JP2019009632A - Script size detection apparatus, script size detection program, and image processing system - Google Patents

Abstract

To provide a script size detection apparatus capable of detecting a script size, without requiring an instruction of the script size by an operator, when a script image is read by a reading device.SOLUTION: First acquisition means of a script size detection apparatus acquires a first image, i.e., the entire image of a script becoming a reading object, second acquisition means acquires a second image, i.e., a partial image of the script read by a reading device, and detection means detects the script size by using matching results of the first and second images and a reading size, i.e., the size of the second image read by the reading device.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a document size detection device, a document size detection program, and an image processing system.

  Japanese Patent Application Laid-Open No. 2004-228867 allows a simple operation to be performed without using a special image extraction unit when a large-size document is divided and read and combined into a single image and output. The predetermined angle of the original is abutted against the register of the image reading unit, the image of the original is read and stored in the image storage unit, and then the predetermined angle of the original is imaged by rotating the original by a predetermined angle. Abutting against the register of the reading unit, similarly reading the original image and storing it in the image storage unit, the document size, copy magnification, and readable size are known, and the position of the register is fixed, so the read image is stored in the image It is disclosed that a writing start address is calculated in advance and stored in an image storage unit in a predetermined direction from the writing start address prior to storage in the image storage unit.

Japanese Patent Laid-Open No. 10-229487

When a document image is read by the reading device, the reading device may need to grasp the document size.
The present invention provides a document size detection device, a document size detection program, and an image processing system that can detect a document size without an operator specifying the document size when a document image is read by a reading device. The purpose is that.

The gist of the present invention for achieving the object lies in the inventions of the following items.
According to the first aspect of the present invention, a first acquisition unit that acquires a first image that is an entire image of a document to be read, and a second image that is a partial image of the document read by the reading device. Using the second acquisition means for acquiring the image, the result of matching between the first image and the second image, and the reading size that is the size of the reading of the second image by the reading device. A document size detecting apparatus having a detecting means for detecting the size of the document.

  According to a second aspect of the present invention, there is further provided guide means for guiding a reading procedure to the operator when the original is read by the reading device in a plurality of times using the size of the original and the reading size. The document size detection apparatus according to Item 1.

  The invention according to claim 3 is the document size detection device according to claim 2, wherein the reading procedure includes an instruction of which region of the document is to be read by the reading device at each reading.

  According to a fourth aspect of the present invention, in the reading procedure, an instruction as to which position or orientation of the original is to be set on the reading device at each reading is provided. This is a document size detection device.

  The invention according to claim 5 is the document size detection apparatus according to claim 2, wherein the reading procedure includes an instruction of the number of times of reading the document.

  The invention according to claim 6 is the document size detecting device according to claim 2, wherein the reading procedure includes an instruction as to whether or not reading is further required after at least one reading is completed.

  According to a seventh aspect of the invention, the first acquisition unit is a second reading device different from the reading device, and uses the second reading device having a reading accuracy lower than that of the reading device. The document size detection apparatus according to claim 2, wherein a result of reading the entire area is acquired.

  The invention according to claim 8 is the method according to claim 1, wherein the detection unit calculates a ratio of an area occupied by an image corresponding to the second image in the first image from a result of the matching process. This is a document size detection apparatus.

  The invention according to claim 9 is the document size detection apparatus according to claim 8, wherein the detection means detects the size of the document by using the ratio and the read size.

  According to a tenth aspect of the present invention, the detection means calculates a ratio between a width ratio and a height ratio of an area occupied by an image corresponding to the second image in the first image from the result of the matching process. The document size detecting device according to claim 9.

11. The document size detection apparatus according to claim 10, wherein the detection unit detects the width and height of the document using the width ratio, the height ratio, and the reading size. It is.

  The invention according to claim 12 is the document size detection device according to claim 2, wherein the guide unit determines a reading procedure according to the size of the document and the readable size of the second acquisition unit.

  According to a thirteenth aspect of the present invention, the guide means determines a reading procedure so that the width or height of the readable size is longer than or greater than the width or height of the original size. The document size detecting device described in 1. above.

  According to a fourteenth aspect of the present invention, in the document size detecting apparatus according to the twelfth aspect, the guide means determines a reading procedure so as to read the overlapping document areas when reading adjacent areas.

  According to a fifteenth aspect of the present invention, a computer is a first acquisition unit that acquires a first image that is an entire image of a document to be read, and a first image that is a part of the document read by the reading device. Second acquisition means for acquiring the second image, a result of matching processing between the first image and the second image, and a reading size that is a size obtained by reading the second image with the reading device. , A document size detection program for functioning as detection means for detecting the size of the document.

  According to a sixteenth aspect of the present invention, there is provided a document size detecting device, a reading device, and an image synthesizing device, wherein the document size detecting device acquires a first image that is an entire image of a document to be read. An acquisition unit; a second acquisition unit that acquires a second image that is a partial image of the document read by the reading device; and a result of a matching process between the first image and the second image. Detecting means for detecting the size of the document using a reading size that is a size obtained by reading the second image by the reading device, and the reading device has reading means for reading the document, The image composition device is an image processing system having composition means for compositing a plurality of images read by the reading device.

  According to a seventeenth aspect of the present invention, (1) the reading device includes the document size detection device, (2) the reading device includes the image composition device, and (3) the reading device includes the image composition device and the document. The image processing system according to claim 16, further comprising a size detection device.

  According to the document size detection apparatus of the first aspect, when the document image is read by the reading device, the document size can be detected without an operator specifying the document size.

  According to the document size detection apparatus of the second aspect, it is possible to guide the reading procedure when the document is read by the reading device in a plurality of times.

  According to the document size detection apparatus of the third aspect, the reading procedure can include an instruction as to which area in the document is to be read by the reading device at each reading.

  According to the document size detection apparatus of the fourth aspect, the reading procedure can include an instruction as to which position or orientation of the document is to be set in the reading device at each reading.

