JP6798309B2 - Image processing equipment, image processing methods and programs - Google Patents

Description

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

Conventionally, there has been known a technique for reducing the file size by accurately determining the character area and increasing the compression rate for a character-only original when performing processing such as compression on an image. .. Such a technique is described in, for example, Patent Document 1.
Further, there is known a technique of extracting vertical and horizontal ruled lines from a form, extracting cells based on the extracted ruled lines, and performing character recognition for each cell. Such a technique is described in, for example, Patent Document 2.

Further, in Patent Document 3, after detecting the background level of an image obtained by digitally scanning a document, character edges of the image are detected using a plurality of parameters, and a plurality of parameters are changed according to the background level. The configuration to be used is disclosed.

However, when trying to separate the image area such as distinguishing the character area from others by the above-mentioned conventional method, when it is applied to an image scanned from a paper document having a high background level such as a newspaper, the character is displayed. There was a problem that the area was erroneously detected as a picture area. The problem related to false detection of a character area has not been sufficiently solved even by using the technique of Patent Document 3.

An object of the present invention is to solve such a problem and enable accurate image region separation. The area to be detected in the image is not limited to the character area.

In order to achieve the above object, the image processing apparatus of the present invention includes an input means for inputting image data and an extraction means for extracting a predetermined feature element from the image data input by the input means in the image processing apparatus. With respect to the predetermined feature element, the extraction means refers to a determination condition in which the condition to be satisfied by the feature element and the attribute of the region determined based on the feature element satisfying the condition in the image data are determined in advance. Based on the feature element extracted by the above and the determination condition, an attribute setting means for setting the attribute defined by the determination condition is provided in the area defined by the determination condition in the input image data . Extraction of the feature element by the extraction means and setting of the attribute for the input image data with reference to the determination condition by the attribute setting means are performed for each of the plurality of feature elements, and the attribute setting means is described. The attributes set according to the plurality of feature elements are aggregated for the plurality of feature elements, and the attributes of each part in the input image data are set.

According to the above configuration, image area separation can be performed with high accuracy.

It is a figure which shows the hardware structure of the MFP which is one Embodiment of the image processing apparatus by this invention. It is a figure which shows the functional structure of the image processing unit 200 included in the MFP shown in FIG. It is a figure which shows the functional structure of the scanner correction part 210 shown in FIG. It is a figure which shows the functional structure of the character area determination part 212 shown in FIG. 3 in detail. It is a basic flowchart of image processing by the image processing unit 200 shown in FIG. It is a flowchart of the more detailed processing procedure of the character area determination (S11) shown in FIG. It is a continuation flowchart of FIG. It is a figure for demonstrating an example which applies the process of setting the area of a ruled line to the image data which read the paper surface. It is another figure. It is yet another figure. It is a figure for demonstrating an example which applies the process of setting the area about the background ruled line to the same image data as FIG. 8A. It is another figure. It is a figure for demonstrating the process of area setting for a specific character. It is a figure for demonstrating the method of extracting the background ruled line using the judgment condition by a ruled line. It is another figure. It is a figure for demonstrating the method of extracting the candidate of the background ruled line from the result of the background extraction. It is another figure. It is a figure for demonstrating the method of summarizing the setting result of the area based on a plurality of feature elements, and finally fixing a character area.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 shows a hardware configuration of an MFP (digital multifunction device) which is an embodiment of an image processing device according to the present invention.
The MFP 100 shown in FIG. 1 is an image processing device having functions such as scanning, printing, copying, facsimile communication, and document storage.
As shown in FIG. 1, the MFP 100 includes a CPU 101, a ROM 102, a RAM 103, an HDD (hard disk drive) 104, a communication I / F (interface) 105, an operation unit 106, a display unit 107, and an engine I / F 108. Then, these are connected by the system bus 109 to form the MFP 100. Further, a scanner 120, a plotter 130, and an image processing unit 200 are connected to the engine I / F 108.

Then, the CPU 101 controls the entire MFP 100 and realizes various functions by executing a required program stored in the ROM 102 or the HDD 104 with the RAM 103 as a work area.
The ROM 102 and the HDD 104 are non-volatile storage media (storage means), and store various programs executed by the CPU 101 and various data described later.
The communication I / F 105 is an interface for communicating with an external device. It suffices to provide the one corresponding to the standard of the communication path to be used.

The operation unit 106 is an operation means for receiving an operation from the user, and is composed of various keys, buttons, a touch panel, and the like.
The display unit 107 is a presentation means for presenting the operating state, setting contents, messages, etc. of the MFP 100 to the user, and includes a liquid crystal display, a lamp, and the like.

