JP5035443B2 - Image processing apparatus, image processing method, and computer program - Google Patents

Description

The present invention relates to an image processing apparatus, an image processing method, and a computer program. More specifically, for example, line drawing data including a missing portion obtained by various data extraction processes, such as a restoration processing of a missing portion included in difference data between an original document and an additionally written document, which is performed in an analysis process of additional information, for example. The present invention relates to an image processing apparatus, an image processing method, and a computer program that efficiently execute restoration.

In the field of image processing, for example, there are various processes for extracting a part added by a user with a pen, pencil, stamp, etc. in a document output from a printer or FAX, or for verifying whether a security document has been tampered with. Research and development is underway. In general, in such additional writing and falsification verification processing, processing for comparing original document data with an output document that may be added is performed.

That is, the difference between the scanned image data obtained by scanning a document to be detected for additional writing with an image reading device such as a scanner and the original image data stored in a PC or printer is obtained, and the additional image data Is to get

However, in this method, if there is an overlap in the part of the paper document that was originally added to the original text or figure, when taking the difference from the original and trying to obtain the additional information, There was a problem that the overlapped portion with the original was not included, and the added characters and figures were interrupted.

As a prior art aiming at solving such problems, there is, for example, Patent Document 1. Patent Document 1 discloses a configuration related to repair of discontinuity in a postscript image obtained by subtracting an original image from a scan image. Black pixels of the postscript image are sequentially scanned around black pixels of the original image, and there are black pixels of the postscript image in the vicinity of the target black pixel. At this time, a configuration is disclosed in which the discontinuity is repaired by a process of making the pixels of the postscript image corresponding to the target pixel black.

Further, Patent Document 2 creates an interrupted additional write outline from a postscript image generated by subtracting an original image from a scan image, and further connects the coordinates of the end points to be connected by further subtracting the original image from the outline image. By detecting the direction and connecting the end points from the end point position and connection direction information to form a closed curve and coloring the inside, connecting the detected additional information that has been interrupted, the disconnection The structure which acquires the corrected postscript information is disclosed.

However, there is a high possibility that the scanned image of the document for which additional information is to be detected has degraded image quality, i.e., the degree of blurring or the hue has changed. It may have been copied. In particular, since the image quality deterioration such as fading is severe in the additional writing portion, the contour of the additional writing portion extracted from the scanned image of the document for which additional writing information is to be detected is often not a straight line but a zigzag. For this reason, it is difficult to specify the end points and the interpolation direction, and it is difficult to obtain the complete postscript repaired additional information even if the method of the above-mentioned patent document is applied.

In addition, in the configuration in which the postscript information is acquired by repairing the interruption, the repair of the postscript information consisting of fine lines such as characters added by a pen or pencil can be performed relatively accurately. There is a problem that it is difficult to accurately restore relatively thick additional information such as when processing is performed by marking the original character with a line marker, or characters added by a marker or magic. .
Japanese Patent Laid-Open No. 08-063546 JP 2004-213230 A

The present invention has been made in view of the above-described problems. For example, in the postscript information extraction processing from a document, the missing data included in the difference data extracted based on the difference between the postscript information extraction target document and the original Image processing that makes it possible to accurately and efficiently recover the missing part, especially for the postscript information with a thick line segment. An object is to provide an apparatus, an image processing method, and a computer program.

The first aspect of the present invention is:
It is an image processing apparatus that performs image processing to input restoration target data having a missing part and generate restoration data that eliminates the missing part,
A postscript information extraction unit that inputs postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generates a postscript extraction image obtained by extracting the postscript information from the postscript document image;
Additional line width detection means for detecting the line width of the additional information included in the additional recording extracted image generated by the additional information extraction means;
A process switching means for determining whether to perform additional write defect portion repair processing for fine lines or additional write defect portion repair processing for thick lines according to the line width of the additional write information detected by the additional write line width detection means;
A thick line additional write defect repairing unit that inputs the additional write extracted image generated by the additional write information extraction unit and executes a thick line additional write defect repair process on the thick line additional write information determined as a processing target by the process switching unit; ,
Fine line additional write defect portion repairing means for inputting the additional write extracted image generated by the additional write information extraction means and executing thin line additional write defect repair processing on the thin line additional write information determined as a processing target by the process switching means; ,
An image processing apparatus characterized by comprising:

Furthermore, in one embodiment of the image processing apparatus of the present invention, the thick line additional write defect portion repairing means has an expansion processing means, and is based on an expansion process of additional write information included in the additional write extraction image generated by the additional write information extraction means. It is a structure which performs a defect | deletion part repair process, It is characterized by the above-mentioned.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the thin line additional writing defect portion repairing means includes a thinning means, an end point extracting means, and an end point connecting means, and the additional writing extraction generated by the additional information extracting means. The additional information included in the image is subjected to thinning processing in the thinning means, the endpoint extraction means performs endpoint extraction processing based on the thinning processing result, and the endpoint connection means performs extraction endpoint connection processing. It is the structure which performs and performs a defect | deletion part repair process.

Furthermore, in an embodiment of the image processing apparatus of the present invention, the thin line additional write defect portion repairing means further includes an expansion processing means, and the endpoint connection data generated by the endpoint connection means by the extraction endpoint connection processing. It is the structure which performs the defect part repair process by an expansion process, It is characterized by the above-mentioned.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional writing line width detecting means has a number of effective pixels (N1) corresponding to pixels constituting additional writing information included in the additional writing extracted image generated by the additional writing information extracting means. ) And the number of constituent pixels (N2) of the thinned data of the additional writing information, the line width of the additional writing information is expressed by the following equation:
Line width = N1 / N2
It is the structure which performs the process calculated according to this.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the process switching means is for adding a write-once missing portion for thin lines or processing for a thick line according to the line width of the postscript information detected by the postscript line width detection means. In the process of determining which of the additional write defect portion repair process is to be performed, the determination process is performed by applying a predetermined threshold value.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the process switching means is for adding a write-once missing portion for thin lines or processing for a thick line according to the line width of the postscript information detected by the postscript line width detection means. In the process of determining which of the additional write missing part repair process is executed, the determination process is performed by applying a threshold value that is determined according to the character size or line spacing of the document for which additional writing has been executed. And

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional record information extraction unit is configured to input original document image data and the additional record document image data, and to extract a difference between the two input image data. It is characterized by being configured.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional record information extracting unit inputs the additional record document image data, and extracts color record information of a specific color from the additional record document image data as additional record information. It is characterized by comprising.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional record information extracting means inputs the additional record document image data, deletes ruled line information from the additional record document image data, and uses information other than the ruled line information as additional record information. It is characterized by comprising ruled line separating means for extracting.

Furthermore, the second aspect of the present invention provides
It is an image processing apparatus that performs image processing to input restoration target data having a missing part and generate restoration data that eliminates the missing part,
A postscript information extraction unit that inputs postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generates a postscript extraction image obtained by extracting the postscript information from the postscript document image;
A first additional write defect repairing unit that inputs the additional write extraction image generated by the additional write information extraction unit and executes the additional write defect repairing process according to a predetermined first processing sequence;
Second write-once deficient part repairing means for inputting a postscript extracted image generated by the postscript information extracting means and executing a postscript missing part repairing process according to a predetermined second processing sequence different from the first processing sequence When,
OR processing means for executing final processing of the processing result of the first additional writing defect portion repairing means and the processing result of the second additional writing defect portion repairing means to generate final additional writing defect portion repair processing result data ,
An image processing apparatus characterized by comprising:

Furthermore, in an embodiment of the image processing apparatus of the present invention, the first additional write defect portion repairing unit includes an expansion processing unit, and an expansion process of the additional write information included in the additional write extracted image generated by the additional write information extraction unit. It is the structure which performs the defect | deletion part repair process by.