  According to the document size detection apparatus of the fifth aspect, the instruction of the number of times of reading the document can be included as the reading procedure.

  According to the document size detecting apparatus of the sixth aspect, the reading procedure can include an instruction as to whether or not reading is necessary after reading at least once.

  According to the document size detection apparatus of the seventh aspect, it is possible to acquire the result of reading the entire area of the document using the second reading device having a reading accuracy lower than that of the target reading device.

  According to the document size detection apparatus of the eighth aspect, it is possible to calculate the ratio of the area occupied by the image corresponding to the second image in the first image.

  According to the document size detection apparatus of the ninth aspect, the size of the document can be detected by using the ratio and the read size.

  According to the document size detection apparatus of the tenth aspect, it is possible to cope with a document size outside the standard.

  According to the document size detection apparatus of the eleventh aspect, the width and height of the document can be detected.

  According to the document size detection apparatus of the twelfth aspect, the reading procedure can be determined according to the readable size of the second acquisition means and the size of the document.

  According to the document size detecting apparatus of the thirteenth aspect, the reading procedure can be determined so that the width or height of the readable size is longer or larger than the width or height of the document size.

  According to the document size detection apparatus of the fourteenth aspect, when reading adjacent areas, it is possible to determine the reading procedure so that the document areas are read overlappingly.

  According to the document size detection program of the fifteenth aspect, when the document image is read by the reading device, the document size can be detected without an operator specifying the document size.

  According to the image processing system of the sixteenth aspect, when the document image is read by the reading device, the document size can be detected without an operator specifying the document size.

  According to the image processing system of claim 17, (1) a mode in which the reading device has a document size detection device, (2) a mode in which the reading device has an image composition device, and (3) the reading device has an image composition device and a document size. It can be either of the form which has a detection apparatus.

It is a conceptual module block diagram about the structural example of this Embodiment. It is explanatory drawing which shows the system configuration example using this Embodiment. It is explanatory drawing which shows the system configuration example using this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the example of a data structure of a camera image size table. It is explanatory drawing which shows the example of a data structure of a scanning image size table. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the example of a data structure of a reader / readable size correspondence table. It is explanatory drawing which shows the process example by this Embodiment. It is explanatory drawing which shows the process example by this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Hereinafter, an example of a preferred embodiment for realizing the present invention will be described with reference to the drawings.
FIG. 1 shows a conceptual module configuration diagram of a configuration example of the present embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment is a computer program for causing these modules to function (a program for causing a computer to execute each procedure, a program for causing a computer to function as each means, and a function for each computer. This also serves as an explanation of the program and system and method for realizing the above. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used. However, when the embodiment is a computer program, these words are stored in a storage device or stored in memory. This means that control is performed so as to be stored in the apparatus. Modules may correspond to functions one-to-one, but in mounting, one module may be configured by one program, or a plurality of modules may be configured by one program, and conversely, one module May be composed of a plurality of programs. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. Hereinafter, “connection” is used not only for physical connection but also for logical connection (data exchange, instruction, reference relationship between data, etc.). “Predetermined” means that the process is determined before the target process, and not only before the process according to this embodiment starts but also after the process according to this embodiment starts. Also, if it is before the target processing, it is used in accordance with the situation / status at that time or with the intention to be decided according to the status / status up to that point. When there are a plurality of “predetermined values”, they may be different values, or two or more values (of course, including all values) may be the same. In addition, the description of “do B when A” is used to mean “determine whether or not A and do B when A”. However, the case where it is not necessary to determine whether or not A is excluded. In addition, when enumerating things such as “A, B, C”, etc., it is an enumerated list unless otherwise specified, and includes cases where only one of them is selected (for example, only A).
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc., and one computer, hardware, device. The case where it implement | achieves by etc. is also included. “Apparatus” and “system” are used as synonymous terms. Of course, the “system” does not include a social “mechanism” (social system) that is an artificial arrangement.
In addition, when performing a plurality of processes in each module or in each module, the target information is read from the storage device for each process, and the processing result is written to the storage device after performing the processing. is there. Therefore, description of reading from the storage device before processing and writing to the storage device after processing may be omitted. Here, the storage device may include a hard disk, a RAM (Random Access Memory), an external storage medium, a storage device via a communication line, a register in a CPU (Central Processing Unit), and the like.

  The document size detection apparatus 100 according to the present embodiment detects the size of a document and includes an image acquisition A module 105, an image acquisition B module 110, and a guide module 115 as shown in the example of FIG. doing. If the reading method guidance is not required, the reading size / readable size extraction module 130, the procedure generation module 135, and the procedure presentation module 140 in the guidance module 115 may be unnecessary.

Further, by including the reading size / readable size extraction module 130, the procedure generation module 135, and the procedure presentation module 140 in the guide module 115, the document size detection apparatus 100 has a size larger than the area readable by the reading apparatus. It is also possible to present guidance for causing a reading device to read a document image having a number of times divided by the reading device.
Conventionally, a method of reading a document image using a reading device is known. However, in a general reading device, the size of an area that can be read at a time is limited. Depending on the size of an original to be read, the original size may be the size of an area that can be read by the reading apparatus (hereinafter, “ Some of them are referred to as “readable size”. In such a case, when an entire original image is to be read, it is necessary to read the original with a reading device in a plurality of times.
Therefore, as a method of scanning a document in multiple steps, the scanning procedure is determined according to the document size and the readable size so that the entire document image can be read by multiple scanning. There is known a method for displaying a guide corresponding to (for example, a document setting position and the number of times).
However, in order to consider the document size as described above, it is necessary for the operator to specify the document size. Therefore, the operator may need to measure the size of the document.
The document size detection device 100 (the document size detection device 100 having a reading size / readable size extraction module 130, a procedure generation module 135, and a procedure presentation module 140 in the guide module 115) can be read by the reading device. In a configuration in which a document image having a size larger than the area is read in a plurality of times by the reading device, it is possible to generate a composite image obtained by combining the read images without the operator specifying the document size.

