral 1711 denotes an edge cluster formed first by the edge cluster formation process, and reference numeral 1712 denotes a cluster determined as an edge cluster by the edge cluster determination process. Reference numeral 1713 denotes an edge cluster result obtained by integrating these edge clusters. As described above, in this embodiment, an edged image is handled by edge cluster formation processing, edge cluster determination processing, and edge cluster integration processing.

<Example of vectorization based on segmentation of clipped image with border>
FIG. 11 shows an example of vectorization by a series of processing of edge extraction, edge cluster generation, region division, region integration, noise region determination, noise region reprocessing, edge cluster determination, and edge cluster integration for a clipped image with a border. FIG.

  In FIG. 11, the clipped image 1721 with a border is divided into clusters shown in the region division result 1722 when the target value of the number of regions to be divided is designated as 16. The vector image 1723 is a result of converting the region division result 1722 into vector data. Since the file size of the vector image 1723 is 45 Kbytes and the file size of the original clip art image 1721 is 2739 Kbytes, the vectorization reduces the size to 1/50 or less. Thereby, the edge information can be suppressed to one cluster.

<Division processing of clip art image with gradation>
FIG. 12 is a flowchart for explaining the details of the region dividing process of the clip art image with gradation in step S19 of FIG.

  First, an edge is extracted from the edge clip art image (step S1801), and an edge cluster is formed by pixels whose edge strength is equal to or greater than a set threshold value (step S1802).

  Next, the RGB color space is converted to the HSV color space (step S1901), and the image is divided into an achromatic color portion and a chromatic color portion by the color S (step S1902). In the separation processing of the achromatic color portion and the chromatic color portion, pixels whose color S value is 0 belong to the achromatic color portion, and pixels whose color S value is not 0 belong to the chromatic color portion.

  Further, the region of the achromatic part is divided (step S1903). This processing is the same as the region division processing in step S1601, but the luminance value of the pixel is used as the feature amount, and the difference in luminance value is used as the distance between the pixel and the cluster.

  Next, the chromatic color part is divided into regions (step S1904). In this process, RGB color information of a pixel is used as the feature amount, and RGB Euclidian distance is used as the distance between the pixel and the cluster.

  Next, the achromatic portion is integrated (step S1905). This processing is the same as the region integration processing in step S1602, but the luminance value of the pixel is used as the feature amount, the difference in luminance value is used as the distance between the pixel and the cluster, and the integration condition is between clusters. Is less than a certain threshold.

  Further, the chromatic color area is integrated (step S1906). In this process, the RGB color information and hue H information of the pixel are used as the feature amount, and the difference between RGB Euclidian distance and H is used as the distance between the pixel and the cluster. As an integration condition, the RGB distance between clusters is equal to or less than the RGB threshold, and the H distance is equal to or less than the H threshold.

  Then, the following processing is performed on the pixels other than the edge cluster in the same manner as the processing of the clipped image with a border. That is, a series of processes of labeling processing in step S1603, noise region determination processing in step S1604, noise region reprocessing in step S1605, edge cluster determination processing in step S1803, and edge cluster integration processing in step S1804 are performed. Through the above processing, the result of area division is obtained.

<Example of vectorization based on area division of image with gradation>
FIG. 13 is a diagram illustrating an example of vectorization by performing various processes on a clip art image with gradation. Various processes include edge extraction, edge cluster generation, separate area division of achromatic and chromatic parts, integration of separate areas of achromatic and chromatic parts, noise area determination, noise area reprocessing, edge cluster determination A series of processing of edge cluster integration is performed.

  In FIG. 13, the clip art image 1801 with gradation is divided into each cluster of the region division result 1802 when the target value of the number of regions to be divided is designated as 10. Here, since the data size of the vector image 1803 is 56 Kbytes and the data size of the original clip art image 1801 is 2739 Kbytes, it is reduced to 1/50 or less by vectorization. As a result, the gradation can be accurately divided into regions.