Furthermore, in an embodiment of the image processing apparatus of the present invention, the second additional write defect repairing means includes a thinning means, an end point extraction means, an end point connection means, and an expansion processing means, and the additional write information extraction means. The thinning means executes the thinning process in the thinning means, the endpoint extraction means executes the endpoint extraction process based on the thinning processing result, and the endpoint connection means extracts End point connection processing is executed, and in the expansion processing means, the end point connection data generated by the extraction end point connection processing in the end point connection means is executed to execute defect portion repair processing. It is characterized by.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional record information extraction unit is configured to input original document image data and the additional record document image data, and to extract a difference between the two input image data. It is characterized by being configured.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional record information extracting unit inputs the additional record document image data, and extracts color record information of a specific color from the additional record document image data as additional record information. It is characterized by comprising.

Furthermore, in one embodiment of the image processing apparatus of the present invention, the additional record information extracting means inputs the additional record document image data, deletes ruled line information from the additional record document image data, and uses information other than the ruled line information as additional record information. It is characterized by comprising ruled line separating means for extracting.

Furthermore, the third aspect of the present invention provides
It is an image processing method for inputting image data to be repaired having a missing part and executing image processing to generate restoration data in which the missing part is eliminated,
A postscript information extraction step of inputting postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generating a postscript extraction image obtained by extracting the postscript information from the postscript document image;
An additional writing line width detecting step for detecting a line width of additional writing information included in the additional writing extracted image generated in the additional writing information extraction step;
A process switching step for determining whether to perform additional writing defect portion repair processing for thin lines or additional writing defect portion repair processing for thick lines according to the line width of the additional writing information detected in the additional writing line width detection step;
A thick line additional write defect repair step for inputting the additional write extracted image generated in the additional write information extraction step and executing a thick line additional write defect repair process for the thick line additional write information determined as a processing target in the process switching step; ,
A thin line additional write defect repairing step that inputs the additional write extracted image generated in the additional write information extraction step and executes a thin line additional write defect repair process on the thin line additional write information determined as a processing target in the process switching step; ,
An image processing method characterized by comprising:

Furthermore, in one embodiment of the image processing method of the present invention, the thick line additional write defect portion repairing step executes a defective portion repair process by an expansion process of additional write information included in the additional write extraction image generated in the additional write information extraction step. It is characterized by that.

Furthermore, in one embodiment of the image processing method of the present invention, the thin line additional writing defect portion repairing step performs thinning processing of the additional writing information included in the additional writing extracted image generated in the additional writing information extracting step, and the thinning process is performed. It is a step of executing an end point extraction process based on the result, and further executing an extraction end point connection process to execute a defect portion repair process.

Furthermore, in one embodiment of the image processing method of the present invention, the thin line additional write defect portion repairing step further executes an expansion process of the end point connection data generated by the end point connection process.

Furthermore, in an embodiment of the image processing method of the present invention, the additional line width detecting step includes the number of effective pixels (N1) corresponding to the pixels constituting the additional write information included in the additional write extracted image generated by the additional write information extraction step. ) And the number of constituent pixels (N2) of the thinned data of the additional writing information, the line width of the additional writing information is expressed by the following equation:
Line width = N1 / N2
The process of calculating according to is performed.

Furthermore, in an embodiment of the image processing method of the present invention, the process switching step includes a thin line additional write defect repair process or a thick line depending on the line width of the additional write information detected in the additional write line width detecting step. In the process of determining which of the additional write defect portion repair process is to be performed, a determination process to which a pre-fixed threshold is applied is performed.

Furthermore, in an embodiment of the image processing method of the present invention, the process switching step includes a thin line additional write defect repair process or a thick line depending on the line width of the additional write information detected in the additional write line width detecting step. In the process of determining which of the additional writing missing part repairing process is executed, a determination process is performed in which a threshold value determined in accordance with the character size or line spacing of the document for which additional writing has been executed is applied.

Furthermore, in one embodiment of the image processing method of the present invention, the additional information extracting step includes a difference extraction process of inputting the original document image data and the additional document image data and extracting a difference between the two input image data. It is a step to be executed.

Further, in one embodiment of the image processing method of the present invention, the additional information extraction step inputs color additional document image data, and extracts a specific color recording information from the additional document image data as additional information. It is the step which performs.

Further, in one embodiment of the image processing method of the present invention, the additional information extraction step inputs additional document image data, deletes ruled line information from the additional document image data, and uses information other than the ruled line information as additional information. It is a step for executing a ruled line separation process to be extracted.

Furthermore, the fourth aspect of the present invention provides
It is an image processing method for inputting image data to be repaired having a missing part and executing image processing to generate restoration data in which the missing part is eliminated,
A postscript information extraction step of inputting postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generating a postscript extraction image obtained by extracting the postscript information from the postscript document image;
A first additional write defect repair step that inputs the additional write extracted image generated in the additional write information extraction step and executes the additional write defect repair process according to a predetermined first processing sequence;
Second write-once defect portion repair step of inputting the postscript extraction image generated in the postscript information extraction step and executing the post-write defect portion repairing process according to a predetermined second processing sequence different from the first processing sequence When,
An OR processing step of performing OR processing of the processing result in the first additional write defect portion repair step and the processing result in the second additional write defect portion repair step to generate final additional write defect portion repair processing result data; ,
An image processing method characterized by comprising:

Furthermore, in one embodiment of the image processing method of the present invention, the first additional write defect portion repairing step performs a defective portion repair process by an expansion process of additional write information included in the additional write extraction image generated in the additional write information extraction step. It is a step to perform.

Furthermore, in one embodiment of the image processing method of the present invention, the second additional write defect portion repairing step performs thinning processing of the additional writing information included in the additional writing extracted image generated in the additional writing information extraction step, and the thinning is performed. This is a step of executing the end point extraction processing based on the processing result, executing the extraction end point connection processing, executing the end point connection data generated by the extraction end point connection processing, and executing the missing portion repair processing. It is characterized by that.

Furthermore, in one embodiment of the image processing method of the present invention, the additional information extracting step includes a difference extraction process of inputting the original document image data and the additional document image data and extracting a difference between the two input image data. It is a step to be executed.

Further, in one embodiment of the image processing method of the present invention, the additional information extraction step inputs color additional document image data, and extracts a specific color recording information from the additional document image data as additional information. It is the step which performs.

Further, in one embodiment of the image processing method of the present invention, the additional information extraction step inputs additional document image data, deletes ruled line information from the additional document image data, and uses information other than the ruled line information as additional information. It is a step for executing a ruled line separation process to be extracted.