  Here, “a document having a size larger than the area that can be read by the reading device” corresponds to an A3 size document when the reading size of the scanner is an A4 size, for example. In such a case, an image of the entire document cannot be acquired by one reading (also called scanning), and multiple readings are necessary. Then, the read images are combined to generate an image of the original size (A3 size in the above example). Due to this combination processing, the reading procedure may differ depending on the feature amount in the document image. The document size detection apparatus 100 presents this reading procedure.

Hereinafter, terms will be defined in describing the present embodiment.
“Size” means the length of the long side when the document or readable area is rectangularized (if the area before the rectangularization itself is rectangular, the rectangularization may not be necessary) And the length of the short side, and is not determined only by the length of either one of the long side or the short side or the area of the rectangle. Note that “size A is larger than size B” means that the length of the long side and the length of the short side of size A are both larger than that of size B. For example, there are A3 size, A4 size, B4 size, B5 size, etc. defined by international standards, Japanese industrial standards, and the like.
“Readable size” refers to the size of a readable area. Specifically, this is the maximum size that can be read by a reading device B 195 described later.
The “read image” refers to an image obtained by one reading.
“Reading size” refers to the size of the read image. Specifically, it is the size of a document read by a reading device B 195 described later. The size may be the same as the readable size.
“Composite image” refers to an image obtained by combining read images.
“Characteristic amount (of image)” is an amount indicating a feature in an image, and refers to, for example, physical quantities of color parameters such as brightness, saturation, and hue, and the degree of change of each physical quantity. More specifically, the amount of edge (the amount of the portion where the brightness of the image is discontinuously converted), the histogram (density value distribution), the character recognition result (character code, information indicating whether or not the character can be recognized) (Including a value indicating the likelihood of the character recognition result), or a combination thereof. In general, the characteristics of various images such as characters, photographs, edges, and blank pages can be grasped from the results of analysis.

  The reading device A: 190 is connected to the image acquisition A module 105 of the document size detection device 100. Reading device A: 190 reads an image of the entire area (the entire document) of the document to be read. The reading device A: 190 is different from the reading device B: 195 in that the reading accuracy is lower than that of the reading device B: 195. Examples of the reading device A: 190 include a portable digital camera, a portable information device (including a mobile phone, a smartphone, a mobile device, a wearable computer, and the like) having a digital camera. Accordingly, when a document is read by the reading device A: 190, distortion or the like often occurs compared to the reading device B: 195. Note that the image read by the reading device A: 190 is an image as a pre-scan, and is not an image for final synthesis.

Reading device B: 195 is connected to image acquisition B module 110 of document size detection device 100. Reading device B: 195 reads at least a partial area of the document. Examples of the reading device B: 195 include a scanner and a multifunction device having a scanner function (an image processing device having functions of a printer, a copier, a fax machine, etc. in addition to the scanner function). . The readable size that is the size of the area that can be read by the reading device B: 195 is fixed. This is because a reading surface (generally referred to as a document table or document glass) on which a document is set is fixed. Note that the image read by the reading device B: 195 is an image for final synthesis.
Further, the size of the image read by the reading device B 195 may be a readable size or a size smaller than the readable size. For example, when the readable size of the reading device B: 195 is A4 size, it may be possible to read even B5 size, A5 size, etc. smaller than A4 size. In this case (when there are a plurality of types of reading sizes), the reading size is determined by the operation of the operator when the original is read. Of course, when there is only one type of reading size, the readable size is the reading size.

The image acquisition A module 105 is connected to the matching processing module 120 of the guide module 115 and the reading device A: 190. The image acquisition A module 105 acquires a first image, which is an entire image of a document to be read, from the reading device A: 190. As an image to be received, it is only necessary to photograph “the entire image of the document”, and an image other than the document (an image serving as a background other than the region of the document) may be photographed as long as the document can be extracted from the image. If an image other than the document is included or a tilted document is shot, the existing technology is used to correct the tilt and distortion, and the document is transformed into a rectangular image. In other words, an image of only the original may be generated.
The image acquisition B module 110 is connected to the matching processing module 120 of the guide module 115 and the reading device B: 195. The image acquisition B module 110 acquires a second image (part of an original image) read by the reading device B 195. The original to be read here is the same as the original photographed by the reading apparatus A: 190. The size of the image acquired from the reading device B: 195 is a readable size in the reading device B: 195 or a size smaller than the readable size. A document to be read is larger than the readable size of the reading device B: 195. Therefore, the reading device B: 195 requires multiple readings. The document may have a size that conforms to a standard (for example, JIS standard), or may have a non-standard size (non-standard) size.

The guidance module 115 includes a matching processing module 120, a document size detection module 125, a reading size / readable size extraction module 130, a procedure generation module 135, and a procedure presentation module 140.
The matching processing module 120 is connected to the image acquisition A module 105, the image acquisition B module 110, and the document size detection module 125. The matching processing module 120 performs matching processing between the first image acquired by the image acquisition A module 105 and the second image acquired by the image acquisition B module 110. An existing matching process may be used as the matching process. The first image includes an image of the entire document, and the second image is a partial image of the document. Accordingly, as a result of the matching process, the ratio (ratio) of the second image in the original image in the first image can be detected.

