JP2005260663A - Digital camera and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To save user labor or the like by quickly and accurately determining image quality in document computerization using a digital camera. <P>SOLUTION: A control part 110 of a digital camera 100 calculates a hand shaking amount at the time of photographing on the basis of a detection value acquired from a sensor part 170 and compares the hand shaking amount with a preset determination reference value to thereby determine whether a document image to be acquired is illegible. The determination reference value is individually set in accordance with image usage application, and an outputting part 140 outputs notification information based on a determination result corresponding to the usage application. The control part 110 segments a character part from the acquired document image and specifies a character size on the image. The control part 110 performs comparison with the determination reference value performed in advance to thereby determine whether the document image is illegible. The determination reference value is individually set in accordance with the image usage application and an influence of lens performance, whether to be illegible is determined by taking into consideration the usage application and the lens performance and the outputting part 140 outputs notification information corresponding to a determination result. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a digital camera, and more particularly to a digital camera suitable for digitizing a document.

  Conventionally, in order to digitize documents on paper etc., it was common to read them with a flatbed scanner, etc., but in recent years, high-pixel digital cameras have become available at low prices. Digital cameras are being used instead of scanners and memos. Taking advantage of the features of a digital camera that can record the captured image as digital data, document information can be obtained by shooting a document printed on paper or characters on a signboard in the city with a digital camera. Can be easily digitized. In addition, unlike a flatbed scanner or the like, a digital camera is excellent in portability, so that it is possible to digitize a document anytime and anywhere regardless of the form of the target document. Further, since it can be recorded as digital data, it can be easily converted into convenient text data by a predetermined character recognition process or the like.

  However, unlike flatbed scanners where the distance to the target is always constant, shooting with digital cameras has different shooting conditions for each shooting, so it is always possible to obtain the image quality required for character recognition processing. Have difficulty. In other words, shooting with a digital camera is affected by external light, lens performance, camera shake, and the like, and it is difficult to always obtain an image under certain conditions as in a flatbed scanner. As a result, necessary image quality may not be obtained, and an image that is not suitable for character recognition processing may be recorded.

  Therefore, when document information is recorded using a digital camera, conventionally, (1) a plurality of images of the same object to be imaged are selected and the image with the best image quality is selected after shooting, or (2) each image is captured. The work was done by checking the image quality on the screen and re-taking the image if the image quality was bad. In the method (1), even image data with low image quality must be recorded, so that the memory area is occupied unnecessarily, which may hinder the recording of a really necessary image. In addition, a screen (such as a liquid crystal display device) provided in a digital camera often has a low resolution, and in order to check the image quality, the image must be enlarged or scrolled. Therefore, in the method (2), the work time for confirmation becomes long and the photographing efficiency is lowered. In addition, since both methods are operations performed by the user (photographer), the user's labor is required and is a burden.

  In order to eliminate such inconveniences, techniques (for example, Patent Documents 1 and 2) that automatically determine whether or not the image quality is predetermined are proposed. However, in these methods, since the image quality is determined by performing image processing on the acquired image data, it takes time for processing, and it may be necessary to wait for processing at the time of shooting. For this reason, rapid photographing cannot be performed, and photographing efficiency is lowered. As a result, the work efficiency associated with the digitization of the document is reduced, and the convenience of the digital camera cannot be fully utilized.

  Further, in photographing with a digital camera, distortion and blur may occur near the edge of an image due to the influence of lens aberration. When character size is specified by cutting out characters from such an image, even a character of the same size may be specified as a different size depending on the position on the image. Therefore, as in the conventional technique described above, the method of unambiguously cutting out characters in an image and specifying the character size does not consider the influence of lens performance, so it is difficult to specify the character size accurately. . In other words, the determination of the image quality according to the above prior art is not accurate and may be erroneous.

  Furthermore, the usage of the photographed document image is often different depending on the photographing object and the user. That is, there are cases where the purpose is to acquire text data by character recognition processing, while there are cases where it is only necessary to display an image or the like. When it is desired to perform character recognition at a high recognition rate by character recognition processing, a relatively high image quality is usually required. On the other hand, the permissible range of human legibility is wider than this, and even an image having an image quality lower than the image quality required in the character recognition process can be recognized. That is, there is a difference in the level of image quality required between the case of character recognition processing and the case of visual recognition.

However, in the prior art, since the judgment criteria for image quality are uniform, there is a case where re-taking is forced even though necessary and sufficient image quality is obtained. That is, when the level required in the character recognition process is used as a reference, it may be determined that the image quality is low although an image with an image quality sufficient for visual recognition can be taken. In this case, the user performs re-taking according to the judgment, but if the purpose is visual recognition, it becomes useless work and the photographing efficiency is lowered.
JP-A-10-247220 Japanese Patent Laid-Open No. 08-063547

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a digital camera and a program capable of quickly and appropriately determining and notifying image quality when taking a document.

  It is another object of the present invention to provide a digital camera and a program capable of accurately and appropriately determining and notifying image quality when taking a document.

In order to achieve the above object, a digital camera according to the first aspect of the present invention provides:
In a digital camera that acquires image data by converting incident light into digital data,
Detecting means for detecting movement of the digital camera at the time of shooting;
Determination means for determining whether or not the character shown in the image to be acquired can be read based on at least the detection result of the detection means;
Execution means for executing a predetermined operation based on the determination result of the determination means,
The determination means includes
A camera shake amount calculating means for calculating a camera shake amount on the acquired image based on at least the detection result of the detecting means;
A determination criterion storage means for storing determination criterion information indicating a criterion for determination;
Determining whether or not the character can be read based on the camera shake amount calculated by the camera shake amount calculating unit and the criterion information stored in the criterion storage unit;
The execution unit further includes an output unit that outputs predetermined notification information based on a determination result of the determination unit.
It is characterized by that.

In the above digital camera,
The determination criterion storage means stores a plurality of determination criterion information according to the use of the image to be acquired,
The determination means determines whether or not the character can be read based on the use of the image based on the camera shake amount calculated by the camera shake amount calculation means and the determination reference information stored in the determination reference storage means. It is desirable.

In the above digital camera,
It is desirable that the camera shake amount calculating unit calculates the camera shake amount based on at least a detection result of the detecting unit and a shutter speed set at the time of the photographing.

In the above digital camera,
It is desirable that the camera shake amount calculating means calculates the camera shake amount according to the size of the image to be acquired.

In the above digital camera,
It is desirable that the detection means detects a shake of the digital camera.

In the above digital camera,
The determination means includes
Area setting means for setting a predetermined area on the acquired image;
Character specifying means for specifying the character shown in the acquired image for each area set by the area setting means;
Character size specifying means for specifying the size of the character specified by the character specifying means on the image may further be provided.
It is desirable to determine whether or not the character shown in the image can be read based on the character size specified by the character size specifying means and the determination reference information stored in the determination reference storage means.

In the above digital camera,
The area setting means preferably sets the area based on lens performance of the digital camera.