  As described above, according to the present embodiment, the type of processing target image, that is, whether there is an edge and whether there is a gradation is automatically determined, and processing is performed according to each, thereby improving efficiency. It can be well vectorized.

<Other embodiments>
Although the embodiment has been described in detail above, the present invention can take an embodiment as a system, apparatus, method, program, storage medium (recording medium), or the like. Specifically, the present invention may be applied to a system composed of a plurality of devices, or may be applied to an apparatus composed of a single device.

  In the present invention, a software program (in the embodiment, a program corresponding to the flowchart shown in the drawing) that realizes the functions of the above-described embodiments is directly or remotely supplied to a system or apparatus. In addition, this includes a case where the system or the computer of the apparatus is also achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, or the like.

  Examples of the recording medium for supplying the program include the following. Floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, CD-RW, magnetic tape, nonvolatile memory card, ROM, DVD (DVD-ROM, DVD-R) .

  As another program supply method, the program can be supplied by downloading it from a homepage on the Internet to a recording medium such as a hard disk using a browser of a client computer. That is, it connects to a homepage and downloads the computer program itself of the present invention or a compressed file including an automatic installation function from the homepage. It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer is also included in the present invention.

  Further, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, and distributed to users. Then, the user who has cleared the predetermined condition is allowed to download key information for decryption from the homepage via the Internet. It is also possible to execute the encrypted program by using the key information and install the program on a computer.

  Further, the functions of the above-described embodiments are realized by the computer executing the read program. In addition, the function of the above-described embodiment can be realized by an OS running on the computer based on an instruction of the program and performing part or all of the actual processing.

  Further, the functions of the above-described embodiments are realized even after the program read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. That is, the functions of the above-described embodiments are realized by performing a part or all of the actual processing by the CPU or the like provided in the function expansion board or function expansion unit based on the instructions of the program.

It is a block diagram which shows the structure of the image processing apparatus which has a function which performs the vectorization process based on the area division based on one Embodiment of this invention. It is a flowchart for demonstrating the outline about the vectorization process based on the area | region division of the clip art image in one Embodiment of this invention. It is a figure which shows an example which selected the clip art image from the document image in the image processing which concerns on one Embodiment of this invention. 3 is a flowchart for explaining details of a determination process for determining whether or not an image has a border in step S14 of FIG. 2. It is a flowchart for demonstrating the detail of the discrimination | determination process whether an image has a gradation in step S14 of FIG. It is a flowchart for demonstrating the detail of the area | region division process of the borderless clipart image in step S16 of FIG. It is a figure which shows an example of the noise handled by the image processing which concerns on one Embodiment of this invention. It is a figure which shows an example of vectorization by a series of processes of area | region division, area | region integration, noise area determination, and noise area reprocessing with respect to the borderless clipart image in one Embodiment of this invention. It is a flowchart for demonstrating the detail of the area | region division | segmentation process of a clip art image with a border in FIG.2 S18. It is a figure which shows the example integrated into the edge cluster determined as the edge cluster from the divided | segmented cluster in one Embodiment of this invention. It is a figure which shows an example of vectorization by a series of processes of edge extraction, edge cluster generation, area division, area integration, noise area determination, noise area reprocessing, edge cluster determination, and edge cluster integration for a clipped image with a border is there. It is a flowchart for demonstrating the detail of the area | region division process of the clip art image with a gradation in step S19 of FIG. It is a figure which shows an example of vectorization by performing various processes with respect to a clipart image with gradation. FIG. 2 is a block diagram illustrating a main part configuration of a digital multifunction peripheral (MFP) that is an embodiment that realizes the image processing apparatus illustrated in FIG. 1.