The document size detection module 125 is connected to the matching processing module 120, the read size / readable size extraction module 130, and the procedure generation module 135. The document size detection module 125 determines the first image based on the result of the matching process between the first image acquired by the image acquisition A module 105 and the second image acquired by the image acquisition B module 110 (processing result by the matching processing module 120). The ratio of the area occupied by the image corresponding to the second image is calculated. Any one or more of a width ratio, a height ratio, and an area ratio may be used as the ratio. In particular, when it is known that the document conforms to the standard, either the ratio of the width or the ratio of the height may be set by using the short sides or the long sides.
Then, the document size detection module 125 detects the size of the document using the ratio and the read size. In other words, the document size detection module 125 detects the size of the target document using the processing result of the matching processing module 120 and the read size that is the size of the second image read by the reading device B 195. “Reading size that is the size of the second image read by the reading device B: 195” is received from the reading size / readable size extraction module 130. Specifically, the document size detection module 125 may calculate the ratio of the width and the height of the area occupied by the image corresponding to the second image in the first image from the result of the matching process. Good. Then, the document size detection module 125 may detect the width and height of the document using the width ratio, the height ratio, and the reading size.

  The read size / readable size extraction module 130 is connected to the document size detection module 125 and the procedure generation module 135. The reading size / readable size extraction module 130 extracts a reading size of the target document by the reading device B: 195. Then, the reading size / readable size extraction module 130 extracts a readable size that is the size of an area that can be read by the reading device B 195. For example, communication with the reading device B: 195 may be performed, and the reading size of the reading device B: 195 and the readable size of the reading device B: 195 may be acquired by an inquiry. Further, when the reading size is embedded in the second image, it may be extracted. For example, Exif (Exchangeable image file format) information may be used. Further, the readable size of the reading device B: 195 may be extracted using the reading device / readable size correspondence table 1600 shown in the example of FIG.

The procedure generation module 135 is connected to the document size detection module 125, the reading size / readable size extraction module 130, and the procedure presentation module 140. The procedure generation module 135 generates a reading procedure when the target document is read by the reading device B: 195 in a plurality of times using the size of the document and the reading size.
The reading procedure may include one or more of the following.
(1) Instruction of which area in the original is read by the reading device B: 195 at each reading time (2) Reading device B: at which position or in which direction the original is read at each reading time Indication of whether to set to 195 (3) Instruction of the number of times of reading the document (4) Instruction of whether further reading is necessary after at least one reading is completed

For example, the procedure generation module 135 may determine the reading procedure according to the size of the document and the readable size of the reading device B: 195. The reason why the readable size is used here is that the maximum reading size of the reading device B: 195 is used to reduce the number of readings. Therefore, the reading size when the image to be combined is read a plurality of times may be a readable size. For example, the reading size may not be selected by the operator, and the reading size may be fixed.
Specifically, the procedure generation module 135 may determine the reading procedure so that the width or height of the readable size is longer than or greater than the width or height of the document size.
Further, the procedure generation module 135 may determine the reading procedure so that the document area is read in an overlapping manner when the adjacent area is read.

In addition, the procedure generation module 135 determines which area in the document is to be read in each reading so that the reading area at the time of at least two readings includes an area having a large local feature amount change in the document. You may make it produce | generate the reading procedure which guides.
In that case, the procedure generation module 135 selects a reading pattern in which a region having a large change in local feature amount overlaps among a plurality of reading patterns in which reading regions overlap each other for each document size. Also good. The reading pattern is a predetermined reading procedure, and the reading procedure is determined by selecting the reading pattern.
The read pattern may specify, for each read pattern, which area of the document is a multiple-time read area and which area is a single-time read area.
In addition, the procedure generation module 135 may change the number of readings according to the position of the region where the local feature amount change is large.
Further, the procedure generation module 135 may generate a reading procedure so that, when there are a plurality of regions having a large local feature amount change in the document, the plurality of regions are included in the overlapping region.
In addition, the procedure generation module 135 causes any region in the document to be read in each reading so that the reading region at the time of reading at least twice does not include a region with a small local feature amount change in the document. You may make it produce | generate the reading procedure which guides these.

The procedure generation module 135 determines which area in the document is read in each reading so that the reading areas in a plurality of readings do not overlap each other with an area where the local feature amount change is small in the document. You may make it produce | generate the reading procedure which guides. Here, “do not overlap each other” is synonymous with reducing overlapping portions.
Then, when the document size is an integral multiple of the readable size, the procedure generation module 135 identifies a region that can be a joint, and checks whether or not the local feature amount change is small near the region. You may make it do. Here, “the document size is an integral multiple of the readable size” refers to a case where the area is an integral multiple. For example, the document size is the A3 size and the readable size is the A4 size.
Further, the procedure generation module 135 may check the joint area after reading the integer number of times.
In addition, the procedure generation module 135 may check the joint area after reading, and if the change is small, the procedure generation module 135 may generate a reading procedure that provides guidance to end the reading.
In addition, the procedure generation module 135 may check the joint area after reading, and if the change is large, the procedure generation module 135 may generate a reading procedure that provides guidance for prompting the next reading.
Further, the procedure generation module 135 performs a reading procedure for guiding the next reading to include at least a part of the already read area and a part including a part including a large local change as the reading area. You may make it produce | generate.

  As a check in these, determination may be made based on the edge amount in the joining direction, the histogram, the character recognition result, or a combination thereof. For example, if the edge amount is greater than or equal to a predetermined threshold, it is determined that the region has a large change in feature amount. In addition, for example, when the number of objects that could not be recognized as a character recognition result (for example, the number of objects when character recognition could not be performed because part of the character was targeted for character recognition) was greater than or equal to a predetermined threshold May be determined as a region where the change in the feature amount is large. Further, when the character recognition result is blank (a recognition result that there is no character), it may be determined that the region has a small change in feature amount.

If the document size is not an integral multiple of the readable size, the procedure generation module 135 guides which area in the document is to be read in each reading so that the overlapped reading area in multiple readings is reduced. A procedure may be generated. Here, “when the document size is not an integral multiple of the readable size” refers to a case where the area is not an integral multiple, for example, a case where the document size is the B4 size and the readable size is the A4 size.
Then, the procedure generation module 135 may check whether or not a region having a small change in local feature amount is included in the overlapped reading region.
Further, the procedure generation module 135 may perform a check and generate a reading procedure that guides the user to end the reading if a region having a small local feature amount change is included.
Further, the procedure generation module 135 may perform a check and generate a reading procedure for guiding the user to prompt the next reading if an area having a small local feature amount change is not included.
Further, the procedure generation module 135 performs a reading procedure for guiding the next reading to include at least a part of the already read area and a part including a part including a large local change as the reading area. You may make it produce | generate.
As a check in these, determination may be made based on the edge amount in the joining direction, the histogram, the character recognition result, or a combination thereof.