Furthermore, the fifth aspect of the present invention provides
In the image processing apparatus, a computer program for executing image processing for inputting restoration target data having a defect portion and generating restoration data in which the defect portion is eliminated,
A postscript information extraction step of inputting postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generating a postscript extraction image obtained by extracting the postscript information from the postscript document image;
An additional writing line width detecting step for detecting a line width of additional writing information included in the additional writing extracted image generated in the additional writing information extraction step;
A process switching step for determining whether to perform additional writing defect portion repair processing for thin lines or additional writing defect portion repair processing for thick lines according to the line width of the additional writing information detected in the additional writing line width detection step;
A thick line additional write defect repair step for inputting the additional write extracted image generated in the additional write information extraction step and executing a thick line additional write defect repair process for the thick line additional write information determined as a processing target in the process switching step; ,
A thin line additional write defect repairing step that inputs the additional write extracted image generated in the additional write information extraction step and executes a thin line additional write defect repair process on the thin line additional write information determined as a processing target in the process switching step; ,
In a computer program characterized by causing

Furthermore, the sixth aspect of the present invention provides
In the image processing apparatus, a computer program for executing image processing for inputting restoration target data having a defect portion and generating restoration data in which the defect portion is eliminated,
A postscript information extraction step of inputting postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generating a postscript extraction image obtained by extracting the postscript information from the postscript document image;
A first additional write defect repair step that inputs the additional write extracted image generated in the additional write information extraction step and executes the additional write defect repair process according to a predetermined first processing sequence;
Second write-once defect portion repair step of inputting the postscript extraction image generated in the postscript information extraction step and executing the post-write defect portion repairing process according to a predetermined second processing sequence different from the first processing sequence When,
An OR processing step of performing OR processing of the processing result in the first additional write defect portion repair step and the processing result in the second additional write defect portion repair step to generate final additional write defect portion repair processing result data; ,
In a computer program characterized by causing

Note that the computer program of the present invention is a recording medium provided in a computer-readable format for a computer system capable of executing various program codes, for example, a recording medium such as a CD, FD, or MO. A computer program that can be provided by a medium or a communication medium such as a network. By providing such a program in a computer-readable format, processing corresponding to the program is realized on the computer system.

Other objects, features, and advantages of the present invention will become apparent from a more detailed description based on embodiments of the present invention described later and the accompanying drawings. In this specification, the system is a logical set configuration of a plurality of devices, and is not limited to one in which the devices of each configuration are in the same casing.

According to the configuration of the present invention, for example, a repair process that eliminates a missing portion of data having a missing portion, such as difference data between an original document and a postscript document to which additional data is added, is executed efficiently and accurately. be able to. Specifically, in the configuration of an embodiment of the image processing apparatus of the present invention, the line width of the postscript information having a defect portion included in the postscript extracted image is detected, and the line width is thin and the case where the line width is thick, respectively. Execute defect repair processing according to the processing sequence that matches the line width. Specifically, when the additional writing information is a thick line, restoration by expansion processing is executed, and when it is a thin line, restoration processing by thinning processing, endpoint extraction processing, and endpoint connection processing is executed. With this configuration, it is possible to optimally repair the missing portion according to the line width, and it is possible to generate additional information with higher accuracy.

Further, according to the configuration of one embodiment of the present invention, the missing information repair processing of the additional information by a plurality of different processing sequences is performed in parallel, and an OR processing result based on the plurality of processing results is generated, and this OR The processing result is the final defect repair result. According to this configuration, it is possible to compensate for a defective portion that could not be repaired in one repair processing sequence based on the result of the other repair processing sequence, and as a result, it is possible to generate additional information with higher completeness. It becomes.

It is a figure explaining the outline | summary of the process to which the image processing apparatus of this invention is applied. It is a figure explaining the example of a production | generation of the difference data from an original document and a postscript document. It is a figure explaining the example of processing target data by the image processing apparatus of this invention. 1 is a block diagram showing the configuration of an embodiment of an image processing apparatus of the present invention. It is a figure explaining the specific process example of the difference extraction process performed in the image processing apparatus of this invention. It is a figure explaining the specific process example of the line | wire width detection process of the postscript information performed in the image processing apparatus of this invention. 1 is a block diagram showing the configuration of an embodiment of an image processing apparatus of the present invention. It is a figure explaining the specific process example of the expansion process performed in the image processing apparatus of this invention. It is a figure explaining the specific process example of the thinning process performed in the image processing apparatus of this invention. It is a figure explaining the specific process example of the endpoint extraction process performed in the image processing apparatus of this invention. It is a figure explaining the specific process example of the connection endpoint pair extraction process performed in the image processing apparatus of this invention. It is a figure explaining the specific process example of the end point connection process performed in the image processing apparatus of this invention. It is a figure which shows the flowchart explaining the process sequence in the image processing apparatus of this invention. It is a block diagram which shows the one Example structure of the image processing apparatus of this invention. It is a block diagram which shows the one Example structure of the image processing apparatus of this invention. It is a block diagram which shows the one Example structure of the image processing apparatus of this invention. It is a block diagram which shows the one Example structure of the image processing apparatus of this invention. It is a figure explaining the specific process example performed in the image processing apparatus of this invention. It is a figure explaining the specific process example performed in the image processing apparatus of this invention. It is a figure explaining the specific process example performed in the image processing apparatus of this invention. It is a figure which shows the flowchart explaining the process sequence in the image processing apparatus of this invention. It is a figure explaining the hardware structural example of the image processing apparatus of this invention.

Hereinafter, an image processing apparatus, an image processing method, and a computer program according to embodiments of the present invention will be described in detail with reference to the drawings.

First, an outline of processing to which the image processing apparatus of the present invention is applied will be described with reference to FIG. For example, the image processing apparatus of the present invention extracts a difference from the original document 10 shown in FIG. 1 and the additional document 20 including various memos such as comments and underlines and added to the original document 10. In the process of acquiring the data, a process for repairing the missing portion of the difference data is performed. Note that the image processing apparatus of the present invention can be applied not only to difference data, but also to processing for eliminating missing portions in data having missing portions obtained by various processes.

The example shown in FIG. 1 is an example of the processing. The original document 10 and the postscript document 20 are read by the scanner 30, and the original document image data and the postscript document image data are input to the image processing apparatus 100. This is a process of performing difference information acquisition processing, repairing a missing portion included in the difference data, and outputting additional information.

As described in the background art section, in the conventional differential extraction, there is a problem that information in which the overlapping portion between the original and the additional recording is interrupted is acquired. For example, as shown in FIG. 2, when there are an original document 51 and a postscript document 52, difference data from the original document 51 and the postscript document 52 is acquired even though the postscript information is originally the line segment data 53. Then, as shown in the additional record extraction information 55, the original document 51 and the additional record document 52 are detected as data that is interrupted, and correct additional data cannot be detected. In the present invention, the image processing apparatus 100 executes processing for repairing these interruptions.

In the image processing according to the present invention, not only repair processing of additional information detected based on the difference data shown in FIG. 2 but also repair of interrupted data including various missing portions acquired by other methods is executed. can do. For example, FIG. 3A shows a processing example in which the postscript extraction information 62 is extracted from only the postscript document 61 image without applying the original image.

For example, when the additional recording data is recorded in a different color (for example, red) included in the original image data, the additional recording extraction information 62 is acquired by the process of extracting only the additional recording color data from the additional recording document 61. However, also in this case, the additional information is acquired as an interrupted image in the overlapping portion with the original data.

FIG. 3B shows a processing configuration in which ruled line removal information 72 obtained by removing ruled lines from the document 71 with ruled lines is acquired. When such processing is performed, by removing the straight line as the ruled line portion, data from which the overlapping portion with the ruled line is removed is output, and a part of the original data is lost.

The image processing apparatus 100 according to the present invention performs a process of efficiently and accurately generating uninterrupted data for image data having such discontinuities and missing portions by eliminating the missing portions.

Details of the configuration and processing of the image processing apparatus of the present invention will be described with reference to FIG. In the image processing apparatus of the present invention, the restoration process of the defective portion is switched between when the additional writing information is a thin line and when it is a thick line, and different restoration processes are executed. That is, a thin line additional write defect portion repairing means and a thick line additional write defect portion repair means are provided, and in each repair means, a repair process suitable for the thin line additional write defect part and a repair process suitable for the thick line additional write defect part are executed. . As described above, by applying the defect portion repair process of different sequences to the thick append writing and the thin append writing, more accurate defect portion repair is realized.