The operation unit 106 and the display unit 107 may be externally attached. Further, the MFP 100 does not necessarily have to be directly operated by the user. The MFP 100 may accept an operation by an external device connected via the communication I / F 105, or may present information to the external device. In that case, the operation unit 106 and the display unit 107 may not be provided.

The engine I / F 108 is an interface for connecting the scanner 120, the plotter 130, and the image processing unit 200 to the system bus 109 so that they can be controlled by the CPU 101.
The scanner 120 is an image reading device that reads an image of a document and outputs the image data, and sends the read image data to the image processing unit 200.
The image processing unit 200 is an image processing means, determines the original type of the original read by the scanner 120, selects a compression ratio of an image resolution suitable for the original according to the original type, and outputs image data according to the compression ratio. Compress and output compressed image data.
The plotter 130 is an image forming means for forming an image on paper according to the image data, and can form an image based on the compressed image data output by the image processing unit 200.

FIG. 2 shows the functional configuration of the image processing unit 200. The functions of each part shown in FIG. 2 may be realized by dedicated hardware, realized by having a processor execute software, or a combination thereof. It is conceivable that the CPU 101 is responsible for some functions.
As shown in FIG. 2, the image processing unit 200 includes a scanner correction unit 210, a compression processing unit 220, a data interface unit 230, a decompression processing unit 240, and a printer correction unit 250.

Of these, the scanner correction unit 210 has a function of classifying the image data read by the scanner 120 and performing image processing. The details of the function will be described later with reference to FIG.
The compression processing unit 220 has a function of compressing the image data corrected by the scanner correction unit 210 for internal processing.
The data interface unit 230 is an HDD management interface for temporarily storing the image data compressed by the compression processing unit 220 in the HDD 104.

The stretching processing unit 240 has a function of stretching the compressed image data for internal processing in order to use it for image formation on the plotter 130.
The printer correction unit 250 has a function of sending the image data decompressed by the decompression processing unit 240 to the plotter 130 after correcting it as necessary.

Next, FIG. 3 shows the functional configuration of the scanner correction unit 210 shown in FIG.
As shown in FIG. 3, the scanner correction unit 210 includes a document type determination unit 211, a character area determination unit 212, an image area separation unit 213, a scanner γ unit 214, a filter processing unit 215, a color correction processing unit 216, and a character γ. The part 217 is provided.
Of these, the original type determination unit 211 is based on the characteristics of the original containing characters, the characteristics of the chromatic original, the characteristics of the photographic paper photograph, and the characteristics of the printed photograph, and the image data of the original whose image data to be processed is only characters. It has a function to determine whether it is image data of a color original.

The character area determination unit 212 has a function of determining the character area in the image indicated by the image data from the characteristics of the image, and in order to determine the image data that cannot be determined by the document type determination unit 211 and prevent erroneous determination. It plays a role of making a re-judgment.
The image area separation unit 213 has a function of separating the image data to be processed into a black character edge area, a color character edge area, and three other areas while referring to the determination result of the character area by the character area determination unit 212. There is.

The scanner γ unit 214 has a function of converting image data from reflectance linear data to density linear data.
The filter processing unit 215 has a function of switching between a plurality of filters and performing different filter processing on the three regions of the image data to be processed separated by the image area separation unit 213.

The color correction processing unit 216 is a means for converting RGB image data into CMYK image data other than the black character edge region.
The character γ unit 217 has a function of setting γ on a color character and a black character in a character area to emphasize the character. The image data processed by the character γ unit 217 is supplied to the compression processing unit 220.

Next, FIG. 4 shows in more detail the functional configuration of the character area determination unit 212 shown in FIG.
The character area determination unit 212 includes a ruled line area determination unit 261, a background ruled line area determination unit 262, a specific character area determination unit 263, a determination condition acquisition unit 264, a determination condition 265, a range extraction unit 266, and a determination result setting unit 267. Will be done.
The ruled line area determination unit 261 has a function of setting an area and attributes to image data based on the ruled line when an item related to the ruled line exists in the determination condition acquired by the determination condition acquisition unit 264.

The ruled line area determination unit 261 extracts vertical ruled lines and horizontal ruled lines from, for example, form data or image data read from a form printed on paper, and calculates parameters for comparing each of the extracted ruled lines with a determination condition. To do. Then, the parameters of the extracted ruled lines are collated with the determination conditions, and for each of the matching ruled lines, the area setting and the attributes are set according to the determination conditions. The attributes set in each area may be a character area, a picture area, and the like.

The background ruled line area determination unit 262 has a function of setting an area and attributes for image data based on the background ruled line when an item related to the background ruled line exists in the determination condition acquired by the determination condition acquisition unit 264. The background ruled line is a ruled line constructed by using the space of the background instead of the line.