  The procedure presentation module 140 is connected to the procedure generation module 135. The procedure presentation module 140 presents the reading procedure generated by the procedure generation module 135. In addition to the display on a display device such as a liquid crystal display, the presentation here may include an output as a 3D (Dimensions) video, and further, audio output by a sound output device such as a speaker, vibration, printer You may combine the printing with printing apparatuses, such as these.

FIG. 2 is an explanatory diagram showing a system configuration example using the present embodiment. In particular, in order to read the document 280 by the image processing apparatus 205, the document 280 is read (pre-scanned) by the image processing apparatus 205 before that, the size of the document 280 is detected, and a reading procedure in the image processing apparatus 205 is presented. It is.
The example shown in FIG. 2A is configured by a portable information processing device 200A and an image processing device 205A.
The portable information processing apparatus 200A includes a document size detection apparatus 100 and a reading apparatus A: 190. Document size detection apparatus 100 and reading apparatus A: 190 are connected. The image processing apparatus 205A has a reading apparatus B: 195.
The original 280 is read (pre-scanned) by the reading device A: 190 of the portable information processing device 200A, the reading procedure is presented on the display of the portable information processing device 200A, and the operator views the image processing device 205A while looking at it. The original 280 is read by operating.

The example shown in FIG. 2B is configured by a portable information processing device 200B and an image processing device 205B.
The portable information processing device 200B has a reading device A: 190. The image processing device 205B includes a document size detection device 100 and a reading device B: 195. Document size detection apparatus 100 and reading apparatus B: 195 are connected. Reading apparatus A 190 in portable information processing apparatus 200B and document size detection apparatus 100 in image processing apparatus 205B are connected via a communication line (which may be wired or wireless). Yes.
The document 280 is read (pre-scanned) by the reading device A: 190 of the portable information processing device 200B, and the image is transmitted to the document size detection device 100 of the image processing device 205B via a communication line. Then, the document size detection apparatus 100 presents a reading procedure on the display of the image processing apparatus 205B, and the operator operates the image processing apparatus 205B while reading it to read the document 280.

FIG. 3 is an explanatory diagram showing a system configuration example using the present embodiment.
The document size detection device 100, the portable information processing device 200A, the portable information processing device 200B, the image processing device 205A, the image processing device 205B, the image processing device 205C, the image processing device 205D, and the combining device 210 are respectively connected via the communication line 290. It is connected. The communication line 290 may be wireless, wired, or a combination thereof, and may be, for example, the Internet or an intranet as a communication infrastructure. The functions of the document size detection apparatus 100 and the composition apparatus 210 may be realized as a cloud service. The portable information processing apparatus 200A includes a document size detection apparatus 100 and a reading apparatus A: 190. The portable information processing device 200B has a reading device A: 190. The image processing apparatus 205A has a reading apparatus B: 195. The image processing device 205B includes a document size detection device 100 and a reading device B: 195. The image processing device 205C includes a reading device B: 195 and a composition device 210. The image processing device 205D includes a document size detection device 100, a reading device B: 195, and a composition device 210. The synthesizing device 210 synthesizes a plurality of images read by the image processing device 205. Then, the synthesized image may be output. To output an image is, for example, printing on a printing device such as a printer, displaying on a display device such as a display, transmitting an image on an image transmission device such as a fax machine, or sending an image to an image storage device such as an image database. , Storing in a storage medium such as a memory card, passing to another information processing apparatus, and the like.

As a synthesis process performed by the synthesis apparatus 210, for example, there is a technique described in the following document.
http://matthewalunbrown.com/autostitch/autostitch.html
http://news.mynavi.jp/series/computer_vision/029/
In these combining processes, for example, if an overlapping area in a plurality of images is a portion with a small feature amount (a flat portion with a small pattern or the like), it cannot be used for alignment of the combining. Therefore, the area to be read in duplicate needs to include an area with a large change in the feature amount to the extent that it can be used for the alignment of synthesis. The document size detection apparatus 100 presents a reading procedure so that an area having a large change in the feature amount is included in the overlapping area.

For example, it is possible to synthesize an image read in a plurality of times by combining the portable information processing device 200A, the image processing device 205A, and the synthesizing device 210.
Further, for example, by combining the portable information processing device 200B, the image processing device 205B, and the combining device 210, it is possible to combine the images read in multiple times.
In addition, for example, by combining the portable information processing device 200 </ b> B and the image processing device 205 </ b> D, it is possible to synthesize an image read in multiple times.
In the example shown in FIGS. 2A and 2B, the document size detection device 100 is included in the portable information processing device 200A or the image processing device 205B, but the document size detection device 100 is configured alone. Also good. For example, the function of the document size detection device 100 is provided as a cloud service, and the procedure presentation module 135 causes the portable information processing device 200 or the image processing device 205 used by the operator who reads the document to present the reading procedure. Good.
For example, it is possible to synthesize an image read in a plurality of times by combining the portable information processing device 200B, the document size detection device 100, and the image processing device 205C.

FIG. 4 is a flowchart showing an example of processing according to this embodiment.
In step S402, the procedure presentation module 140 instructs the operator to read the entire original with the reading device A: 190.
In step S404, in accordance with the operation of the operator, the reading device A: 190 reads the entire original image A of the document.
In step S <b> 406, the image acquisition A module 105 receives the entire original image A of the original from the reading device A: 190.
An example of processing from step S402 to step S406 will be described using the example of FIG.
The display device of the camera-equipped portable information processing device 510 displays that the entire document 500 is to be photographed.
As shown in the example of FIG. 5A, the operator operates the camera-equipped portable information processing apparatus 510 to photograph the entire document 500.
Then, as illustrated in the example of FIG. 5B, the image acquisition A module 105 acquires the entire image 520 of the original 500 from the camera-equipped mobile information processing device 510.