Explanation of symbols

DESCRIPTION OF SYMBOLS 11 Input part 12 Area | region separation part 13 Clip art image selection part 14 Clip art image type discrimination | determination part 15 Clip art image area division part 16 Clip art image vector conversion part

Claims (11)

An image processing method in an image processing apparatus for inputting and vectorizing a document image including a clip art image,
A selection step of selecting the clipart image by dividing the document image into regions;
A discriminating step for discriminating the type of the clip art image;
An area dividing step of further dividing the clip art image according to the type of the determined image;
A conversion step of converting the segmented clip art image into vector data;
An image processing method comprising: The discrimination step is
An edge determination step for determining whether the clip art image has an edge; and
A gradation determination step for determining whether or not the clip art image has gradation;
The image processing method according to claim 1, further comprising: The edge discrimination step includes
An edge extraction step of extracting edges from the clip art image;
Determining a histogram distribution based on the extracted intensity of the edge, and determining whether the clipart image has an edge based on the histogram; and
The image processing method according to claim 2, further comprising: The determination step includes
In the histogram distribution, when the number of pixels having an edge strength equal to or higher than the threshold value gradually decreases as the edge strength threshold value is increased, the clip art image is determined to be a clip art image with a border, and the edge strength threshold value is increased. 4. The image processing method according to claim 3, wherein the clip art image is determined to be a borderless clip art image when the number of pixels having an edge strength equal to or greater than the threshold value does not gradually decrease as the clip image increases. The gradation discrimination step
A color conversion step of converting the clip art image from an RGB color space to an HSV color space;
A determination step of determining whether or not the clip art image has gradation based on information on hue H and color S in the HSV color space;
The image processing method according to claim 2, further comprising: The determination step includes
In the HSV color space, when the hue H is small and the color S appears in a wide range, the clip art image is determined as a clipped image with gradation, and when the hue S is small and the color S does not appear in a wide range. 6. The image processing method according to claim 5, wherein the clip art image is determined as a clip image without gradation. When the determination step determines that the clip art image is a borderless clip art image, the region dividing step includes:
Dividing the clip art image into a plurality of clusters based on pixel color features;
Inputting a target number of areas of the clip art image;
Integrating the plurality of clusters within a range of the target number using similarity to other clusters;
Determining a noise region from a plurality of clusters after integration;
Assigning a cluster determined to be a noise region to a cluster having a high degree of similarity;
The image processing method according to claim 4, further comprising: When it is determined by the determination step that the clip art image is a clip image with a border, the region dividing step includes:
Extracting an edge from the clip art image;
Forming an edge cluster based on the extracted intensity of the edge;
Dividing the clip art image into a plurality of clusters based on color characteristics of pixels other than edge clusters in the clip art image;
Inputting a target number of areas of the clip art image;
Integrating the plurality of clusters within a range of the target number using similarity to other clusters;
Determining a noise region from a plurality of clusters after integration;
Assigning a cluster determined to be a noise region to a cluster having a high degree of similarity;
Determining whether the cluster after allocation is an edge cluster;
Integrating a cluster determined to be an edge cluster with the edge cluster formed based on the strength of the edge;
The image processing method according to claim 4, further comprising: When the determination step determines that the clip art image is a clip art image with gradation, the region dividing step includes:
Extracting an edge from the clip art image;
Forming an edge cluster based on the extracted intensity of the edge;
Converting the clip art image from an RGB color space to an HSV color space;
Separating the clipart image into an achromatic region and a chromatic region with reference to the color S;
Dividing the achromatic color region and the chromatic color region; and
Integrating each divided region using pixel information;
Labeling the clip art image into a plurality of clusters based on color features of pixels other than the edge clusters in the clip art image;
Determining a noise region from the plurality of clusters;
Assigning a cluster determined to be a noise region to a cluster having a high degree of similarity;
Determining whether the cluster after allocation is an edge cluster;
Integrating a cluster determined to be an edge cluster with the edge cluster formed based on the strength of the edge;
The image processing method according to claim 6, further comprising: An image processing apparatus for inputting and documentizing a document image including a clip art image,
Selection means for selecting the clipart image by dividing the document image into regions;
Discriminating means for discriminating the type of the clip art image;
Area dividing means for further dividing the clip art image according to the determined type of image;
Converting means for converting the clipped art image divided into regions into vector data;
An image processing apparatus comprising:   A program for causing a computer to execute the image processing method according to claim 1.

Images