The background ruled line area determination unit 262 extracts, for example, the background area from the form data or the image data read from the form printed on paper, and calculates the parameters for comparing the extracted background area with the determination conditions. From the beginning, only an elongated area that is a candidate for a background ruled line may be extracted. Then, the parameters of the extracted skin areas in each area are collated with the judgment conditions, and the matching skin areas are set as the skin ruled lines, and the area settings and attributes are set for the skin ruled lines in each area according to the judgment conditions. The method for extracting the background region will be described later with reference to FIGS. 12A and 12B.

The specific character area determination unit 263 has a function of setting an area and attributes to image data based on a specific character when an item related to the specific character exists in the determination condition acquired by the determination condition acquisition unit 264.
The specific character area determination unit 263 searches, for example, whether a specific character that matches the determination condition exists in the form data or the image data read from the form printed on paper. Then, for each of the extracted specific characters, the area is set and the attributes are set according to the determination conditions.

The determination condition acquisition unit 264 has a function of reading and acquiring the information registered as the determination condition 265.
The determination condition 265 defines various conditions for determining various regions including a character region from the characteristics of the original (image data) that is easily erroneously detected.
The determination is made based on a feature element such as a ruled line, a background ruled line, and a specific character that are used as a reference for the position of an area such as a character area or a pattern area. A specific example will be described later, but the determination condition 265 is data that defines a condition to be satisfied by the feature element and a region of which attribute is set at which position based on the feature element that satisfies the condition in the image data. is there.

The range extraction unit 266 is a range of various attribute areas such as a character area and a picture area in the image data from the results set by the ruled line area determination unit 261 and the background ruled line area determination unit 262 and the specific character area determination unit 263. To confirm.
The determination result setting unit 267 is a means for setting a compression rate different from that of the other portion in the range determined as the character region in the image data.
Whether or not the ruled line area determination unit 261, the background ruled line area determination unit 262, and the specific character area determination unit 263 actually perform the determination depends on which feature element condition is held as the determination condition 265. ..

Next, Tables 1 to 4 show some specific examples of the determination condition 265.
The determination condition 265 includes a list of category of feature elements shown in Table 1 and a detailed table of each category shown in Tables 2 to 4.

Each table in Tables 1 to 4 can be prioritized among the items in the table. As an example, when it is desired to make a judgment regarding a background ruled line before a judgment regarding a ruled line, by rearranging the feature elements in the table of Table 1 in the desired execution order, the judgment regarding each feature element can be performed in the execution order. Can be considered. The same applies to each determination condition in Tables 2 to 4. In Tables 1 to 4, the ID is a sequential number including the priority.

Table 1 is a table composed of the ID of the category of the feature element and the information of the type of the feature element constituting the category. It is also conceivable to use types other than the ruled lines, specific characters, and background ruled lines shown in Table 1. In that case, the character area determination unit 212 is provided with a determination unit corresponding to the type of the feature element.

Tables 2 to 4 are tables in which the details of the determination conditions for the feature elements of each category defined in Table 1 are registered. Detailed tables are created for the number of categories defined in Table 1, and Tables 2 to 4 are provided here corresponding to the three categories defined in Table 1.
In the detailed tables of Tables 2 to 4, one row of data indicates the content of one determination condition. Then, each determination condition includes information of "ID", "element condition", "range", and "determination result".

Of these, the "element condition" defines a feature element or a condition that the relationship between the feature element and another element should satisfy, and the number and contents differ depending on the category of the feature element.
"Range" indicates the position where the area is set based on the feature element. The "judgment result" indicates the attribute to be set in the set area. In the examples of Tables 2 to 4, the determination result is only characters (character area), but it goes without saying that other attributes may be set.

The table in Table 2 is a table in Table 1 and is a table of determination conditions regarding the ruled line with ID = A. Regarding the ruled line, the direction, line color, thickness, range color, and interval are provided as element conditions.
Of these, "direction" is a condition for the direction of the ruled line, and one of vertical lines, horizontal lines, and Don't care (optional) is included. "Line color" is a condition of the color of the ruled line, and although it is shown as black in Table 2, it may be color information such as the ratio or amount of RGB. The "thickness" is a condition of the thickness of the ruled line, and is shown in millimeters (mm) in the figure, but an appropriate unit such as inches (inch) or pixels can be used. It does not have to be just the thickness, as long as it is within a predetermined error range.

The "range color" means that the corresponding feature element satisfies the element condition or may include a color only when the area set according to the "range" condition based on the corresponding feature element is black and white. Is specified. The "spacing" is the spacing between the ruled lines, and is the condition of the spacing between the extracted adjacent ruled lines. The "range color" and "interval" are not conditions relating to the characteristics of the feature element itself.