In the above digital camera,
The determination criterion storage means stores a plurality of determination criterion information according to the use of the acquired image and the position on the image,
The determination means determines whether or not the character shown in the image is legible based on the character size specified by the character size specification means and the determination reference information stored in the determination reference storage means according to the application. It is desirable to do.

In the above digital camera,
The character size specifying means preferably specifies the character size on the image according to the size of the acquired image.

The above digital camera
It is desirable to further include an input means for inputting an instruction from the user.
It is desirable that the determination criterion storage unit updates the determination criterion information in accordance with a user instruction input to the input unit.

In the above digital camera,
It is desirable that the output means outputs information indicating whether or not the characters in the acquired image can be read at the time of photographing according to the determination result of the determination means.

In the above digital camera,
The output means, according to the determination result of the determination means, whether or not the characters shown in the acquired image can be visually read, whether or not the characters can be read by computer recognition, and / or It is desirable to output information indicating whether or not the entire image can be read as the notification information.

In the above digital camera,
The determination criterion storage means includes a determination criterion for determining whether or not the characters shown in the acquired image can be visually read and a determination criterion for determining whether or not character recognition by a computer is possible It is desirable to store determination criterion information indicating

In order to achieve the above object, a program according to the second aspect of the present invention is:
To a computer that controls a digital camera that converts incident light into digital data and acquires image data,
A step of setting and storing determination criterion information indicating a criterion for determining whether or not the character shown in the image to be acquired can be read, according to the use of the image;
Obtaining information indicating movement of the digital camera that causes camera shake;
Calculating the amount of camera shake on the acquired image based on the movement of the digital camera according to the size of the image;
Based on the calculated amount of camera shake and the determination criterion information, determining whether or not the character shown in the acquired image is readable according to the application;
Outputting predetermined notification information according to the determination result;
Is executed.

In order to achieve the above object, a program according to the third aspect of the present invention is:
To a computer that controls a digital camera that converts incident light into digital data and acquires image data,
Setting and storing determination criterion information indicating a criterion for determining whether or not the character shown in the acquired image is readable according to the use of the image and the position on the image;
Setting a predetermined area based on the lens performance of the digital camera on the image to be acquired; and
Specifying the characters shown in the image to be acquired for each of the set areas, and specifying the character size on the image;
Based on the specified character size and the determination criterion information, determining whether or not the character shown on the acquired image is readable according to the application;
Outputting predetermined notification information according to the determination result;
A program characterized by having executed.

  According to the present invention, the amount of camera shake is detected by detecting the movement of the digital camera at the time of shooting, and it is determined and notified whether or not the characters shown in the image can be read. Judgment can be made quickly. In addition, since an area is allocated on the photographed image and the character size is specified for each area to determine whether or not the character can be read, the image quality can be accurately determined and notified. Furthermore, since the determination reference value can be set according to the usage of the captured image, it is possible to appropriately determine and notify the image quality. As a result, it is possible to improve shooting efficiency, save labor in shooting or post-processing, and prevent waste of the memory area.

(Embodiment 1)
Embodiments according to the present invention will be described below with reference to the drawings. In this embodiment, when a character or document is photographed by a digital camera (imaging device) that acquires image data using an imaging device such as a CCD (Charge Coupled Device) (hereinafter referred to as “document photographing”). ) As an example. In this embodiment, “document shooting” refers to, for example, shooting characters written on paper, billboards, etc. with a digital camera, and recording document information (character information) as a substitute for taking in with a scanner or a memo. It shall be said. In addition, an image acquired by document shooting is referred to as a “document image”. Such a document image is converted into text data by being subjected to a predetermined character recognition process. That is, document information is digitized by photographing a document with a digital camera.

  The configuration of the digital camera according to this embodiment will be described with reference to FIGS. FIG. 1 is a block diagram showing a system configuration (internal configuration) of a digital camera 100 according to the present embodiment, FIG. 2 is a diagram showing an example of the appearance of the digital camera 100 (FIG. 2A is a front view, FIG. b) is a rear view). As illustrated, the digital camera 100 according to the present embodiment includes a control unit 110, an imaging unit 120, an input unit 130, an output unit 140, an image recording unit 150, a storage unit 160, a sensor unit 170, Is provided.

  The control unit 110 includes, for example, a CPU (Central Processing Unit) and controls each unit of the digital camera 100. Here, the control part 110 implement | achieves each process mentioned later by running the operation | movement program stored in the memory | storage part 160. FIG. Note that the control unit 110 includes a storage area for developing (loading) data and operation programs necessary for operation. This storage area (hereinafter referred to as “work area”) is configured by, for example, a register, a cache memory, and a RAM (Random Access Memory).

  The imaging unit 120 performs an imaging operation under the control of the control unit 110. In the present embodiment, as illustrated in FIG. 1, the imaging unit 120 includes a lens unit 121, a distance measurement / photometry unit 122, an imaging element 123, and the like.

  The lens unit 121 includes an optical member including a lens group and diaphragm blades, and a drive unit that drives the optical member. The drive unit drives the optical member under the control of the control unit 110. For example, the diaphragm blades are driven to achieve the set diaphragm (F value). In addition, when the lens unit 121 has an AF (Auto Focus) function, the optical member is driven to focus on an object to be photographed. The optical member is driven accordingly.

  The distance measuring / photometric unit 122 includes, for example, an infrared irradiation unit, a light receiving unit, a distance sensor, a light sensor, and the like, and measures a distance, a light amount (EV value), and the like from the digital camera 100 to a photographing target (subject).

  The imaging device 123 is configured by, for example, a CCD (Charge Coupled Device), and converts visible light (incident light) incident through the lens unit 121 into electric charge by photoelectric conversion and accumulates it. Here, the image pickup device 123 includes a predetermined AD conversion circuit and the like, and converts it into digital data based on the accumulated charge amount. That is, the converted digital data constitutes “image data” obtained from incident light.

  The input unit 130 is configured by a member operated by the user, and receives an instruction from the user. The input unit 130 inputs a user instruction to the control unit 110 by sending a predetermined signal corresponding to the operation to the control unit 110. In the present embodiment, the input unit 130 includes at least a shutter button 131 and an operation input unit 132.

  The shutter button 131 includes a button that can be moved up and down in response to a press by the user, and a signal that instructs the start of shooting (hereinafter referred to as a “shutter signal”) when pressed by the user. 110. Note that the shutter button 131 sends different signals to the control unit 110 depending on two states, a so-called “half-pressed” state and a “full-pressed” state. Here, “half-pressed” refers to a state where the shutter button 131 is pressed halfway, and “full-pressed” refers to a state where the shutter button 131 is fully pressed.

  As with a normal camera, the digital camera 100 according to this embodiment performs distance measurement, photometry, focusing (focusing) and the like (hereinafter referred to as “imaging preparation operation”) by “half-pressing”. “Press” to capture and record (hereinafter referred to as “imaging operation”). Therefore, when the shutter button 131 is half-pressed, a shutter signal indicating that effect (hereinafter referred to as “half-press signal”) is sent to the control unit 110, and the control unit 110 starts the focusing operation accordingly. And so on. When the shutter button 131 is fully pressed, a shutter signal indicating that effect (hereinafter referred to as a “full press signal”) is sent to the control unit 110, and the control unit 110 executes the start of an imaging / recording operation. To do. That is, the control unit 110 starts each operation for imaging upon reception of a signal transmitted from the shutter button 131.