In the image processing apparatus of the present invention, the line width (thickness) of the additional writing information is detected, and an optimal defect (discontinuity) repair process corresponding to the line width is performed to improve the repair accuracy. Various methods can be applied as a method for determining whether the postscript information is thick or thin.

In determining whether the line width of additional information is thick or thin, it may be a process that applies a fixed numerical value as a threshold value, but it is not a process that applies a fixed numerical value as a threshold value, but a determination according to the document to be processed It is good also as a structure which performs a process. For example, the determination is made based on whether the additional writing is larger or smaller than the overlapping characters. In other words, even with an additional writing written with a 1 mm wide sign pen, if it is a small character such as 8 points, it is better to process it as a thick additional writing, and an additional writing written with a line marker of 4 mm width The process is such that a portion of a large character such as a point is processed as a thin postscript.

When determining the line width of additional writing information, the line width of additional writing information is determined in various units such as page units, line units, and character units. Based on the determination result, thin line additional writing defect repair means, or thick line additional writing deletion In any of the part repairing means, the defective part repairing process is executed.

With reference to FIG. 4, an embodiment of the image processing apparatus of the present invention will be described. The image processing apparatus shown in FIG. 4 is an example of processing in which original document image data 151 and postscript document image data 152 are input, a difference is detected, and breaks are repaired based on the detected difference data. The image processing apparatus shown in FIG. 4 includes a difference extraction unit 201, a process switching unit 202, a postscript line width detection unit 203, a thick line postscript defect part repair unit 204, and a thin line postscript defect part repair unit 205. Hereinafter, processing executed by each of these processing means will be described.

[Difference extraction means]
The difference extraction means 201 inputs original document image data 151 as image data read by a scanner or the like and additional record document image data 152 including additional notes not included in the original, and extracts differences from these documents. That is, the added information is read as difference information between two documents.

The difference extraction unit 201 extracts the difference between the original document image data 151 and the additionally-recorded document image data 152 that have been aligned, and outputs the additionally-recorded extracted image data 153. This process is the same as the conventional process, and is executed as a process similar to the process described in JP-A-2004-213230, JP-A-2004-341914, or the like. For example, the presence / absence of a difference between the coordinate position (x, y) of the original document image data 151 and the corresponding coordinate position (x, y) of the postscript document image data 152 is detected, and data is extracted only when the difference exists. .

An example of the difference extraction process will be described with reference to FIG. In the example shown in FIG. 5, difference extraction is performed from the original document 301 and the postscript document 302 as in FIG. 2 described above. The postscript document 202 includes postscript additional information 303 that is not included in the original original document 301. The difference extraction unit 201 performs difference extraction from the original document 301 and the additional writing document 302 to generate additional writing extracted image data 304. However, as can be understood from the figure, the extraction information included in the additionally-recorded extracted image data 304 obtained by the difference extraction has an overlapping portion with the original data (characters [1, 2, 3 that are originally described in the original shown in the figure]. ] Is an incomplete additional record data. This additional recording extracted image data corresponds to the additional recording extracted image data 153 output from the difference extraction unit 201 shown in FIG.

[Process switching means and additional line width detection means]
Processing of the process switching unit 202 and the additional write line width detection unit 203 will be described. The additional recording line width detection unit 203 detects the line width of additional recording information included in the additional recording extracted image data 153 output from the difference extraction unit 201 shown in FIG. 4, and the process switching unit 202 detects the additional recording line width detection unit 203. Based on the line width of the additional write information, it is determined which of the thick line additional write defect repairing unit 204 or the thin line additional write defect repairing unit 205 performs the repair process of the defective part included in the additional write information.

An example of a line width detection process for additional information in the additional line width detection unit 203 will be described with reference to FIG. Various methods can be applied to the processing method of the line width detection process of the postscript information. FIG. 6 shows an example. The additional write extracted image data 304 shown in FIG. 6 corresponds to the additional write extracted image data 153 output from the difference extraction unit 201 shown in FIG. The postscript line width detection unit 203 executes thinning processing of the postscript extracted image data 304. The thinning process is executed as a process of setting the line width of the additional recording information included in the additional recording extracted image data 304 to a 1-dot (pixel) width. An image generated by this thinning process is assumed to be thinned image data 305 shown in FIG.

The postscript line width detection unit 203 counts the total number of dots (N1) of the postscript information included in the postscript extracted image data 304 and the total number of dots (N2) of the thinned data included in the thinned image data 305, and adds the additional data The line width of the additional information included in the extracted image data 304 is calculated according to the following formula.
Additional information line width = N1 / N2

The process switching unit 202 determines whether the postscript information is a thick line or a thin line based on the line width (N1 / N2) of the postscript information included in the postscript extracted image data 304 calculated by the postscript line width detection unit 203. To do. This determination is performed based on, for example, a threshold value (Th) held by the process switching unit 202. For example,
Postscript information line width = N1 / N2 ≧ Th
If so, the postscript information is determined to be a thick line,
Postscript information line width = N1 / N2 <Th
If so, the additional information is determined to be a thin line.
When the process switching unit 202 determines that the additional recording information is a thick line, the additional recording extracted image data 153 as the repair processing target data is output to the thick line additional recording missing part repairing unit 204 shown in FIG. 4, when the additional writing information is determined to be a thin line, the additional writing extracted image data 153 as the repair processing target data is output to the thin line additional writing defect portion repairing unit 205 shown in FIG. The defect repair process is executed according to the processing sequence.

As described above, in the process of determining whether the line width of the additional information to be executed by the process switching unit 202 is thick or thin, as described above, a fixed numerical value may be used as a threshold value. Instead of a process of applying a numerical value as a threshold value, a determination process according to a document to be processed may be performed. That is, a configuration may be adopted in which the original document image data 151 is referenced to determine whether the additional writing information is larger or smaller than the overlapping characters.

For example, even if additional writing written with a 1 mm wide sign pen is recorded in the original document image data 151 as small characters such as 8 points, it is determined that the additional writing information is thick and written with a line marker of 4 mm wide. In addition to the additional writing, when a large character such as 36 points overlaps, processing such as determination as thin additional writing is executed, and based on the determination result, the thick line additional writing defect repairing unit 204 shown in FIG. The additionally extracted extracted image data 153 is output to the missing part repairing unit 205 as repair processing target data. Note that the additional information information line width determination processing and restoration means application switching processing can be performed in various units such as page units, line units, and character units. For example, referring to the original document image data 151, the line spacing of the character part may be detected, and a threshold value may be set as a boundary value between a thin line and a thick line corresponding to each line width.

In this way, when detecting the character size, line spacing, and the like, as shown in FIG. 7, the process switching unit 202 is configured to input the original document image data 151 to the characters with the additional information to be overlapped. It is determined whether the additional writing information is a thin line or a thick line depending on the line spacing.

In the case of determining whether the additional writing information is a thin line or a thick line based on the size of the character, the processing switching unit 202 detects the size of the character included in the original document image data 151. The detection means and a threshold value determination means for determining a threshold value for determining whether the additional writing information is a thick line additional writing or a thin line additional writing based on the character size. Note that a layout analysis technique used as a preprocessing for recognizing a character by OCR or the like can be applied to the character size detection process. Further, the threshold value determining means performs a process of setting and applying, for example, half of the character height as a threshold value based on the character outline (particularly height) detected by the character outline detecting means. To do.