For example, under the judgment condition of ID = A_001, a certain ruled line is a vertical black ruled line having a thickness of 0.1 mm and a portion sandwiched between the adjacent ruled line (based on the condition of "range"). If it is black and white, the element condition is satisfied regardless of the distance between the adjacent ruled lines. Then, in this case, an area is set in the part sandwiched between the ruled line satisfying the element condition and the adjacent ruled line (which also needs to satisfy the element condition of the same ID), and the attribute of the area is set to ". It is stipulated that it should be set to "character".

Next, the table in Table 3 is a table of determination conditions regarding a specific character with ID = B in the table in Table 1. For specific characters, symbol, range color, combination, symbol included or orientation are provided as element conditions.
The "symbol" indicates a specific character (may be a character string) used in the judgment, and is indicated by image data, a character code, a font, a size (width and height), and the like. The "range color" is the same as in Table 2. The "combination" is an item for designating an ID when it is desired to define a "range" using a feature element that satisfies the element conditions of another ID. A plurality of IDs may be specified.
"Whether to include a symbol" indicates whether or not to set the "range" to include the specific character itself. "Orientation" indicates the orientation of the character string used in the determination, and specifies either horizontal or vertical.
Of these, other than "symbol" and "direction", there are no conditions related to the characteristics of the feature element itself.

For example, under the determination condition of ID = B_001, a specific character "Å" is arranged horizontally, includes the character "Å", and from that character, the next ID = A_001 is directed toward the arrangement direction of the character string. If the area up to the ruled line of is black and white (based on the condition of "range"), the character "Å" satisfies the element condition. Then, in this case, it is stipulated that an area based on the above-mentioned "range" condition should be set and the attribute of the area should be set to "character".

Next, the table in Table 4 is a table of determination conditions regarding the background ruled line with ID = C in the table in Table 1. For the background ruled line, the direction, thickness, range color, and interval are defined as element conditions. The judgment condition regarding the background ruled line is the same as the judgment condition regarding the ruled line in Table 2 except that the element condition does not include "color".

Next, the procedure of image processing including the setting of the area and the attribute according to the determination conditions described above by the image processing unit 200 will be described with reference to the flowchart.
FIG. 5 shows the basic flow of the image processing.
When the image processing unit 200 acquires the image data from the scanner 120, the image processing unit 200 starts the process shown in the flowchart of FIG. The process related to the acquisition of the image data is the process of the input procedure. It also corresponds to the function of the input means.

Then, first, the character area determination unit 212 of the scanner correction unit 210 determines the character area in the image data and the other area (S11). The details of the character area determination in step S11 will be described later with reference to FIGS. 6 and 7. Next, each unit from the image area separation unit 213 to the character γ unit 217 of the scanner correction unit 210 sequentially performs image processing for a scanner image on the image data acquired from the scanner 120 (S12).

Next, the compression processing unit 220 performs compression processing on the image data acquired from the scanner 120 in the character area and other areas (for example, the pattern area) by an appropriate method according to the determination of the character area determination unit 212. (S13). After that, the image processing unit 200 saves the compressed image data in the HDD 104 through the data interface unit 230 (S14).

After that, when the plotter 130 prints out, the stretching processing unit 240 stretches the image saved in step S14 (S15). Next, the printer correction unit 250 performs image processing on the expanded image data according to the characteristics of the plotter 130, and also performs image processing for emphasizing the characters in the character area according to the determination result in step S11. , The processed image data is output (S16).
This completes the process of FIG. The reason why the special image processing is performed on the characters in step S16 is that the edges of the characters are thinned by performing the processing of steps S12 to S15, and the original with a high background level is set off. , To improve the difficulty of reading characters.

Next, FIG. 6 shows a flowchart of a more detailed processing procedure for determining the character area in step S11 of FIG. The process shown in this flowchart corresponds to the function of the character area determination unit 212 shown in FIG.
In the process of FIG. 6, first, the character area determination unit 212 refers to the category list (Table 1) of the determination condition 265 acquired by the determination condition acquisition unit 264, and whether or not the determination condition 265 has a condition related to the ruled line. Judgment (S21). Here, if there is, the ruled line area determination unit 261 extracts all the ruled lines from the image data (S22) and sequentially processes each determination condition (see Table 2) regarding the ruled lines in order to consider the setting of the area for the ruled lines. The processing of steps S23 to S25 is repeated while targeting.

That is, the ruled line area determination unit 261 first acquires, among the ruled lines extracted in step S22, those that meet the element conditions in the determination conditions to be processed (S23). At this time, the ruled line area determination unit 261 also retains the information of the ruled line that has not been acquired.
Then, the ruled line area determination unit 261 sets an area based on the ruled line and its attributes in the image data according to the ruled line acquired in step S23 and the determination condition of the processing target (S24). For example, when the determination condition of ID = A_001 is used, an area is set in the portion sandwiched between the ruled lines satisfying the element conditions, and the attribute of the area is set to "character". Finally, the ruled line that matches the element condition is saved in association with the determination condition of the processing target (S25). This preservation is performed for reference in the processing related to another feature element.