  The operation input unit 132 includes, for example, predetermined operation buttons, dials, cursor keys, and the like, and instructions for changing various settings are input by user operations. In the present embodiment, it is used not only for changing / setting various modes including a photographing mode but also for setting a criterion for determining whether characters can be read in a document image. In this embodiment, it is assumed that “document shooting mode” is prepared as the shooting mode. When the digital camera 100 performs shooting of a document, the operation input unit 132 is operated to set the document shooting mode.

  The output unit 140 outputs various types of information notified to the user. In the present embodiment, the display unit 141 that outputs an image, the sound report unit 142 that outputs sound, lighting, flashing, and the like. The indicator part 143 which performs this light emission is provided. The display unit 141, the sound report unit 142, and the indicator unit 143 are configured on the back side of the digital camera 100 as shown in FIG. That is, it is desirable that the output information is configured at a position where it can be transmitted to the photographer (user).

  The display unit 141 is composed of, for example, a liquid crystal display device, and displays and outputs image information. In the present embodiment, in addition to displaying an image obtained by the image sensor 123 and an image recorded in the image recording unit 150, a menu screen for changing the setting, and information indicating a setting state and a warning to the user (for example, , Characters and icons) are displayed. In the present embodiment, an image or character information indicating a warning or guidance to the user according to whether or not the document image can be read is displayed. Note that when the display unit 141 includes a touch panel or the like, the display unit 141 may function as an input device equivalent to the operation input unit 132.

  The sound report unit 142 includes, for example, a speaker and outputs predetermined sound information. Here, sound (alarm sound, etc.) corresponding to various operations (for example, focusing, shutter pressing, etc.) at the time of shooting by the digital camera 100 is output, and in the present embodiment, depending on whether the document image can be read or not. A voice indicating a warning or guidance to the user is output.

  The indicator unit 143 includes, for example, an LED (Light Emitting Diode) and the like, and has a predetermined color or blinking pattern according to various operations (for example, focusing, shutter pressing, etc.) at the time of shooting by the digital camera 100. In addition to the light emission, in the present embodiment, the light is also emitted at the time of warning / guidance to the user according to whether or not the document image can be read.

  It should be noted that the warning and guidance output depending on whether the document image can be read may be performed by all of the display unit 141, the report sound unit 142, and the indicator unit 143, or any one of them. . It is assumed that which output device is used can be arbitrarily selected and set by the user.

  The image recording unit 150 includes, for example, a ROM (Read Only Memory) or a memory card including a storage device such as a flash memory, and records digital data converted by the AD conversion circuit of the image sensor 123. The image data obtained by the imaging operation of the imaging unit 120 is recorded. Further, it is assumed that the image recording unit 150 has a storage area (hereinafter referred to as “buffer”) that temporarily stores image data obtained by the image sensor 123.

The storage unit 160 includes, for example, a storage device such as a ROM or a flash memory, and stores a program executed by the control unit 110, data necessary for each process (hereinafter referred to as “process data”), and the like. In this embodiment, in addition to a program for executing various preparations for the imaging preparation operation and the imaging operation (hereinafter referred to as “imaging program”), in this embodiment, it is determined whether or not the characters shown in the document image can be read and notified. A program for storing is stored. More specifically, the following program is stored.
(P1) “Camera shake amount calculation program”: A program for calculating the amount of camera shake on a document image based on the detection value by the sensor unit 170, photographing parameters, etc. (P2) “Readability determination program”: calculated A program (P3) “determination criteria setting program” for determining the image quality of a document image based on the amount of camera shake and determining whether or not the characters shown in the document image are readable Program (P4) “notification information output program” for setting a reference value used for determination of: a program for outputting predetermined notification information based on the determination result of legibility

When the control unit 110 executes such a program, the control unit 110 realizes the following functions.
(F1) “Imaging function”: a function for operating the imaging unit 120 and acquiring image data based on incident light incident from the lens unit 121 (F2) “camera shake detection function”: based on a detection value of the sensor unit 170 Function for detecting the presence or absence of camera shake and calculating the amount of camera shake in the document image (F3) “readability determination function”: the image quality of the document image is determined based on the amount of camera shake, etc. Function for determining whether or not the characters shown in the image are legible (F4) “Judgment criteria setting function”: Function for setting judgment criteria for legibility by user's arbitrary input (F5) “Output function”: Reading Function to output notification information to the user according to the determination result

  In the present embodiment, each function is realized by software processing by the control unit 110 executing a program. For example, a circuit or the like that specially processes each function (so-called “ASIC” (Application By configuring the Specific Integrated Circuit)) in the digital camera 100, the above functions may be realized by hardware processing.

  Further, in the storage unit 160, as “process data”, for example, information indicating various settings required at the time of shooting such as a combination of an aperture value (F value) with respect to an exposure amount (EV value) at the time of shooting and a shutter speed, In the present embodiment, information indicating the criterion at the time of determination by the “readability determination function” (hereinafter referred to as “determination criterion information”) is stored. . That is, in the present embodiment, the legibility of the character is determined based on the degree of camera shake at the time of shooting by each process described later, and information indicating a reference for the camera shake determination is stored in the storage unit 160 in advance. The Here, the reference indicated in the determination reference information is indicated by a predetermined numerical value, for example, and functions as a threshold for legibility.

  Note that “reading” in the embodiment of the present invention means “a user (human) can visually recognize a character” when displaying an acquired document image or the like, or a character recognition process by a computer. In the above, “characters are recognized at a certain recognition rate (acceptable recognition rate)”. Hereinafter, human visual recognition (interpretation) is referred to as “visual recognition”, and computer recognition (interpretation) is referred to as “machine recognition”.

  In the present embodiment, whether or not the captured document image is decipherable is determined based on “the amount of camera shake” indicating the degree of camera shake at the time of shooting (details will be described later). Therefore, the determination criterion information according to the present embodiment indicates a predetermined reference value for the amount of camera shake. Here, “pixel” is adopted as the unit of the amount of camera shake. That is, when a blur occurs in an image due to camera shake, the blur width (blur width) is defined by the number of pixels constituting the image.

  Such determination criterion information is set in, for example, a “determination criterion information table” as shown in FIG. Here, a determination reference value is set in the “determination reference information table” according to the use application of the document image acquired by the digital camera 100. In the present embodiment, “visual recognition” and “machine recognition” are assumed as usages of the document image. Accordingly, as shown in FIG. 3 (a), items of “visual recognition” and “machine recognition” are prepared in the “set value” field where the determination reference value is set, and the determination reference value is independently set for each item. Is set.

  As described above, the determination reference value functions as a threshold for legibility, and these numerical values indicate the blur width on the image. Therefore, for example, if a camera shake with a blur width that is greater than or equal to the value set for “visual recognition” in the “determination criterion information table” occurs, it is determined that “character recognition cannot be performed visually”. become. Similarly, when a camera shake having a blur width equal to or greater than the value set in “machine recognition” occurs, it is determined that “cannot be recognized with a desired recognition accuracy in the character recognition process”. That is, if blurring that exceeds the determination reference value occurs, it means “not desired image quality”.