In addition, when it is configured to determine whether the additional writing information is a thin line or a thick line based on the line interval, the line interval detecting means for detecting the line interval and the additional writing information according to the line interval are the thick line additional writing. It is assumed that there is a threshold value determining means for determining a threshold value for determining whether or not a thin line is additionally recorded. Note that a layout analysis technique used as a pre-process for recognizing characters by OCR or the like can be applied to the line interval detection process. Further, the threshold value determination unit is configured to perform processing such as setting and applying, for example, ½ of the line interval as a threshold value based on the line interval detected by the line interval detection unit.

[Thick line additional writing defect repairing means 204]
Next, processing in the thick line additional write defect portion repairing means 204 will be described. When it is determined that the postscript information is a thick line, the thick line postscript missing part repairing unit 204 executes a repair process for the missing part included in the postscript by a process suitable for the thick line.

The thick line additional writing defect portion repairing means 204 performs a repair process suitable for repairing the interruption of the thick additional writing. There are various methods for repair processing suitable for repairing the interruption of the thick additional writing. The repair processing to which one expansion processing is applied will be described with reference to FIG.

The thick line postscript missing part repairing unit 204 inputs the postscript extracted image data 304. This corresponds to the additionally recorded extracted image data 153 generated by the difference extracting unit 201 shown in FIG. The thick line additional write missing part repairing unit 204 executes expansion processing (thick line processing) on the additional write extracted image data 304. As shown in FIG. 8, the expansion process (thickening process) is a process of expanding additional information 311 having a defective part to be repaired up, down, left and right by n pixels. As a result of the expansion process, the short gap portions are joined and the discontinuity disappears. By this expansion processing, expansion processing image data 306 having additional information 312 in which the missing portion is eliminated is generated. The expansion amount n is determined according to the processing target image, for example, 3 to 10 pixels. The expansion processed image data 306 corresponds to the repair additional write extracted image data 155 output from the thick line additional write missing portion repair unit 204 shown in FIG.

It should be noted that the defect repair process executed by the thick line additional write defect repairing unit 204 is not limited to the above-described expansion process, and other techniques may be applied as long as the repair process is suitable for repairing a thick additional write break. For example, the expansion process is effective when the ratio between the thickness of the additional writing and the gap width is approximately 3 to 1 or less (the range in which the change in the thickness of the additional writing does not matter when the interruption is repaired by expansion), and the line marker Since thick additional writing satisfies this condition, it is a preferable processing as the repairing processing executed by the thick line additional writing missing portion repairing means 204.

[Thin wire added defect portion repair means 205]
Next, processing in the thin line additional write defect portion repair unit 205 will be described. When it is determined that the additional writing information is a thin line, the thin line additional write defect portion repairing unit 205 executes a repair process for the defective portion included in the additional write by a process suitable for the thin line.

The thin line additional write defect portion repairing unit 205 performs a repair process suitable for repairing the interruption of the thin additional write. There are various methods for repair processing suitable for repairing the interruption of the thin additional recording. One example of the repair processing is a thinning processing, an end point extraction processing, and an end point connection processing. Will be described with reference to FIG.

The thin line additional write defect portion repairing unit 205 inputs the additional write extracted image data 304 shown in FIG. This corresponds to the additionally recorded extracted image data 153 generated by the difference extracting unit 201 shown in FIG. The thin line additional write defect portion repair unit 205 includes a thinning unit, and the thin line unit performs thinning processing of the additional write information including the defective portion included in the additional write extraction image data 304, thereby reducing the thinned image data. 321 is generated. The thinning processed image data 321 is data obtained by thinning the postscript information with a width of, for example, one pixel.

The thin line additional writing defect portion repairing unit 205 further includes an end point extracting unit and an end point connecting unit, and extracts the end points from the thinned additional recording information included in the thin line processing image data 321 and connects the extracted end points. Execute. This process will be described with reference to FIG. 10, FIG. 11, and FIG. As shown in FIG. 10, the end point extraction unit of the thin line additional write defect portion repair unit 205 extracts the end point from the thinned additional recording information included in the thinning processed image data 321. The endpoint extraction data 322 shown in the figure shows an example in which six endpoints P1 to P6 are extracted.

Furthermore, as shown in FIG. 11, the end point connecting means of the thin line added defect portion repairing means 205 determines the connection relation of the end points from the end point extracted data 322, and generates the connected end point pair extracted data 323. The connection end point pair extraction process is executed by applying one of the following three processes, for example.
a: The nearest end point of the end point as the search target of the connection end point pair is searched, and the end point within a predetermined threshold distance is set as the connection end point.
b: The extension direction of the line segment is calculated from several dots constituting the line segment connected to the end point as the search target of the connection end point pair, and the closest end point in the direction is set as the connection end point.
c: A fitting curve of the line segment is calculated from tens of dots constituting the line segment connected to the end point to be searched for the connection end point pair, and the closest end point located on the extension of the curve is set as the connection end point. .

When two end points corresponding to any one of these a to c are detected, the end point connecting unit of the thin line added defect portion repair unit 205 extracts and connects them as a connecting end point pair, and executes processing for connecting them. The example of the connection end point pair extraction data 323 shown in FIG. 11 shows an example in which the end point P2 and the end point P3, and the end point P4 and the end point P5 are extracted as connection end point pairs.

As illustrated in FIG. 12, the end point connection unit of the thin line added defect portion repair unit 205 executes the connection process between the connection end point pairs of the connection end point pair extraction data 323 to generate end point connection data 324. As a result of this processing, end point connection data 324 shown in FIG. 12 is generated. This end point connection data 324 corresponds to the repair additional record extracted image data 155 output from the thin line additional record missing portion repair unit 205 shown in FIG.

Note that the end point connection data 324 generated by the thin line added defect portion repairing unit 205 is still thin line data as shown in FIG. 12, so that this data is subjected to expansion processing and output as a thick line. It is good. The expansion process (thickening process) is a process of expanding an effective image area such as a line segment up, down, left, and right by n pixels. By this processing, the thinned data is expanded and restored to a thick line. The expansion processing result data may be output as the repair additional write extracted image data 155.

As described above, in the image processing apparatus of the present invention, the thick line and the thin line added by the thick line additional write defect repairing unit 204 and the thin line additional write defect repairing unit 205 according to the line width of the additional write information having the defective part, respectively. Since the processing adapted to the repair of the missing portion is executed, more accurate additional information restoration is realized by the optimum restoration adapted to the line width of each additional information.

Next, a processing sequence executed in the image processing apparatus shown in FIG. 4 will be described with reference to the flowchart shown in FIG. First, in step S101, postscript document image data including postscript information is acquired. This is image data read by, for example, a scanner. In step S102, original document image data that does not include additional writing is acquired. This is also image data read by, for example, a scanner.

In step S103, a difference extraction process based on these two image data is executed. This is a process in the difference extraction means 201 shown in FIG. 4, and as a result, additional extracted image data is generated. However, this postscript extracted image data is data including a missing portion in which an overlap portion of the postscript information and the original information is missing.

The processes of the next steps S104 to S107 are the processes of the postscript line width detection unit 203 shown in FIG. As described above with reference to FIG. 6, the postscript line width detection unit 203 first calculates the total number of dots (N1) of the postscript information (effective pixels) included in the postscript extraction image data in step S104. . Next, in step S105, thinning processing of the additionally recorded extracted image data is executed, and in step S106, the total number of dots (N2) of the thinned data (effective pixels) of the additionally recorded extracted image data is counted. Furthermore, in step S107, the line width of the additional recording information included in the additional recording extracted image data is calculated according to the following equation.
Additional information line width = N1 / N2

The determination process of the next step S108 is the process of the process switching unit 202 shown in FIG. 4 and is executed based on the threshold value (Th) held by the process switching unit 202. For example,
Postscript information line width = N1 / N2 ≧ Th
If so, the postscript information is determined to be a thick line,
Postscript information line width = N1 / N2 <Th
If it is determined that the additional writing information is a thin line, and it is determined that the additional writing information is a thick line, the additional writing extracted image data 153 as the repair processing target data is output to the thick line additional writing defect portion repairing unit 204 shown in FIG. If it is determined that the line is a thin line, the additionally-recorded extracted image data 153 is output to the thin line additional write missing part repairing unit 205 as the repair process target data. Note that, as described above, this determination processing may be configured to perform determination processing in consideration of character size, line spacing, and the like.