Further, after the end of the loop in steps S22 to S25, or if NO in step S21, the process proceeds to step S31. Here, the character area determination unit 212 determines whether or not the determination condition 265 acquired by the determination condition acquisition unit 264 includes a condition related to the background ruled line (S31). In the example of FIG. 6, unlike the data in Table 1, the determination regarding the background ruled line is performed second.

If Yes in step S31, the background ruled line area determination unit 262 extracts all the background ruled lines from the image data (S32), and each determination condition (table) regarding the background ruled line, in order to examine the setting of the area for the background ruled line. 4) is sequentially targeted for processing, and the processing of steps S33 to S35 is repeated.

That is, the background ruled line area determination unit 262 first acquires the background ruled line extracted in step S32 that meets the element conditions in the determination conditions to be processed (S33). At this time, the background ruled line area determination unit 262 also retains the information of the background ruled line that has not been acquired.
Then, the background ruled line area determination unit 262 sets an area based on the background ruled line and its attributes in the image data according to the background ruled line acquired in step S33 and the determination condition of the processing target (S34). For example, when the determination condition of ID = C_001 is used, an area is set in the portion sandwiched between the background ruled lines satisfying the element conditions, and the attribute of the area is set to "character". Finally, the background ruled line that matches the element condition is saved in association with the determination condition of the processing target (S35). This preservation is performed for reference in the processing related to another feature element.

Further, after the end of the loop in steps S32 to S35, or when NO in step S31, the process proceeds to step S41 in FIG. 7. Here, the character area determination unit 212 determines whether or not the determination condition 265 acquired by the determination condition acquisition unit 264 has a condition related to a specific character (S41).
If Yes in step S41, the specific character area determination unit 263 sequentially targets each determination condition (see Table 3) related to the specific character in order to examine the setting of the area for the specific character, and steps S42 to S46. Repeat the process. In the case of a specific character, since the condition for extracting the specific character is included in the judgment condition, the specific character is extracted in the loop unlike the case of the ruled line or the background ruled line.

In the loop processing, the specific character area determination unit 263 first generates data of a specific character for search from the determination conditions of the processing target according to the designation of the "symbol" and the "direction" (S42). Next, the specific character area determination unit 263 extracts all the specific characters from the image data to be processed according to the generated specific character data (S43).
Then, among the extracted specific characters, those that meet the element conditions in the determination conditions to be processed are acquired (S44). At this time, the specific character area determination unit 263 also retains the information of the specific character that has not been acquired. Further, the specific character area determination unit 263 saves the feature element (here, the ruled line saved in step S25 or the ruled line saved in step S35) in association with the determination condition designated as the "combination" in the determination condition to be processed. The background ruled line) is acquired (S45).

Next, the specific character area determination unit 263 sets an area based on the specific character in the image data according to the specific character acquired in step S44, the feature element acquired in step S45, and the determination condition of the processing target. The attribute is set (S46). For example, when the judgment condition of ID = B_001 is used, an area is set in the range from a specific character satisfying the element condition to the ruled line of the next ID = A_001 in the character arrangement direction, and the attribute of the area is set to "character". Set to.

After the end of the loop of steps S42 to S46, or when NO in step S41, the range extraction unit 266 integrates the area set based on each of the ruled line, the background ruled line, and the specific character, and the character in the image data. The attribute area is fixed (S47). Although it is a character attribute here, other attributes may be used.
This completes the process of FIG. 7. The details of the process in step S47 will be described later with reference to FIG.

In the above processes of FIGS. 6 and 7, the processes of steps S22, S32 and S43 are the processes of the extraction procedure and correspond to the functions of the extraction means. The processing of steps S24, S34, S46 and S47 is the processing of the attribute setting procedure, and corresponds to the function of the attribute setting means.
The character area determination unit 212 in this embodiment considers the extraction of the feature elements for the plurality of feature elements by the extraction means and the setting of the notation attributes by the attribute setting means as described above. Perform while selecting in a predetermined order.

Next, an example of applying the processing of FIGS. 6 and 7 to specific image data will be described.
First, FIGS. 8A to 8C show an example in which the process of setting the area for the ruled line in steps S22 to S25 is applied to the image data obtained by reading the paper surface.
FIG. 8A is a simplified representation of the image data in the initial state. The thick lines 601 to 605 in the figure indicate ruled lines, and the thin lines 610 in the figure are simplified representations of characters.
FIG. 8B shows a state in which ruled lines satisfying the element conditions are extracted from the thick lines 601 to 605. Assuming that the interval of one step is 30 mm and the thickness of each ruled line is 0.1 mm, the ruled line as a ruled line satisfying the element condition is obtained by the processing of steps S22 and S23 of FIG. 6 for ID = A_002. 701 to 704 are extracted.