  The determination reference value set in the “determination reference information table” is determined in advance by the manufacturer of the digital camera 100 and can be arbitrarily set by the user. Therefore, as shown in FIG. 3A, the set value by the manufacturer is recorded as “default value”, and the set value by the user is recorded as “user set value”.

  Setting by the user is performed using the operation input unit 132 and the display unit 141. That is, by displaying the setting screen as shown in FIG. 4 on the display unit 141 and operating the operation input unit 132, a determination reference value desired by the user is input. The input information is recorded in “user set value” of the “determination reference information table”. Since the necessity of setting by the user is arbitrary, when there is no setting in the “user setting value”, the value set in the “default value” is adopted for the determination, and the “user setting value” is set. In this case, the value set in the “user set value” is adopted for the determination.

  Such setting of the determination reference value is an example, and the value and unit set as the determination reference value, the setting method, and the like are arbitrary. For example, the determination reference value to be set to “machine recognition” can be set according to a character recognition processing program, device recognition accuracy, and the like. In this case, the determination reference value of “machine recognition” is automatically set by, for example, cooperation (cooperation) between the digital camera 100 and the character recognition program as well as being settable by the user operating the operation input unit 132. You may make it set to.

  In this embodiment, the control unit 110 calculates the “hand shake amount” used to determine whether or not the image can be read based on the shake of the digital camera 100 (details will be described later). Depending on the focal length (f value) at the time of shooting, the number of recorded pixels (image size), and the like. In other words, the longer the focal length of the lens (that is, the telephoto side), the more susceptible to camera shake. Therefore, even if the degree of shaking of the digital camera 100 is the same, if the focal length differs, The amount (blur width) is also different. In addition, when the number of effective pixels of the image sensor 123 can be controlled to switch to a plurality of types of image sizes, the resolution differs for each image size. Therefore, when the blur width is represented by the number of pixels as in the present embodiment, if the resolution is different, the number of pixels representing it is different even if the blur degree is the same.

  That is, even if the shake (direction and amount) of the digital camera 100 that causes camera shake is the same, if the conditions such as the focal length and the image size at that time are different, the degree of shake on the image and that are expressed. The number of pixels will be different. Therefore, when calculating the amount of camera shake, an appropriate amount of camera shake is obtained by using a predetermined constant (hereinafter referred to as “camera shake amount constant C”) according to various conditions at the time of shooting. For this reason, in this embodiment, a “camera shake amount constant table” for defining this “camera shake amount constant C” is created in the storage unit 160 (FIG. 3B).

  As shown in FIG. 3B, the “camera shake amount constant table” corresponds to a combination of lens performance (for example, focal length f) of the digital camera 100 and recordable image size (number of recording pixels). A camera shake amount constant C is set. Note that the digital camera 100 according to the present embodiment has a so-called zoom function in which the focal length f is variable, and a plurality of types of image sizes (by controlling the number of effective pixels of the image sensor 123 ( It is possible to switch to (Resolution). In such a case, as shown in FIG. 3B, in the “camera shake amount constant table”, the zoom range (focal length range) is divided into, for example, predetermined steps (1 to n). "Shake amount constant C" is associated with the combination of the image size (for example, 1 to m types).

  That is, the “camera shake amount constant table” is set according to the performance of the digital camera 100, and is appropriately set according to the focal length of the lens, the obtainable image size, and the like. Further, since the total number of pixels of the image sensor 123 influences, the performance of the image sensor 123 is set in consideration. Such a setting value is determined based on an actual measurement value obtained by the manufacturer of the digital camera 100, for example. Note that information indicating the image size selected at the time of shooting is stored in the storage unit 160 as a shooting parameter.

  The storage unit 160 stores “notification information” output from the output unit 140. In the present embodiment, predetermined notification information is output in accordance with the legibility determined by processing described later. Therefore, in this embodiment, a “notification information table” as shown in FIG. 3C is prepared in the storage unit 160 in which information indicating the determination result of legibility is associated with output notification information. . In the item “notification information” of the “notification information table”, text data (or image data) indicating a predetermined message is recorded, and image data such as an icon is recorded as necessary.

  In the present embodiment, since the determination reference value is set independently for “visual recognition” and “machine recognition”, notification information is prepared according to the determination result for each application. For example, a message indicating that “visual recognition is possible but machine recognition is not possible” (since the judgment standard in “machine recognition” is usually more severe than the judgment standard in “visual recognition”) A message indicating that “recognition and machine recognition are both impossible” is recorded as notification information, and is selectively output according to a determination result for each application. In the example of FIG. 3C, the case where the determination result is “unreadable” is described as “NG”, and the case where it is “readable” is described as “OK”.

  In the “notification information table”, information indicating which notification method is set is also recorded. Here, the “notification method” is an output form of notification information, and is prepared according to the configuration of the output unit 140 of the digital camera 100. In this embodiment, for example, “message display”, “icon display”, “indicator light emission”, “voice notification”, “alarm notification”, and the like are prepared as notification methods (details will be described later). These notification methods are arbitrarily selected by the user, and the notification method desired by the user is selected and set by the operation of the operation input unit 132 or the like. In addition, when “indicator light emission” or “alarm notification” is prepared as the “notification method”, for example, information indicating a light emission pattern, a sound report pattern, etc. is recorded in the “notification information” column of the “notification information table”. It shall be.

  The sensor unit 170 includes, for example, an acceleration sensor, an angular velocity sensor (gyro sensor), and the like, and is a sensor (a shake sensor) that detects a movement (such as “shake”) of the digital camera 100 that causes a camera shake during shooting. is there. In the present embodiment, the digital camera 100 is assumed to be composed of an acceleration sensor, and an acceleration (mm / s) indicating the degree is sent to the control unit 110 as a detection value as needed.

  That is, the sensor unit 170 detects the presence or absence of camera shake at the time of shooting, and when a camera shake occurs, the degree is detected. Here, “camera shake” means that the digital camera 100 moves due to an external force acting on the digital camera 100 at the time of shooting (for example, a user operation such as pressing a shutter), and thus a shot image is blurred. Due to the occurrence of camera shake, the image quality deteriorates, and in document photographing, the readability of the acquired document image decreases. The sensor unit 170 detects such camera shake at the time of photographing by a physical detection operation. Note that the type of sensor and the detection method are arbitrary as long as camera shake during shooting can be detected.

  Note that each of the above-described configurations is a main part necessary for carrying out the present invention, and in addition to these, the digital camera 100 includes other configurations and functions necessary as a digital camera, and other additional configurations and functions. Are provided as necessary.

  Next, the operation of the digital camera 100 configured as described above will be described below with reference to the drawings. Each process to be described later is realized by the control unit 110 executing an operation program stored in the storage unit 160.