In step S408, the procedure presentation module 140 instructs the reading device B: 195 to read a part of the document.
In step S410, the reading device B: 195 reads a part of the image B of the document according to the operation of the operator.
In step S412, the image acquisition B module 110 receives a part of the image B of the document.
The process example from step S408 to step S412 is demonstrated using the example of FIG.
The display device of the image processing device 610 displays that a part of the document 500 is read.
As shown in the example of FIG. 6A, the operator operates the image processing device 610 to read a part of the document 500.
As shown in the example of FIG. 6B, since the size of the document 500 is larger than the readable size of the image processing apparatus 610 (the size of the reading surface 620), a part of the document 500 is read. In the example of FIG. 6B, the upper left corner of the document 500 (upper left corner when viewed from the back) and the upper left corner of the reading surface 620 are matched, so the upper left portion of the document 500 is read. Note that the reading here does not necessarily have to be a readable size of the image processing apparatus 610. Depending on the designation of the operator, the image processing apparatus 610 may be smaller than the readable size.
Then, as illustrated in the example of FIG. 6C, the image acquisition B module 110 acquires the partial image 630 of the document 500 from the image processing apparatus 610.

In step S414, the matching processing module 120 performs matching processing between the entire image A and the image B.
For example, matching processing is performed on the entire image 520 illustrated in FIG. 7A and the partial image 630 illustrated in FIG. Here, the camera image size table 800 is acquired as the size of the entire image 520, and the scan image size table 900 is acquired as the size of the partial image 630. FIG. 8 is an explanatory diagram showing an example of the data structure of the camera image size table 800. The camera image size table 800 has a width column 810 and a height column 820. The width column 810 stores the number of pixels of the width (Wide) of the entire image 520. The height column 820 stores the number of pixels of the height (High) of the entire image 520. FIG. 9 is an explanatory diagram showing an example of the data structure of the scanned image size table 900. The scanned image size table 900 has a width column 910 and a height column 920. The width column 910 stores the number of pixels of the width (Wide) of the partial image 630. The height column 920 stores the number of pixels of the height (High) of the partial image 630.
As shown in the example of FIG. 10A, matching processing between the entire image 520 and the partial image 630 is performed. As the matching process, for example, a SIFT (Scale Invariant Feature Transform) technique capable of matching an image regardless of the scale or color may be used. The SIFT technology is described at the following URL.
URL: http://news.mynavi.jp/series/computer_vision/029/
As shown in the example of FIG. 10B, the partial image 630 indicates that it matches the upper right portion (corresponding region 1040) of the entire image 520.

Further, the matching process may be performed as follows.
The example shown in FIG. 11 is an explanatory diagram showing an example of matching processing according to the present embodiment. As shown in the example of FIG. 11A, matching processing is performed between the upper right partial image 1120a in the partial image 630 and the upper right region of the entire image 520. In general, since reading is performed by matching the corners of the original and the reading surface, matching processing is performed in a region between the corners. If they match, as shown in the example of FIG. 11B, matching processing is performed with the upper right partial image 1120b (region larger than the partial image 1120a) in the partial image 630 with the upper right region of the entire image 520. I do. This process is repeated by gradually increasing the partial image 1120 (FIG. 11C,..., FIG. 11E). If it is determined that they do not match, the same matching process may be performed at other corners.

  The example shown in FIG. 12 is an explanatory diagram showing an example of matching processing according to the present embodiment. As shown in the example of FIG. 12A, a partial image 1210 in the partial image 630 is extracted. Then, as shown in the example of FIG. 12B, the entire image 520 is scanned while performing a matching process with a partial image 1210. Then, as shown in the example of FIG. 12C, matching processing is performed on the entire region of the partial image 630 at a matching position in the entire image 520.

The example shown in FIG. 13 is a flowchart showing an example of matching processing according to the present embodiment. Unlike the image matching process, the influence of the resolution on the character recognition result is small, which is useful for the matching process between the whole image 520 and the partial image 630 having different resolutions. In particular, when it is determined that the image has many characters, the matching process shown in the example of FIG. 13 may be performed.
In step S1302, character recognition is performed on the entire image A (entire image 520). The character recognition process here outputs the position of the target character image (position in the whole image A) as the character recognition result together with the recognition result (text) of the character image.
In step S1304, character recognition is performed on the image B (partial image 630). The character recognition process here outputs the position of the target character image (position in the whole image B) as the character recognition result together with the recognition result (text) of the character image.
In step S1306, matching processing is performed between the texts that are the results of character recognition of both. In the matching processing between texts, characters that are likely to be erroneously recognized in character recognition (predetermined characters, specifically I, 1, etc.) may not be targeted for matching processing. .
In step S1308, the positions of the corresponding characters are matched, and the position of the matching partial image B in the entire image A is specified.