FIG. 8C shows an area set according to those ruled lines. In the process of step S24 of FIG. 6, since the area is set in the portion sandwiched between the extracted ruled lines, the areas 706 to 708 are set.
Note that FIG. 8B also shows a ruled line 705 extracted when ID = A_001 in Table 2 is used as a processing target. However, the ruled line extracted under this condition is only the ruled line 705, and since there is no portion sandwiched between the plurality of ruled lines, the area is not set.

Next, FIGS. 9A and 9B show an example in which the process of setting the area for the background ruled line in steps S32 to S35 of FIG. 6 is applied to the same image data as in FIG. 8A.
FIG. 9A shows a state in which the background satisfying the element conditions is extracted from the background. As shown in FIG. 9A, as the background region in the image data, for example, the regions shown by reference numerals 801 to 804 can be extracted. However, among these, for example, the background areas satisfying the element conditions of ID = C_002 in Table 4 are only the background ruled lines 801 and 802, and these are extracted as the background ruled lines.

FIG. 9B shows an area set according to those ruled lines. In the process of step S34, since the area is set in the portion sandwiched between the extracted background ruled lines, the area 811 is set. The area 812 is not sandwiched between the background ruled lines of FIG. 9A. However, if A_002 is specified as a "combination" in the element condition so that the area can be set also in the portion sandwiched between the ruled line 703 and the background ruled line 802, the area 812 can also be set. The same applies when the "range" is set to "the part in contact with the background ruled line".

Next, FIG. 10 shows an example in which the process of setting the area for a specific character in steps S42 to S46 in FIG. 7 is applied. Here, the determination conditions for ID = B_001 in Table 3 will be described.
In this determination condition, since the ruled line of A_001 is specified as the "combination", the area is set using the ruled lines 901 and 902 that satisfy the element conditions of A_001.
The specific character area determination unit 263 of FIG. 4 generates image data of specific characters from "Å" of "symbol" and "horizontal" of "direction" in the element condition, and together with the image data generated in the image data. Search if there is a match. As a result, the character "Å" indicated by reference numeral 95 is found. Then, the range sandwiched between the position of the character "Å" and the next ruled line 902 is set as the area 903.
Here, it takes time to search for matching character data from the image data, so define the position of a specific character with respect to the ruled line defined in "Combination", and only at the defined position. On the other hand, it is better to search for a specific character.

Next, with reference to FIGS. 11A and 11B, a method of extracting the background ruled line using the judgment condition based on the ruled line will be described when the document includes the background ruled line and there is no determination condition for the background ruled line. This process corresponds to a modified example of the background extraction in the processes of FIGS. 6 and 7.

In FIG. 11A, the ruled lines 701 to 704 are the same as those extracted in FIG. 8B. In this case, where the ruled line is cut off in the middle of the image, such as the ruled lines 701 and 702, there is often a background ruled line on the extension line. Therefore, if the background is detected on the extension lines 1001 and 1002 and the determination condition regarding the ruled line is applied to the detected background area, the area of the background ruled line that is the basis of the area setting can be extracted.
Here, assuming that the ruled lines 1003 and 1004 are extracted on the extension lines 1001 and 1002 as shown in FIG. 11B, the areas 1006 and 1007 sandwiched between the ruled lines are set according to the determination conditions regarding the ruled lines.

Next, a method of extracting candidate background ruled lines from the result of background extraction will be described with reference to FIGS. 12A and 12B.
It should be noted that it is possible to specify whether the characters are written vertically or horizontally in the image data by appropriately applying a known technique. In this specified state, as shown in FIG. 12A, histograms 1102 and 1103 of the black portions in the vertical and horizontal directions of the image data 1101 of the original are acquired. Since the image data 1101 is written vertically, the line spacing of the histogram 1103 is acquired. However, the line spacing is not a candidate for the background ruled line. The background in the image data 1101 at the portion corresponding to the portions 1131 and 1132 having a width equal to or larger than the line spacing and having a low histogram value is extracted, and as shown in FIG. 12B, the regions 1133 and 1134 with continuous background are extracted as candidates for the background ruled line. it can.

Further, from the histogram 1102, the background in the image data 1101 of the low value portion 1121, 1122, 1123 can be extracted, and the region 1124, 1125, 1126 in which the background is continuous can be extracted as a candidate for the background rule line.
Here, the criteria 1104 and 1105 for determining whether or not the histogram value is low are fixedly set in the system in advance.