The process of step S109 is a defective portion repair process for the thick line executed by the thick line additional write defective portion repair unit 204 shown in FIG. 4 when it is determined that the additional write information is a thick line. This process is executed as an expansion process, for example, as described above with reference to FIG.

The process of step S110 is a defective portion repair process for a thin line, which is executed by the thin line additional write defective portion repair unit 205 shown in FIG. 4 when it is determined that the additional write information is a thin line. As described above with reference to FIGS. 9 to 12, this process is executed as a process involving a thinning process, an endpoint extraction process, and an endpoint connection process. Furthermore, it is good also as a structure which finally performs an expansion process.

By these processes, the defective portion corresponding to the line width of the additional writing information having the defective portion is repaired, and repair additional extracted image data is generated. In the image processing of the present invention, the thick line additional write defect repairing unit 204 and the thin line additional write defect repairing unit 205 shown in FIG. By the optimum restoration adapted to the line width of the additional information, the additional information can be restored with higher accuracy.

Note that the processing of the thick line additional write defect portion repairing means 204 and the thin line additional write defect portion repairing means 205, that is, the processing of steps S109 and S110 in the processing flow shown in FIG. 13, can be executed in parallel. The thin line additional recording information and the thick line additional recording information included in the target document may be classified, and the defective portion repair processing may be executed in parallel in each repairing unit.

In the image processing apparatus shown in FIG. 4, first, the original document image data 151 and the additional record document image data 152 including the additional notes that are not included in the original are input to the difference extracting means 201, and the additional information is obtained by differential extraction. It was set as the structure which performs the process to extract.

When performing differential extraction, an original document is required, but it may be possible to extract postscript information by inputting only the postscript document. For example, in the case of a postscript document in which the original recording information is recorded in black and the postscript is recorded in red, the postscript information is extracted by color identification processing that extracts only the information recorded in red from the postscript document. Extraction is possible.

FIG. 14 shows such an image processing apparatus configuration. The difference between the image processing apparatus shown in FIG. 14 and the image processing apparatus shown in FIG. 4 is that the difference extracting unit 201 in FIG. 4 is changed to the color extracting unit 401 in FIG. This is the only point. Other configurations and processes are the same as the processes and configurations described with reference to FIG.

The image processing apparatus shown in FIG. 14 is applicable when the color of character information or the like included in the original document is different from the color of the added information. For example, this is the case when the original is recorded entirely with black characters and line segments, and the additional writing is made in red. The color extraction unit 401 inputs the postscript document image data 152 including the postscript, and extracts information having a color (for example, red) corresponding to the postscript information as the postscript information from the postscript document image data 152. The color information of the additional information is processed by the user.

The additional recording information extracted by the color extraction unit 401 is interrupted in the overlap with the information included in the original, similarly to the additional recording information generated by the difference extraction unit 201 described above with reference to FIG. There is a case. For example, there is a case where the additionally recorded red color recorded on the black characters included in the original is not accurately recognized as red but is recognized as black. This is because they may not be identified.

Similar to the embodiment described above with reference to FIG. 4 and the like, such a discontinuous portion is respectively detected in the thick line additional write defect repairing means 204 and the thin line additional write defect repairing means 205 according to the line width of the additional write information. The restoration process is executed, and finally the repair additional record extracted image data 154 composed of accurate additional record information is generated.

Further, a configuration example using ruled line separation means 402 instead of the difference extraction means will be described with reference to FIG. The difference between the configuration shown in FIG. 15 and the configuration shown in FIG. 4 is that the difference extraction unit 201 shown in FIG. 4 is changed to a ruled line separation unit 402 and the input information is only the postscript document image data 152. Other configurations and processes are the same as the processes and configurations described with reference to FIG.

The image processing apparatus shown in FIG. 15 extracts character information or the like as additional information that does not include a ruled line when the original document is composed of ruled line information such as a table and characters and the like are recorded in the table as additional information. It becomes effective when doing. The ruled line separation unit 402 inputs the postscript document image data 152 including the postscript, and extracts the postscript information in which only the ruled line is deleted from the postscript document image data 152.

The additional writing information extracted by the ruled line separation unit 402 is also interrupted in the overlap with the information included in the original, similarly to the additional writing information generated by the difference extraction unit 201 described above with reference to FIG. There is a case. This is because, for example, the additional writing information recorded on the ruled line included in the original is deleted as the ruled line information and is not included in the extracted additional writing information.

Similar to the embodiment described above with reference to FIG. 4 and the like, such a discontinuous portion is respectively detected in the thick line additional write defect repairing means 204 and the thin line additional write defect repairing means 205 according to the line width of the additional write information. The restoration process is executed, and finally the repair additional record extracted image data 154 composed of accurate additional record information is generated.

Next, a further embodiment of the image processing apparatus of the present invention will be described with reference to FIG. The image processing apparatus shown in FIG. 16 applies the additionally-recorded extracted image data 153 generated by the difference extracting unit 201 to the thick-line additional-deletion part repairing unit 204 described above with reference to FIG. 4 regardless of the line width of the additional recording information. Processing is performed in parallel by both of the first additional write defect repairing unit 451 that executes the corresponding process and the second additional write defect repairing unit 452 that performs the process corresponding to the thin line additional write defect repairing unit 205. Further, in the OR processing means 453, the OR processing of the output of the first additional write defect portion repair means 451 and the output of the second additional write defect portion repair means 452 is executed, and this processing result is output as repair additional write extraction image data 155. It is a configuration.

FIG. 17 is a block diagram showing the first additional write defect repairing means 451 and the second additional write defect repairing means 452 shown in FIG. 16 as specific processing means. 16 corresponds to the expansion processing means 454 shown in FIG. 16 corresponds to the thinning means 455, the end point extraction means 456, the end point connection means 457, and the expansion processing means 458 shown in FIG.

A specific processing example executed by the image processing apparatus according to the present exemplary embodiment will be described with reference to FIG. The postscript extraction image data 461 shown in FIG. 18 corresponds to the postscript extraction image data 153 generated by the difference extraction unit 201 shown in FIG. The additionally extracted extracted image data is subjected to expansion processing in the expansion processing means 454 shown in FIG. 17, and expansion processing image data 462 shown in FIG. 18 is generated. By the expansion process, the minute discontinuity included in the additionally recorded extracted image data 461 is repaired, but as shown in the expansion process image data 462, the large discontinuity is not repaired and remains.

In parallel with this expansion processing, the postscript extracted image data 461 is also processed in the thinning unit 455, the end point extraction unit 456, the end point connection unit 457, and the expansion processing unit 458 shown in FIG. The processing in the thinning unit 455, the end point extraction unit 456, and the end point connection unit 457 is the processing described with reference to FIGS. 9 to 12 in the previous embodiment. After the thinning process, the end points of the thinned data are processed. Is extracted, end point pairs are detected and connected. The data after this end point connection is end point connection thinned data 465 shown in FIG.