In step S416, the reading size of the reading device B: 195 is extracted. For example, the reading size may be extracted from the image processing apparatus 610 by inquiry communication.
In step S418, the document size is detected. The document size may be detected using the matching processing result in step S414 and the read size extracted in step S416.
14 and 15 are explanatory diagrams illustrating an example of processing according to the present embodiment.
The example shown in FIG. 14 shows the size relationship between the entire image 520 and the partial image 630. When the width of the entire image 520 is W, the height is H, the width of the partial image 630 is W ′, and the height is H ′, the width ratio is “W: W ′”, and the height ratio is “ H: H '". Then, the entire image 520 may be calculated using the size of the partial image 630 extracted in step S416 (read size with the reading device B: 195).
Specifically, the width ratio and the height ratio are W ′ = 0.8 × W and H ′ = 0.7 × H, as shown in the examples of FIGS. When the partial image 630 is A4 size (width (W ′): 297 mm, height (H ′): 210 mm), the width (Wo) and height (Ho) of the document 500 are calculated as follows. can do.
Wo = W ′ × (1 / 0.8)
= 297 × (1 / 0.8)
= 372 (mm)
Ho = H ′ × (1 / 0.7)
= 210 x (1 / 0.7)
= 300 (mm)

  In step S420, the readable size of the reading device B: 195 is extracted. For example, a reader / readable size correspondence table 1600 is used. FIG. 16 is an explanatory diagram showing an example of the data structure of the reading device / readable size correspondence table 1600. The reading device / readable size correspondence table 1600 has a reading device column 1610 and a readable size column 1620. The reading device column 1610 stores reading device model information (may be information that can uniquely identify the reading device). The readable size column 1620 stores the readable size in the reading device. The model information of the reading device B 195 (image processing device 610) connected to the document size detection device 100 may be searched from the reading device column 1610, and the information in the readable size column 1620 may be extracted.

In step S422, the procedure generation module 135 performs a reading procedure generation process. That is, the reading procedure is determined according to the document size and the readable size.
For example, the arrangement relationship between the reading surface and the document is determined so that the width or height of the reading surface (readable size) is longer than or greater than the width or height of the document size. For example, as shown in FIG. 17A, in the case of a size relationship between the reading surface 620 (readable size) and the document 1700, the height of the reading surface 620 is longer than the height of the document 1700. Arrange. That is, when one side of the reading surface 620 is longer than one side of the original 1700, the entire side of the original 1700 is arranged so that it can be read once. As a result, reading can be performed simply by moving the document 1700 in one direction (a direction perpendicular to the one side, in the example shown in FIG. 17, the horizontal direction). That is, it is not necessary to move the document 1700 in the direction of one side (vertical direction in the example of FIG. 17).
As shown in the example of FIG. 17B, the second and subsequent readings are repeated until the document 1700 is moved in the horizontal direction and the entire document 1700 is read. The number of readings may be calculated by the ratio of the length in the moving direction. In the example of FIG. 17, the width of the original 1700 may be divided by the width of the reading surface 620. However, the number of readings is adjusted so that an overlapping range (overlap) occurs. This number of times is presented to the operator. In addition, after the reading is completed, an instruction as to whether further reading is necessary may be presented.
As shown in the example of FIG. 18A, when the size relationship between the reading surface 620 (readable size) and the document 1800 is satisfied, the width of the reading surface 620 is longer than the width of the document 1800. , Arrange.
As shown in the examples of FIGS. 18B and 18C, the second and subsequent readings are repeated until the original 1800 is moved in the vertical direction and the entire original 1800 is read. The number of readings may be calculated by the ratio of the length in the moving direction. In the example of FIG. 18, the height of the document 1800 may be divided by the height of the reading surface 620. However, the number of readings is adjusted so that an overlapping range occurs. This number of times is presented to the operator. In addition, after the reading is completed, an instruction as to whether further reading is necessary may be presented.

In the second and subsequent readings, the arrangement is determined so that an overlapping range occurs. This overlapping range has a role as a joint when performing the synthesis process.
When three or more readings are required, the entire image captured by the reading device A: 190 is presented so that the operator can grasp the reading range of each time. You may make it designate using etc. Since an image is used, the reading range at each reading can be easily understood. Further, since the image itself is used, it is an instruction indicating which area in the document is to be read by the reading device B: 195, and in what position or in what direction the document is read to the reading device B: 195. It is also an instruction on whether to set.

  In step S424, the procedure presentation module 140 presents a reading procedure to the operator. Thereafter, the operator performs a scanning operation with the reading device B: 195 in accordance with the presented reading procedure, and performs a plurality of readings to generate a composite image.

FIG. 19 is a flowchart showing an example of processing according to the present embodiment. An example of processing for combining and outputting an image after the processing according to the flowchart shown in the example of FIG. 4 is performed will be described.
In step S1902, reading apparatus B: 195 reads a document according to a reading procedure. Multiple readings.
In step S1904, the synthesizing device 210 synthesizes the read images to generate an image of the entire document.
In step S1906, the synthesizing device 210 outputs an image of the entire synthesized document.

  With reference to FIG. 20, a hardware configuration example of document size detection apparatus 100 (including portable information processing apparatus 200, image processing apparatus 205, etc.) according to the present embodiment will be described. The configuration illustrated in FIG. 20 is configured by a personal computer (PC), for example, and illustrates a hardware configuration example including a data reading unit 2017 such as a scanner and a data output unit 2018 such as a printer.

  A CPU (Central Processing Unit) 2001 includes various modules described in the above-described embodiments, that is, an image acquisition A module 105, an image acquisition B module 110, a guide module 115, a matching processing module 120, a document size detection module 125, It is a control part which performs the process according to the computer program which described the execution sequence of each module, such as reading size / the readable size extraction module 130, the procedure production | generation module 135, and the procedure presentation module 140.

  A ROM (Read Only Memory) 2002 stores programs, calculation parameters, and the like used by the CPU 2001. A RAM (Random Access Memory) 2003 stores programs used in the execution of the CPU 2001, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 2004 constituted by a CPU bus or the like.

  The host bus 2004 is connected via a bridge 2005 to an external bus 2006 such as a peripheral component interconnect / interface (PCI) bus.

  A keyboard 2008 and a pointing device 2009 such as a mouse are devices operated by an operator. The display 2010 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text or image information. Further, a touch screen or the like having both functions of the pointing device 2009 and the display 2010 may be used. In that case, with respect to the realization of the keyboard function, even if the keyboard 2008 is not physically connected, a keyboard (so-called software keyboard, screen keyboard, etc.) is drawn on the screen (touch screen) by software, You may make it implement | achieve the function of a keyboard.