Next, with reference to FIG. 13, a method of totaling the setting results of the areas based on the plurality of feature elements and finally determining the character area will be described.
The setting result of the character area based on the ruled line is 1201, the setting result of the character area based on the background ruled line is 1202, and the setting result of the character area based on the specific character is 1203.
The combined state of 1201 and 1202 is 1204, and the combined state of 1204 and 1203 is 1205. In order to explain the overlapping portion in 1205, one line is picked up, and the portion in which the character attribute area is set based on each feature element is indicated by a frame and “1” (121 to 1213). In addition, as a guideline for the size of one line, data in which all are set to "0" as 1214 are shown.

The results of 1211-1213 can be added for each coordinate (1215, 1216) and the addition result can be used to determine the final character area.
Reference numeral 1215 is an example in which 2 is used as the threshold value and the area where the addition result is 2 or more is set as the character area. In this case, the framed range is fixed as the character area.
Reference numeral 1216 is a case where the priority of the setting result of the character area based on the ruled line is increased. Here, the framed portion in which the addition result is 2 or more and the determination result of 1213 is “1” is determined as the character area.

As described above, the character area determination unit 212 of this embodiment extracts the feature element by the extraction means and sets the attribute for the input image data with reference to the determination condition by the attribute setting means for each of the plurality of feature elements. Do. Then, the attribute setting means aggregates the attributes set according to the plurality of feature elements for each of the plurality of feature elements, and sets the attributes of each part in the input image data.
Further, when there are many judgment methods, the judgment result of the method having a high priority is multiplied by a large number corresponding to the priority, and the value when the multiplied values are added is a standard such as 2 when 1215. The character area can be determined depending on whether or not it is equal to or greater than the value. In any case, the threshold value and the priority are set in advance.

The description of the embodiment is completed above, but in the present invention, the specific configuration of the device, the specific processing procedure, the data format, the specific data content, the content and number of determination conditions, the items, etc. , The invention is not limited to that described in the embodiment.
For example, when a feature related to a character area is acquired from a plurality of feature element extracts and handled, the final character area should be determined by considering the priority of the feature from multiple types of results and conditioning the character area. It is conceivable to do. As a result, the expandability is improved even when the character area determination is performed in a processing process other than the above-described embodiment. In addition, if a UI is provided so that the user can perform conditioning, there is an effect that convenience can be improved.

Further, when the characteristics related to the character area are acquired from the ruled line extraction, it may be determined that the ruled line to be determined is, for example, a newspaper ruled line. As a result, it is possible to set conditions for the discrimination attribute of the attribute information, specify the characteristics of the ruled line extracted by the ruled line extraction, and improve the accuracy.
Further, when the feature related to the character area is acquired from the background ruled line extraction, it is preferable to assume an extension line of the ruled line extraction and determine whether or not the character range can be determined from the image data on the extension line. By doing so, the accuracy of character area determination can be maintained even in a place where no ruled line exists.

Further, when the characteristics related to the character area are acquired from the specific character extraction, the character area may be determined based on the font data. In this way, special characters that are easily erroneously determined by line extraction can be determined as a character area, so that accuracy can be improved.
Further, when extracting based on a plurality of feature elements, it is preferable that the user can determine the priority of which extraction is performed first. By defining the extraction order, it is possible to determine the character area and the pattern area intended by the user.

Further, when the judgment condition is retained as information including the extraction range and the judgment result, it is preferable to acquire the extraction range and the judgment result together with the judgment condition and determine the extraction range and the judgment result based on the acquired information. .. As a result, it is possible to determine the extraction range and retain the determination result according to the number of items of the extraction standard.
Further, when the determination condition is held as information including the control method of image processing, it is preferable to acquire the control method together with the determination condition and control based on the acquired information. As a result, the control can be changed according to the number of items of the extraction standard.

In addition, it is preferable to maintain the extraction criteria for extracting the type of the original, and to determine the type of the original such as a character original or a photographic original as a feature of the original. If the type of the original can be identified, it is possible to shorten the compression processing time for the original having a large proportion of characters and perform image processing according to the original type.
Further, when the characteristics of characters and patterns are distinguished as the characteristics of the image, it is preferable to switch the image processing of the character portion and the pattern portion. As a result, for image data in which the end portion of the character becomes thin and difficult to read, the character can be made easier to read by thickening the end portion of the character portion or darkening the character itself.

Further, when the characteristic of the image is the characteristic of the original, it is preferable to switch the image processing according to the characteristic of the original. As a result, there are newspapers and advertisements in a manuscript having a high background density and a thin paper, but when the background is too dark or double-sided printing is performed, the characters are set off and the characters become difficult to read. The characters can be made easier to read by strengthening the background correction or removing the set-off with respect to the image data obtained by reading the original with such characteristics.