Furthermore, the expansion processing means 458 shown in FIG. 17 executes the expansion processing of the end point connection thinned data 465 to generate the expanded end point connection thinned data 466 shown in FIG. The OR processing unit 453 illustrated in FIG. 17 performs an OR process between the processing result of the expansion processing unit 454 and the processing result of the expansion processing unit 458. That is, the dilated image data 462 and dilated end point connection thinning data 466 shown in FIG. 18 are input, and OR processing of these images is executed. As a result of this OR processing, the missing portion of one of the images is compensated by the other image, and is generated as OR processing data 467. This OR processing data 457 corresponds to the repair additional recording extracted image data 155 output from the OR processing means shown in FIG.

As described above, in this processing example, the means for executing the defective portion repair processing of two different processing sequences is executed in parallel to execute the defective portion repair of the same additional information, regardless of the line width of the additional information, and the result By performing an OR process on an image, it becomes possible to supplement a portion that has not been repaired by one repairing unit by applying data repaired by the other repairing unit, thereby realizing a more complete repairing process.

With reference to FIG. 19 and FIG. 20, description will be given of a repair processing example in the case where the postscript information is executed with a thick line such as a line marker. FIG. 19 shows an original document 491 and an additional record document 492 including additional information 493 using line markers. The difference extraction unit 201 shown in FIG. 17 extracts the difference from both of these documents, and obtains the postscript extracted image data 494.

The postscript extracted image data 494 includes a missing part (1, 2, 3 character constituent parts). With respect to the postscript extracted image data including the defective portion, the first and second defective portion repairing means execute a defective portion repair process using different processing sequences. This process will be described with reference to FIG.

The postscript extracted image data 494 shown in FIG. 20 corresponds to the postscript extracted image data 153 extracted by the difference extracting unit 201 shown in FIG. This additional record extracted image data is subjected to expansion processing in the expansion processing means 454 shown in FIG. 17, and expansion processing image data 495 shown in FIG. 20 is generated. By the expansion process, the minute interruption included in the additionally recorded extracted image data 494 is repaired. In this case, an example in which all interruptions are eliminated is shown.

In parallel with this expansion processing, the postscript extracted image data 494 is also processed in the thinning unit 455, the end point extraction unit 456, the end point connection unit 457, and the expansion processing unit 458 shown in FIG. The thinning unit 455 executes thinning processing on the additionally extracted extracted image data 494 to generate thinning data 496 shown in FIG. The end point connection and expansion processing for the thinned data is executed, and expanded thinned data 597 shown in FIG. 20 is generated.

The OR processing unit 453 illustrated in FIG. 17 performs an OR process between the processing result of the expansion processing unit 454 and the processing result of the expansion processing unit 458. That is, the dilated image data 495 and dilated thinned data 497 shown in FIG. 20 are input, and OR processing of these images is executed. As a result of this OR processing, the missing portion of one of the images is compensated by the other image, and is generated as OR processing data 498. This OR processing data 498 corresponds to the repair additional extraction extracted image data 155 output from the OR processing means shown in FIG.

A processing sequence in this processing example will be described with reference to the flowchart shown in FIG. First, in step S201, postscript document image data including postscript information is acquired. This is image data read by, for example, a scanner. In step S202, original document image data that does not include additional writing is acquired. This is also image data read by, for example, a scanner.

In step S203, a difference extraction process based on these two image data is executed. This is a process in the difference extraction means 201 shown in FIG. 16 or FIG. 17, and as a result, additional record extracted image data is generated. However, this postscript extracted image data is data including a missing portion in which an overlap portion of the postscript information and the original information is missing.

The processes in steps S204 and S205 are the processes of the first additional write defect repair unit 451 and the second additional write defect repair unit 452 shown in FIG. In FIG. 17, this corresponds to the processing of the expansion processing means 454 (S204) and the processing of the thinning means 455 to the expansion processing means 458 (S205).

The first additional write defect portion repairing means 451 shown in FIG. 16, that is, the expansion processing means 454 shown in FIG. 17, executes the expansion processing of the additional write extracted image data having the defective portion in step S204. In addition, the second additional write defect portion repairing means 452 shown in FIG. 16, that is, the thinning means 455 to the expansion processing means 458 shown in FIG. Extraction processing, end point connection processing, and expansion processing are executed.

Finally, in step S206, the OR processing means 453 shown in FIGS. 16 and 17 performs OR processing of the repaired images executed in two different sequences, and this OR processing result image is extracted as the final repair appending extraction. Output as image data.

By these processes, the postscript information having a defective part is repaired in a plurality of different processing sequences, and finally the repair process result is ORed so that it is not repaired by one repair process. The part can be supplemented by the result of the other repair process, and a repair additional image with more reliable repair can be obtained.

Finally, with reference to FIG. 22, an example of the hardware configuration of the image processing apparatus that executes the above-described processing will be described. The configuration illustrated in FIG. 22 illustrates a hardware configuration example including an information processing apparatus such as a PC, an image data reading unit 531 such as a scanner, and an image data output unit 532 such as a printer.

A CPU (Central Processing Unit) 501 performs various types of data processing described in the above-described embodiments, that is, data extraction processing including a missing portion such as difference data, line width determination processing for additional information, and expansion processing for processing target data , A series of processing including thinning processing, end point extraction, connection processing, OR processing, and the like is executed. A CPU 501 serving as a control unit executes processing according to a computer program describing an execution sequence of these processing.

A ROM (Read Only Memory) 502 stores programs used by the CPU 501, calculation parameters, and the like. A RAM (Random Access Memory) 503 stores programs used in the execution of the CPU 501, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 504 including a CPU bus.

The host bus 504 is connected to an external bus 506 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 505.

A keyboard 508 and a pointing device 509 are input devices operated by the user. The display 510 includes a liquid crystal display device, a CRT (Cathode Ray Tube), or the like, and displays various information as text or image information.

An HDD (Hard Disk Drive) 511 includes a hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 501 and information. The hard disk stores information such as original document image data and postscript document image data, data generated in various processes, and the like. Further, various computer programs such as various data processing programs are stored.

The drive 512 reads data or a program recorded on a removable recording medium 521 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and the data or program is read out from the interface 507 and the external bus 506. , And supplied to the RAM 503 connected via the bridge 505 and the host bus 504. The removable recording medium 521 can also be used as a data recording area similar to a hard disk.

The connection port 514 is a port for connecting the external connection device 522 and has a connection unit such as USB or IEEE1394. The connection port 514 is connected to the CPU 501 and the like via the interface 507, the external bus 506, the bridge 505, the host bus 504, and the like. The communication unit 515 is connected to a network and executes data communication processing with the outside. The data reading unit 531 executes document reading processing, and the data output unit 532 executes document data output processing.

Note that the hardware configuration example of the image processing apparatus shown in FIG. 22 shows one example of the apparatus, and the image processing apparatus of the present invention is not limited to the configuration shown in FIG. Any configuration capable of executing the process may be used.

The present invention has been described in detail above with reference to specific embodiments. However, it is obvious that those skilled in the art can make modifications and substitutions of the embodiments without departing from the gist of the present invention. In other words, the present invention has been disclosed in the form of exemplification, and should not be interpreted in a limited manner. In order to determine the gist of the present invention, the claims should be taken into consideration.

The series of processes described in the specification can be executed by hardware, software, or a combined configuration of both. When executing processing by software, the program recording the processing sequence is installed in a memory in a computer incorporated in dedicated hardware and executed, or the program is executed on a general-purpose computer capable of executing various processing. It can be installed and run.