  The “document shooting process (1)” according to the first embodiment of the present invention will be described with reference to the flowcharts shown in FIGS. Here, characters (hereinafter referred to as “document”) written on a sheet of paper or a signboard are photographed by the digital camera 100 and stored as image data indicating the contents of the document. For example, the stored image data is processed by a predetermined character recognition program to be converted into text data or the like and extracted, thereby being used as a substitute for capturing with a conventional memo or scanner. Shooting a document for such a purpose is referred to as “document shooting”, and an image obtained by document shooting is referred to as a “document image”. The “document shooting process (1)” described below is started when the control unit 110 receives a shutter signal from the shutter button 131 in a state where “document shooting mode” is selected as the shooting mode. When the “document shooting mode” is selected, the image sensor 123 receives incident light that enters through the lens unit 121 and displays an image corresponding to the charge of the received element on the display unit 141. .

  When the user determines the composition, the angle of view, or the like by adjusting the position of the digital camera 100 or performing a zoom operation based on the image displayed on the display unit 141, the user presses the shutter button 131 (half-press). In response to this, a half-press signal is sent from the shutter button 131 to the control unit 110. The control unit 110 starts a shooting preparation operation when receiving a half-press signal from the shutter button 131 (step S101).

  Here, based on the distance measurement / photometry operation by the distance measurement / photometry unit 122, the lens unit 121 is driven to perform focusing (focusing) on the document, and an appropriate shutter speed and aperture value (imaging parameters). ) Is identified. Also, the focal length (f value) determined by the zoom operation is specified. It is assumed that the half-press signal continues to be sent from the shutter button 131 to the control unit 110 while the user is pressing the shutter button 131 halfway.

  When the document is in focus, the user instructs shooting by pressing the shutter button 131 fully. In response to this, a full-press signal is sent from the shutter button 131 to the control unit 110. When the control unit 110 receives a full-press signal from the shutter button 131, the control unit 110 determines that the instruction is a shooting instruction from the user (step S102: Yes), and drives the lens unit 121 so as to obtain the aperture specified in step S101. The image sensor 123 is exposed according to the shutter speed that has been set. Thereby, imaging is performed with the specified imaging parameter, and image data (captured image) corresponding to the incident light is acquired and stored in the buffer of the image recording unit 150 (step S103).

  For example, when the user releases the half-pressed state of the shutter button 131 due to interruption of shooting, the shutter signal from the shutter button 131 is interrupted, and the control unit 110 determines that there is no shooting instruction from the user ( Step S102: No), the process ends.

  When there is a shooting instruction, the control unit 110 acquires the detection value at that time from the sensor unit 170 simultaneously with the imaging operation in step S103 (step S104). More specifically, a detection value indicating the shaking of the digital camera 100 is acquired from the time when the full press signal is received until the time (seconds) corresponding to the shutter speed specified in step S101 elapses.

  The control unit 110 calculates the camera shake amount on the captured image acquired in step S103 based on the detection value acquired in step S104 and the shutter speed and focal length (f) specified in step S101 (step S105). . As described above, in the present embodiment, the camera shake amount on the image data is obtained by the number of pixels indicating the blur width. Here, the amount of camera shake is obtained by the control unit 110 calculating “camera shake amount (pixel) = detection value (mm / s) × shutter speed (s) × camera shake amount constant C”.

  That is, for example, when the digital camera 100 is shaken due to a load applied to the digital camera 100 when the user presses the shutter button 131, the sensor unit 170 determines the amount of movement of the digital camera 100 by the acceleration (mm / s). Detect as. Here, since the movement amount per second is shown, the movement amount (shake amount) of the digital camera 100 during exposure to the image sensor 123 is obtained by multiplying this by the shutter speed (second) that is the exposure time. I want. Furthermore, it is generated on the image by specifying and multiplying the camera shake amount constant C corresponding to the focal length (f) at the time of shooting and the selected image size from the “camera shake amount constant table” of the storage unit 160. The number of pixels indicating the blur width (shake amount) of the blur can be obtained.

  When the camera shake amount is obtained, the control unit 110 refers to the “determination reference information table” in the storage unit 160 and compares the determination reference value set to “visual recognition” with the obtained camera shake amount ( Step S106). Here, if a judgment reference value is set in “User setting value” in the “Judgment Criteria Information Table”, it is compared with that judgment reference value, and if it is not set, it is set to “Default Value”. Compare with the reference value.

  When the calculated camera shake amount is less than the determination reference value (FIG. 6, Step S107: Yes), the control unit 110 determines that “visual recognition” is “readable” (Step S108). On the other hand, when the amount of camera shake is equal to or greater than the determination reference value (step S107: No), the control unit 110 determines that “visual recognition” is “unreadable” (step S109).

  Next, the control unit 110 compares the determination reference value set in “machine recognition” in the “determination reference information table” with the calculated amount of camera shake (step S110). The selection of “user set value” or “default value” is the same as described above.

  When the calculated amount of camera shake is less than the determination reference value (step S111: Yes), the control unit 110 determines that “readable” in “machine recognition” (step S112). On the other hand, when the amount of camera shake is equal to or greater than the determination reference value (step S111: No), the control unit 110 determines that “unreadable” in “machine recognition” (step S113).

  The control unit 110 determines whether or not there is “unreadable” in the determination result in step S108 or S109 and in step S112 or S113 (step S114).

  If there is no “unreadable” in any of the determination results (step S114: No), the control unit 110 records the image data stored in the buffer in step S103 in the image recording unit 150 (step S117). The process ends. That is, in this shooting, there is no camera shake, or even if there is a camera shake, both “visual recognition” and “machine recognition” are readable levels. The acquired image is stored in the image recording unit 150 as a “document image”.

  On the other hand, if any of the determination results includes “unreadable” (step S114: Yes), the control unit 110 outputs notification information corresponding to the determination result from the output unit 140 (step S115). Here, the control unit 110 selects notification information corresponding to each determination result from the “notification information table” in the storage unit 160 and outputs the notification information from the output unit 140 in the set notification method.

  Here, for example, “message display”, “icon display”, “indicator emission”, “voice notification”, “alarm notification”, and the like are prepared as notification methods. These notification methods are arbitrarily selected according to the user's desire. In other words, the notification method is set in advance by operating the operation input unit 132 or the like. One of these notification methods may be selected, or a plurality may be selected in combination.

  When “message display” is selected, the message shown in the selected notification information is displayed on the display unit 141.

  When “icon display” is selected, a predetermined icon (pictogram) shown in the selected notification information is displayed on the display unit 141.

  When “indicator light emission” is selected, the indicator unit 143 lights up or blinks with a predetermined light emission pattern corresponding to the selected notification information. In this case, the prescribed light emission pattern functions as notification information. Here, as the light emission pattern, for example, a light emission color or a blinking pattern is defined in advance. For example, in the case where the indicator unit 143 is composed of LEDs of two colors of “green” and “red”, which color is to be blinked and how (flashing speed, etc.) is defined. Various detection events (for example, focusing, battery exhaustion, etc.) are associated in advance.