Further, an embodiment of the program of the present invention is a program for causing a computer to control necessary hardware to realize all or a part of the functions of the MFP 100 in the above-described embodiment.
Such a program may be stored in a ROM provided in the computer or another non-volatile storage medium (flash memory, EEPROM, etc.) from the beginning. However, it can also be recorded and provided on any non-volatile recording medium such as a memory card, a CD, a DVD, or a Blu-ray disc. By installing the program recorded on these recording media on a computer and executing it, each of the above-mentioned procedures can be executed.
Further, it is also possible to download an external device connected to a network and having a recording medium on which the program is recorded or a program stored in a storage means, install the program on a computer, and execute the program.

Further, it goes without saying that the configurations of the embodiments and the modifications described above can be arbitrarily combined and implemented as long as they do not contradict each other, and only a part of them can be taken out and implemented.

100: MFP, 101: CPU, 102: ROM, 103: RAM, 104: HDD, 105: Communication I / F, 106: Operation unit, 107: Display unit, 108: Engine I / F, 120: Scanner, 130: Plotter, 200: Image processing unit, 210: Scanner correction unit, 220: Compression processing unit, 230: Data interface unit, 240: Decompression processing unit, 250: Printer correction unit, 261: Rule line area determination unit, 262: Background rule line area Judgment unit 263: Specific character area judgment unit 264: Judgment condition acquisition unit 265: Judgment condition 266: Range extraction unit 267: Judgment result setting unit

Japanese Unexamined Patent Publication No. 2007-189275 Japanese Patent No. 3898645 Japanese Patent No. 3251119

Claims (9)

Input means for inputting image data and
An extraction means for extracting a predetermined feature element from the image data input by the input means, and an extraction means.
With respect to the predetermined feature element, the extraction means refers to a determination condition in which the condition to be satisfied by the feature element and the attribute of the region determined based on the feature element satisfying the condition in the image data are determined in advance. An attribute setting means for setting an attribute defined by the determination condition in a region defined by the determination condition in the input image data based on the extracted feature element and the determination condition is provided .
Extraction of the feature element by the extraction means and setting of the attribute for the input image data with reference to the determination condition by the attribute setting means are performed for each of the plurality of feature elements.
The attribute setting means is an image processing apparatus characterized in that the attributes set according to the plurality of feature elements are aggregated for the plurality of feature elements and the attributes of each part in the input image data are set. .. The image processing apparatus according to claim 1 .
Image processing characterized in that the extraction of the feature elements for the plurality of feature elements by the extraction means and the setting of the attributes by the attribute setting means are performed while selecting the feature elements to be considered in a predetermined order. apparatus. The image processing apparatus according to claim 1 or 2 .
An image processing device characterized in that one of the predetermined feature elements is a ruled line. The image processing apparatus according to claim 1 or 2 .
One of the predetermined feature elements is a specific character, and the range in which the extraction means searches for the specific character in the input image data is determined based on the position of another feature element that has already been extracted. An image processing device characterized in that it is determined according to a determination condition. The image processing apparatus according to claim 1 or 2 .
Said predetermined characteristic element comprises a border and background border, said extraction means, when extracting the ruled lines from image data obtained by the input, to the extension on the area of the extracted ruled line, performing the extraction of the background border An image processing device characterized by. The image processing apparatus according to any one of claims 1 to 5 .
An image processing apparatus comprising: an image processing means for processing each part of the input image data by a processing method according to the attribute set in the part by the attribute setting means. The image processing apparatus according to claim 6 .
An image processing apparatus characterized in that the processing for the image data performed by the image processing means includes a processing for emphasizing characters for a portion in which an attribute of a character area is set. Input procedure for inputting image data and
An extraction procedure for extracting a predetermined feature element from the image data input in the input procedure, and an extraction procedure.
With respect to the predetermined feature element, the extraction procedure refers to a determination condition in which the condition to be satisfied by the feature element and the attribute of the region defined based on the feature element satisfying the condition in the image data are determined in advance. Based on the extracted feature element and the determination condition, an attribute setting procedure for setting the attribute defined by the determination condition in the area specified by the determination condition in the input image data is provided .
Extraction of the feature element by the extraction procedure and setting of the attribute for the input image data with reference to the determination condition by the attribute setting procedure are performed for each of the plurality of feature elements.
The attribute setting procedure is an image processing method in which attributes set according to the plurality of feature elements are aggregated for the plurality of feature elements, and the attributes of each portion in the input image data are set . A program for operating a computer as the image processing device according to any one of claims 1 to 7 .