For example, the program can be recorded in advance on a hard disk or ROM (Read Only Memory) as a recording medium. Alternatively, the program is temporarily or permanently stored on a removable recording medium such as a flexible disk, a CD-ROM (Compact Disc Read Only Memory), an MO (Magneto optical) disk, a DVD (Digital Versatile Disc), a magnetic disk, or a semiconductor memory. It can be stored (recorded). Such a removable recording medium can be provided as so-called package software.

The program is installed on the computer from the removable recording medium as described above, or is wirelessly transferred from the download site to the computer, or is wired to the computer via a network such as a LAN (Local Area Network) or the Internet. The computer can receive the program transferred in this manner and install it on a recording medium such as a built-in hard disk.

Note that the various processes described in the specification are not only executed in time series according to the description, but may be executed in parallel or individually according to the processing capability of the apparatus that executes the processes or as necessary. Further, in this specification, the system is a logical set configuration of a plurality of devices, and the devices of each configuration are not limited to being in the same casing.

As described above, according to the configuration of the present invention, for example, it is possible to efficiently perform a repair process for eliminating a missing portion of data having a missing portion, such as difference data between an original document and an additional document to which additional data is added. Can be executed efficiently and accurately. Specifically, in the configuration of an embodiment of the image processing apparatus of the present invention, the line width of the postscript information having a defect portion included in the postscript extracted image is detected, and the line width is thin and the case where the line width is thick, respectively. Execute defect repair processing according to the processing sequence that matches the line width. Specifically, when the additional writing information is a thick line, restoration by expansion processing is executed, and when it is a thin line, restoration processing by thinning processing, endpoint extraction processing, and endpoint connection processing is executed. With this configuration, it is possible to optimally repair the missing portion according to the line width, and it is possible to generate additional information with higher accuracy.

Further, according to the configuration of one embodiment of the present invention, the missing information repair processing of the additional information by a plurality of different processing sequences is performed in parallel, and an OR processing result based on the plurality of processing results is generated, and this OR The processing result is the final defect repair result. According to this configuration, it is possible to compensate for a defective portion that could not be repaired in one repair processing sequence based on the result of the other repair processing sequence, and as a result, it is possible to generate additional information with higher completeness. It becomes.

DESCRIPTION OF SYMBOLS 10 Original document 20 Additional record document 30 Scanner 51 Original document 52 Additional record document 53 Line segment data 55 Additional record information 61 Additional record document 62 Additional record information 71 Ruled line document 72 Ruled line removal information 100 Image processing apparatus 151 Original document image data 152 Additional record document image data 153 Additional write extraction image data 155 Repair additional write extraction image data 201 Difference extraction means 202 Processing switching means 203 Additional write line width detection means 204 Thick line additional write defect portion repair means 205 Thick line additional write defect portion repair means 301 Original document image data 302 Additional write document image data 303 Additional write Information 304 Additional recording extracted image data 305 Thinned image data 306 Expansion processing image data 321 Thinning processing image data 322 Endpoint extraction Data 323 Connection end point pair extraction data 324 End point connection data 401 Color extraction means 402 Ruled line separation means 451 First additional write defect portion repair means 452 Second additional write defect portion repair means 453 OR means 454 Expansion processing means 455 Thinning means 456 End point extraction means 457 End point connection means 458 Dilation means 461 Additional write extraction image data 462 Dilation processing image data 465 End connection thinning data 466 Dilation processing end point connection thinning data 467 OR processing data 491 Original document 492 Additional writing document 493 Additional writing information 494 Additional writing extraction image data 495 Expansion processing image data 496 Thinning data 497 Expansion processing thinning data 498 OR processing data 501 CPU (Central Processing Unit)
502 ROM (Read-Only-Memory)
503 RAM (Random Access Memory)
504 Host bus 505 Bridge 506 External bus 507 Interface 508 Keyboard 509 Pointing device 510 Display 511 HDD (Hard Disk Drive)
512 drive 514 connection port 515 communication unit 521 removable recording medium 522 external connection device 531 data reading unit 532 data output unit

Claims (8)

It is an image processing apparatus that performs image processing to input restoration target data having a missing part and generate restoration data that eliminates the missing part,
A postscript information extraction unit that inputs postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generates a postscript extraction image obtained by extracting the postscript information from the postscript document image;
A first additional write defect repairing unit that inputs the additional write extraction image generated by the additional write information extraction unit and executes the additional write defect repairing process according to a predetermined first processing sequence;
Second write-once deficient part repairing means for inputting a postscript extracted image generated by the postscript information extracting means and executing a postscript missing part repairing process according to a predetermined second processing sequence different from the first processing sequence When,
OR processing means for executing final processing of the processing result of the first additional writing defect portion repairing means and the processing result of the second additional writing defect portion repairing means to generate final additional writing defect portion repair processing result data ,
An image processing apparatus comprising: The first additional write defect portion repairing means has an expansion processing means,
The image processing apparatus according to claim 1, wherein a defect portion repair process is performed by an expansion process of additional write information included in the additional write extracted image generated by the additional write information extraction unit. The second additional write defect repairing means has a thinning means, an endpoint extraction means, an endpoint connection means and an expansion processing means,
The thinning means executes thinning processing on the additional writing information included in the postscript extraction image generated by the additional writing information extraction means, the endpoint extraction means executes endpoint extraction processing based on the thinning processing result, and the endpoint In the connection means, the extraction end point connection processing is executed, and in the expansion processing means, the end point connection data generated by the extraction end point connection processing in the end point connection means is executed, and the defect portion repair processing is executed. The image processing apparatus according to claim 1, wherein the image processing apparatus is configured as described above. The additional information extracting means is
2. The image processing apparatus according to claim 1, further comprising: difference extraction means for inputting original document image data and the additional document image data and extracting a difference between the two input image data. The additional information extracting means is
The image processing apparatus according to claim 1, further comprising a color extracting unit that inputs additional document image data and extracts recording information of a specific color from the additional document image data as additional information. The additional information extracting means is
2. The image according to claim 1, further comprising ruled line separation means for inputting additional record document image data, deleting ruled line information from the additional record document image data, and extracting information other than the ruled line information as additional record information. Processing equipment. It is an image processing method for inputting image data to be repaired having a missing part and executing image processing to generate restoration data in which the missing part is eliminated,
A postscript information extraction step of inputting postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generating a postscript extraction image obtained by extracting the postscript information from the postscript document image;
A first additional write defect repair step that inputs the additional write extracted image generated in the additional write information extraction step and executes the additional write defect repair process according to a predetermined first processing sequence;
Second write-once defect portion repair step of inputting the postscript extraction image generated in the postscript information extraction step and executing the post-write defect portion repairing process according to a predetermined second processing sequence different from the first processing sequence When,
An OR processing step of performing OR processing of the processing result in the first additional write defect portion repair step and the processing result in the second additional write defect portion repair step to generate final additional write defect portion repair processing result data; ,
An image processing method comprising: In the image processing apparatus, a computer program for executing image processing for inputting restoration target data having a defect portion and generating restoration data in which the defect portion is eliminated,
A postscript information extraction step of inputting postscript document image data based on a postscript process that has been postscripted with respect to the original document, and generating a postscript extraction image obtained by extracting the postscript information from the postscript document image;
A first additional write defect repair step that inputs the additional write extracted image generated in the additional write information extraction step and executes the additional write defect repair process according to a predetermined first processing sequence;
Second write-once defect portion repair step of inputting the postscript extraction image generated in the postscript information extraction step and executing the post-write defect portion repairing process according to a predetermined second processing sequence different from the first processing sequence When,
An OR processing step of performing OR processing of the processing result in the first additional write defect portion repair step and the processing result in the second additional write defect portion repair step to generate final additional write defect portion repair processing result data; ,
A computer program for executing