  An HDD (Hard Disk Drive) 2011 includes a hard disk (may be a flash memory or the like), drives the hard disk, and records or reproduces a program executed by the CPU 2001 or information. The hard disk stores an image read by reading device A: 190, reading device B: 195, a camera image size table 800, a scanned image size table 900, a reading device / readable size correspondence table 1600, and the like. Further, various other data, various computer programs, and the like are stored.

  The drive 2012 reads data or a program recorded in a removable recording medium 2013 such as a mounted magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and the data or program is read from the interface 2007 and an external bus 2006. , The bridge 2005, and the RAM 2003 connected via the host bus 2004. Note that the removable recording medium 2013 can also be used as a data recording area.

  The connection port 2014 is a port for connecting the external connection device 2015, and has a connection unit such as USB, IEEE1394. The connection port 2014 is connected to the CPU 2001 and the like via the interface 2007, the external bus 2006, the bridge 2005, the host bus 2004, and the like. The communication unit 2016 is connected to a communication line and executes data communication processing with the outside. The data reading unit 2017 is a scanner, for example, and executes document reading processing. The data output unit 2018 is a printer, for example, and executes document data output processing.

  Note that the hardware configuration of the document size detection apparatus 100 shown in FIG. 20 shows one configuration example, and the present embodiment is not limited to the configuration shown in FIG. 20, but the modules described in the present embodiment. Any configuration can be used. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line In addition, a plurality of systems shown in FIG. 20 may be connected to each other via communication lines so as to cooperate with each other. In particular, in addition to personal computers, portable information communication devices (including mobile phones, smartphones, mobile devices, wearable computers, etc.), information appliances, robots, copiers, fax machines, scanners, printers, multifunction devices (scanners, printers, An image processing apparatus having two or more functions such as a copying machine and a fax machine) may be incorporated.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standard “DVD + R, DVD + RW, etc.”, compact disc (CD), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), Blu-ray disc ( Blu-ray (registered trademark) Disc), magneto-optical disk (MO), flexible disk (FD), magnetic tape, hard disk, read-only memory (ROM), electrically erasable and rewritable read-only memory (EEPROM (registered trademark)) )), Flash memory, Random access memory (RAM) SD (Secure Digital) memory card and the like.
Then, the whole or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, or a wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part or all of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

DESCRIPTION OF SYMBOLS 100 ... Original size detection apparatus 105 ... Image acquisition A module 110 ... Image acquisition B module 115 ... Guidance module 120 ... Matching processing module 125 ... Original size detection module 130 ... Read size / readable size extraction module 135 ... Procedure generation module 140 ... Procedure presentation module 190... Reading device A
195: Reader B
DESCRIPTION OF SYMBOLS 200 ... Portable information processing apparatus 205 ... Image processing apparatus 210 ... Composition apparatus 280 ... Document 290 ... Communication line

Claims (17)

First acquisition means for acquiring a first image that is an entire image of a document to be read;
Second acquisition means for acquiring a second image which is a partial image of the original read by the reading device;
Detecting means for detecting the size of the document using a matching result of the first image and the second image and a reading size that is a size obtained by reading the second image by the reading device;
A document size detecting apparatus having 2. The document size according to claim 1, further comprising: a guide unit that guides a reading procedure when the document is read by the reading device in a plurality of times using the document size and the reading size. Detection device. The reading procedure includes an instruction of which area in the document is to be read by the reading device at each reading.
The document size detection apparatus according to claim 2. The reading procedure includes an instruction as to which position or orientation the original is to be set in the reading device at the time of each reading.
The document size detection apparatus according to claim 2. The reading procedure includes an instruction of the number of times to read the document.
The document size detection apparatus according to claim 2. The reading procedure includes an instruction as to whether or not reading is necessary after reading at least once.
The document size detection apparatus according to claim 2. The first acquisition means reads a result of reading the entire area of the document using the second reading device which is a second reading device different from the reading device and has a lower reading accuracy than the reading device. get,
The document size detection apparatus according to claim 2. The detection means calculates a ratio of an area occupied by an image corresponding to the second image in the first image from the result of the matching process.
The document size detection apparatus according to claim 1. The detecting means detects the size of the document using the ratio and the read size;
The document size detection apparatus according to claim 8. The detection means calculates, from the result of the matching process, the ratio of the width and the height of the area occupied by the image corresponding to the second image in the first image.
The document size detection apparatus according to claim 9. The document size detection apparatus according to claim 10, wherein the detection unit detects the width and height of the document using the width ratio, the height ratio, and the read size. The guide means determines a reading procedure according to the size of the document and the readable size of the second acquisition means;
The document size detection apparatus according to claim 2. The guide means determines the reading procedure so that the width or height of the readable size is longer than or greater than the width or height of the document size;
The document size detection apparatus according to claim 12. The guide means determines a reading procedure so as to read an overlapping area of an original when reading adjacent areas.
The document size detection apparatus according to claim 12. Computer
First acquisition means for acquiring a first image that is an entire image of a document to be read;
Second acquisition means for acquiring a second image which is a partial image of the original read by the reading device;
Using the result of the matching process between the first image and the second image and the reading size that is the size of the second image read by the reading device, the detection unit detects the size of the document. Document size detection program. A document size detection device, a reading device, and an image composition device;
The document size detection device includes:
First acquisition means for acquiring a first image that is an entire image of a document to be read;
Second acquisition means for acquiring a second image that is an image of a part of the document read by the reading device;
Detecting means for detecting the size of the document using a matching result of the first image and the second image and a reading size that is a size obtained by reading the second image by the reading device;
Have
The reader is
A reading means for reading a document;
The image composition device includes:
An image processing system comprising: a combining unit that combines a plurality of images read by the reading device. (1) The reading device includes the document size detection device.
(2) The reading device includes the image composition device.
(3) The reading device includes the image composition device and the document size detection device.
The image processing system according to claim 16.

Images