  When “voice notification” is selected, a message indicated by the selected notification information is output from the sound report unit 142. In this case, the output voice functions as notification information. Here, the text data acquired in the case of “message display” is acquired, and the message indicated by the text data is output from the sound report unit 142 as if a person is speaking by a predetermined speech synthesis method. Is done. Alternatively, when the “notification information table” stores sampling data of each uttered message as an audio file, the corresponding audio file is reproduced and output as audio.

  When “alarm notification” is selected, an alarm sound is output from the sound report unit 142 in a predetermined sound pattern corresponding to the selected notification information. In this case, a prescribed sound report pattern functions as notification information. The report sound pattern is defined from, for example, a tone color, a pitch, or a sound length.

  In the present embodiment, a display example will be described below assuming that “message display” is selected as the notification method.

  When both “visual recognition” and “machine recognition” are determined to be “unreadable” (steps S109 and S113), a message as shown in FIG. 7A is displayed on the display unit 141. Here, a message indicating that visual recognition and machine recognition are difficult due to camera shake is displayed, and advice information indicating countermeasures for avoidance is displayed (MSG11). That is, camera shake is likely to occur when the digital camera 100 is not stable or the shutter speed becomes long because the amount of light is small, so a countermeasure such as using a tripod or lighting is displayed.

  If “visual recognition” is determined as “readable” (step S108) and “machine recognition” is determined as “unreadable” (step S113), a message as shown in FIG. 7B is displayed. Is displayed on the display unit 141. Here, a message that visual recognition is possible but machine recognition is difficult due to camera shake is displayed, and advice information similar to the above is displayed (MSG12).

  Each message shown in FIG. 7 is an example, and messages according to other determination results may be prepared.

  In addition, on the display screen shown in FIG. 7, a message for inquiring the user whether or not to record an image and options for selecting an answer (“Yes” and “No”) to the inquiry are displayed. That is, in the present embodiment, the message as described above is displayed when there is “determination impossible” in any of the determination results, but the user makes an image according to the displayed message by making an inquiry as described above. Prompts the user to decide whether or not to record. For example, when “visual recognition” is used as the purpose of use of the document image acquired by the user, the requested image quality is obtained even when the message MSG12 is displayed. In this case, since the user desires to record the photographed image, the user selects an answer (“Yes”) indicating “image recording is necessary”. The user selects an answer by operating the operation input unit 132 or the like.

  When a user's answer to the inquiry is instructed according to the operation of the operation input unit 132, a signal indicating the content of the answer is sent to the control unit 110. Based on the received signal, control unit 110 determines the presence / absence of a recording instruction from the user (step S116).

  Here, when there is no recording instruction by the user (step S116: No), that is, when the answer to the inquiry is “no image recording required” (“No”), the control unit 110 displays the image stored in the buffer. Data is deleted (step S118), and the process is terminated.

  On the other hand, if there is a recording instruction from the user (step S116: Yes), the image data stored in the buffer is saved in the image recording unit 150 (step S117), and the process is terminated.

  That is, by displaying a message according to the readability determination for each of “visual recognition” and “machine recognition”, the user can select whether to record or discard the captured image on the spot according to the purpose. Can do.

  According to the above-mentioned “document shooting process (1)”, whether or not to interpret due to the influence of camera shake at the time of shooting is determined at the time of shooting, and notification information corresponding to the determination result is output. Or you can decide to discard. Here, since camera shake detection at the moment of shooting is performed based on the detection value from the sensor unit 170, detection is performed at a higher speed than when camera shake is detected by performing image processing on the acquired image.・ It can be judged. Therefore, in the case of continuous shooting, the next shooting can be performed quickly, and the shooting efficiency is not reduced.

  In addition, the determination of legibility is performed independently according to applications such as "visual recognition" and "machine recognition", and notification information according to each determination result is output. It is possible to appropriately select recording or discarding of images. Further, since the user can arbitrarily set the reference for determining the legibility, it is possible to appropriately determine the legibility according to the user's preference and the accuracy of the character recognition process to be used.

(Embodiment 2)
In the first embodiment, whether or not a document image can be read is determined by camera shake. However, there are other factors other than camera shake in the quality of readability. For this reason, the legibility is usually determined based on the character size (character size) shown in the photographed document image. However, a lens such as a digital camera has aberration due to its performance. Even if the sizes are the same, the character size may not be uniform over the entire surface of the photographed document image. Even if the character size is specified from such an image, it becomes inaccurate, so that the legibility determination based on the character size is also inaccurate.

In the present embodiment, a case will be described in which the digital camera 100 is used to more accurately determine the legibility based on the character size. The configuration of the digital camera 100 and the definition of terms are the same as those shown in the first embodiment, but in addition to the operation programs (P1 to P4) shown in the first embodiment, The program is stored in the storage unit 160.
(P5) “Character size specifying program”: a program for specifying the size of characters shown in the document image

In addition to the functions (F1 to F5) shown in the first embodiment, the following functions are realized in the present embodiment by the control unit 110 executing the “character size specifying program”.
(F6) “Character detection function”: a function for detecting the character portion shown in the document image and specifying the character size

  In this embodiment, the “readable / unreadable program (P2)” stored in the storage unit 160 determines the image quality of the document image based on the specified character size and the like, and displays the image on the document image. "A program for determining whether or not a read character is legible", and the "readability judgment function (F3)" realized by executing this program is an image of a document image based on a character size or the like. “A function for judging quality and judging whether or not the characters shown in the document image are legible”.

  Further, in the present embodiment, the “determination reference information table” (FIG. 3A) and the “notification information table” prepared in the storage unit 160 are used to determine whether or not the image can be read based on the character size rather than the camera shake amount. The content of (FIG. 3C) is different from that of the first embodiment. In addition, other processing data for performing determination based on the character size is also prepared in the storage unit 160. An example of processing data prepared in the storage unit 160 in the present embodiment will be described with reference to the drawings.

  In the present embodiment, a “determination criterion information table” as shown in FIG. In the present embodiment, whether or not a document can be read is determined based on the character size indicated in the document image. A character size serving as a reference for determining whether or not the document can be read is defined in advance, and a “determination reference information table”. Set to Here, it is designated in character size units (for example, “point”, “millimeter”, etc., hereinafter referred to as “default size”) normally used in documents and the like.

  As in the first embodiment, the determination reference value functions as a threshold for determining whether or not a document image can be read. That is, when the size of the character shown in the acquired document image is less than the determination reference value, it is determined that the character cannot be read, and when it is greater than the determination reference value, it is determined that the character can be read. The That is, the image quality of the acquired document image is determined based on the determination reference value.

  As in the first embodiment, the “determination criterion information table” is set in advance by the manufacturer of the digital camera 100 and can be arbitrarily set by the user. Setting by the user is performed using the operation input unit 132 and the display unit 141. That is, by displaying a setting screen as shown in FIG. 8B on the display unit 141 and operating the operation input unit 132, a determination reference value desired by the user is input. The input information is recorded in “user set value” of the “determination reference information table”. Since the necessity of setting by the user is arbitrary, when there is no setting in the “user setting value”, the value set in the “default value” is adopted for the determination, and the “user setting value” is set. In this case, the value set in the “user set value” is adopted for the determination.

  In the present embodiment, in the same manner as in the first embodiment, a plurality of determination reference values are set according to the usage (“visual recognition” and “machine recognition”) of the captured document image, and the lens performance of the digital camera 100 is also improved. Accordingly, a plurality of determination reference values are set.

  Here, lens aberration is assumed as “lens performance”. Lenses potentially have aberrations, the degree of which depends on lens performance. Then, distortion and blur may occur at the edge of the acquired image due to the influence of lens aberration. Thereby, for example, when a document composed of characters of the same character size is photographed, there may be a difference in character size between the central portion and the edge portion on the acquired image. That is, the part of the character where the distortion occurs is stretched in either direction, and as a result, the character size on the image becomes larger than the part of the character where the distortion does not occur. Therefore, when determining the legibility based on the character size on the image, accurate determination cannot be made even if the reference character size is uniformly defined.

  Therefore, in the present embodiment, as shown in FIG. 9A, areas of “central part” and “edge part” (hereinafter referred to as “determination area”) are set on the acquired image, and the character size is set. The determination reference value is set independently for each determination region. Hereinafter, the determination region at the center of the image is referred to as “determination region C”, and the determination region at the image edge is referred to as “determination region E”.

  Therefore, as shown in FIG. 8A, the “determination reference value table” according to the present embodiment includes items (images) indicating determination areas for “visual recognition” and “machine recognition” which are usage applications. "Center" indicating the determination area at the center of the image and "edge" indicating the determination area at the edge of the image) are prepared, and a determination reference value is set for each. Here, for the “default value” set by the manufacturer of the digital camera 100, for example, a determination reference value is set based on a verification result on the lens performance of the digital camera 100.

  In addition, as the “user setting value”, a determination reference value can be arbitrarily set according to a character recognition processing program used by the user, the recognition rate or performance of the apparatus, and the like. In addition, when the lens of the digital camera 100 is an interchangeable type or when a conversion lens can be attached, it can be set arbitrarily according to the performance of the interchangeable lens or the conversion lens. In such a case, for example, an appropriate determination reference value for a plurality of lens products may be prepared in advance as a default value by the manufacturer of the digital camera 100.

  In setting the character size determination reference value, it is desirable to support a plurality of types of units. Therefore, as shown in FIG. 8B, the user can select a desired unit by selecting means such as a pull-down menu. Information indicating which unit is selected is recorded in the “judgment reference value table” (FIG. 8A).

  Such setting of the determination reference value is an example, and the value and unit set as the determination reference value, the setting method, and the like are arbitrary. In this embodiment, in consideration of the influence of lens performance, the determination area is divided into the center and the edge of the image, and the determination reference value is set for each area. Or the performance of the digital camera 100.

  Therefore, the method is not limited to the method of dividing the “center portion” and the “edge portion” as shown in FIG. 9A. For example, as shown in FIG. 9B, the image may be divided into a plurality of rectangular regions. . Also in this case, a determination reference value is set for each determination region. In the case of such area division, for example, when a document written on a signboard or whiteboard is photographed from an oblique direction, a perspective difference occurs in the horizontal direction of the image, and on the photographed document image, a character on the far side Is small and the characters on the near side are large. That is, even if the character size is the same on the original document, the character size varies depending on the position on the captured image. In such a case, by setting a determination reference value corresponding to the perspective difference in each of the multi-divided areas shown in FIG. 9B, it is possible to accurately determine whether or not characters can be read for the entire image. .

  For such area division, for example, a photometric pattern (for example, spot photometry or multi-division photometry) by the distance measurement / photometry unit 122 may be applied. In the present embodiment, the following description will be made assuming that the determination region shown in FIG.

  Next, the “notification information table” prepared in the storage unit 160 in the present embodiment will be described with reference to FIG. Also in the present embodiment, as in the first embodiment, predetermined notification information corresponding to the determination result of legibility is output from the output unit 140. Therefore, the notification information set according to each determination result is recorded in the “notification information table” according to the present embodiment as in the case of the first embodiment. As described above, in this embodiment, in addition to the usage of the document image, the determination of whether or not the image can be read is made for each determination area in consideration of the lens performance. Therefore, as shown in FIG. For each of “recognition” and “machine recognition”, an item “center” and an item “edge” are prepared, and a judgment result (“OK” or “unreadable” indicating “readable”) is determined for each item. Notification information corresponding to “NG”) is set.

  Since the image acquired by the digital camera 100 is a raster image composed of dots (pixels), the size of characters shown in the captured image is defined by the number of dots. Here, since the unit of the character size set as the criterion value is a default unit such as points, the character size (dot) specified on the image is directly compared with the character size set as the criterion value Therefore, it cannot be determined whether or not it is legible.

  Therefore, as shown in FIG. 10B, a “character size correspondence table” in which the number of dots on the image is associated with the character size indicated in the default unit is prepared in the storage unit 160. Here, when a plurality of types of image sizes can be captured by controlling the number of effective pixels of the image sensor 123, the resolution differs for each image size. Therefore, even if the size of characters shown on images of different sizes is substantially the same, the number of dots (number of pixels) representing them varies depending on the image size. Accordingly, as shown in FIG. 10B, in the “character size correspondence table”, the number of dots and the default character size are associated with each image size that can be selected by the digital camera 100. Thereby, even when the image sizes are different, the character size on the image can be specified uniformly.

  Processing when the digital camera 100 configured as described above captures a document (“document capturing process (2)”) will be described with reference to flowcharts shown in FIGS.

  The “document shooting process (2)” is started when the control unit 110 receives a shutter signal from the shutter button 131 in a state where the “document shooting mode” is selected as the shooting mode. When the “document shooting mode” is selected, the image sensor 123 receives incident light that enters through the lens unit 121 and displays an image corresponding to the charge of the received element on the display unit 141. .

  When the user determines the composition, the angle of view, or the like by adjusting the position of the digital camera 100 or performing a zoom operation based on the image displayed on the display unit 141, the user presses the shutter button 131 (half-press). In response to this, a half-press signal is sent from the shutter button 131 to the control unit 110. The control unit 110 starts a shooting preparation operation when receiving a half-press signal from the shutter button 131 (step S201).

  Here, based on the distance measurement / photometry operation by the distance measurement / photometry unit 122, the lens unit 121 is driven to perform focusing (focusing) on the document, and an appropriate shutter speed and aperture value (imaging parameters). ) Is identified. Also, the focal length (f value) determined by the zoom operation is specified. It is assumed that the half-press signal continues to be sent from the shutter button 131 to the control unit 110 while the user is pressing the shutter button 131 halfway.

  The control unit 110 exposes the image sensor 123 with the specified aperture and shutter speed, acquires digital data based on the amount of charge accumulated in the image sensor 123 during that time, and performs image processing for determining whether or not the image can be read. The image to be performed (hereinafter referred to as “determination image”) is recorded in the buffer of the image recording unit 150 (step S202).

  The control unit 110 sets the determination regions (“determination region C” and “determination region E”) shown in FIG. 9A in the determination image recorded in step S202, and specifies the character portion for each determination region. Then, the character is cut out (step S203). Any known / conventional technique can be used to specify and cut out the character portion here. For example, the control unit 110 specifies the gradation of the background color of the determination image, and specifies a portion where pixels having gradations different from the gradation are uniformly dense as a character portion. Then, one character is cut out from each of the set determination areas. The number of characters to be cut out is arbitrary.

  The control unit 110 specifies the size of the character cut out for each determination area by the number of pixels (number of dots), and holds it in the work area (step S204). Here, the number of dots in the horizontal direction of the cut-out character is measured and used as the number of dots indicating the character size. The method for measuring the number of dots for specifying the character size is arbitrary. For example, the character size may be specified by the number of dots in the vertical direction of the character, or the sum of the number of horizontal dots and the number of vertical dots. The character size may be specified by a product or product.

  Based on the character size (number of dots) specified for each determination area and the currently selected image size (resolution), the control unit 110 stores a “character size correspondence table” ( FIG. 10C shows the converted character size (hereinafter referred to as “determination character size”) by converting the character size (number of dots) into a character size of a default unit (such as “point”). Information is held in the work area (step S205). Here, the character size is converted into a character size corresponding to the character size unit set in the “judgment criterion information table” (FIG. 8A).

  The control unit 110 compares the determination reference value set in the “determination reference information table” (FIG. 8A) in the storage unit 160 with the determination character size acquired for each determination region (step S206). ). Here, when the criterion value is set in “User setting value”, it is compared with the criterion value, and when it is not set, it is compared with the criterion value set in “Default value”. To do. In addition, for each of “visual recognition” and “machine recognition”, which are use applications of the image, the determination reference value set to “center” is compared with the determination character size for the determination region C, and “edge” Is compared with the determination character size for the determination region E.

  As a result of the comparison, when the determination character size specified in the determination region C is less than the determination reference value set to “center” of “visual recognition” (FIG. 12, Step S207: Yes), the control unit 110 Determines that the character at the center of the image is “readable” by visual recognition (step S208). On the other hand, when it is equal to or larger than the determination reference value (step S207: No), the control unit 110 determines that the character at the center of the image is “unreadable” by visual recognition (step S209).

  When the determination character size specified in the determination region E is less than the determination reference value set in the “edge” of “visual recognition” (step S210: Yes), the control unit 110 displays the image edge. The character of the part is determined as “readable” by visual recognition (step S211). On the other hand, when the value is equal to or greater than the determination reference value (step S210: No), the control unit 110 determines that the characters at the image edge are “unreadable” by visual recognition (step S212).

  When the character size for determination specified in the determination region C is less than the determination reference value set to “center” of “machine recognition” (step S213: Yes), the control unit 110 displays the image center portion. Is determined to be “readable” by machine recognition (step S214). On the other hand, if it is equal to or greater than the determination reference value (step S213: No), the control unit 110 determines that the character at the center of the image is “unreadable” by machine recognition (step S215).

  When the determination character size specified in the determination region E is less than the determination reference value set in the “edge” of “machine recognition” (step S216: Yes), the control unit 110 displays the image edge. Is determined to be “readable” by machine recognition (step S217). On the other hand, when the value is equal to or greater than the determination reference value (step S216: No), the control unit 110 determines that the characters at the image edge are “unreadable” by machine recognition (step S218).

  The control unit 110 outputs notification information corresponding to each determination result from the output unit 140 (FIG. 13, step S219). Here, the control unit 110 selects notification information corresponding to each determination result from the “notification information table” in the storage unit 160 and outputs the notification information from the output unit 140 in the set notification method.

  The “notification method” is the same as in the first embodiment. Here, a display example will be described below assuming that “message display” is selected as the notification method.

  When all the determination results are determined as “unreadable” (steps S209, S212, S215, and S218), a message as shown in FIG. 14A is displayed on the display unit 141. Here, since the characters are small, a message indicating that visual recognition and machine recognition are difficult throughout the image is displayed (MSG21).

  As for “visual recognition”, when it is determined that “readable” in the center of the image but “unreadable” in the image edge (steps S208 and S212), a message as shown in FIG. 14B is displayed. Displayed on the part 141. Here, although the character at the center of the image can be read by visual recognition, since the character is small, a message indicating that visual recognition of the image edge and machine recognition over the entire image is difficult is displayed (MSG22). .

  In “visual recognition”, it is determined that “reading is possible” in the entire image (steps S208 and S211), and in “machine recognition”, it is determined that “reading is impossible” in the entire image (steps S215 and S218), FIG. A message as shown in (c) is displayed on the display unit 141. Here, although the characters in the entire image can be read by visual recognition, a message indicating that machine recognition is difficult because the characters are small is displayed (MSG23).

  Further, in “visual recognition”, “readable” is determined for the entire image (steps S208 and S211), and in “machine recognition”, “readable” is determined at the image edge (step S218). A message as shown in d) is displayed on the display unit 141. Here, although the characters in the entire image can be read by visual recognition, since the characters are small, a message indicating that machine recognition of the image edge is difficult is displayed (MSG24).

  Since the output of such notification information is performed during the imaging preparation operation (half-pressed state of the shutter button 131), the user determines whether to shoot according to the output notification information. When it is determined that shooting is to be performed, the shutter button 131 is fully pressed. That is, a full press signal is sent from the shutter button 131 to the control unit 110. On the other hand, when the user does not perform shooting under the current shooting conditions due to a change in shooting conditions or the like, the half-pressed state of the shutter button 131 is released. That is, the half-press signal sent from the shutter button 131 to the control unit 110 is interrupted.

  Based on the state of the shutter signal from the shutter button 131, the control unit 110 determines whether there is a shooting instruction from the user (step S220). That is, when a full-press signal is received from the shutter button 131, it is determined that a shooting instruction from the user has been input. If the shutter signal (half-press signal) from the shutter button 131 is interrupted, it is determined that there is no shooting instruction from the user.

  When there is no shooting instruction from the user (step S220: No), the control unit 110 deletes the determination image stored in the buffer (step S221) and ends the process. In this case, for example, the control unit 110 waits for an instruction to start the next shooting preparation operation.

  On the other hand, when there is a user's photographing instruction (step S220: Yes), the control unit 110 records the determination image stored in the buffer as a photographed document image in the image recording unit 150 (step S222), and performs processing. finish.

  That is, for each of “visual recognition” and “machine recognition”, it is possible to know from the output notification information whether or not it is legible, so that the user can continue or stop shooting on the spot according to the purpose. You can choose. In addition, since it is determined whether or not the image can be read in consideration of the influence of the lens performance, it is possible to know whether or not each of the “visual recognition” and “machine recognition” can be read in the entire area of the image. It is possible to avoid recording an image having no image quality.

  According to the above “document shooting process (2)”, whether or not to interpret when the target document is shot is determined at the time of shooting, and notification information corresponding to the determination result is output. Can be determined. Here, the judgment of legibility is performed independently according to the use such as “visual recognition” and “machine recognition”, and the notification information according to each judgment result is output. , You can choose the right or wrong of shooting. Furthermore, since it is determined based on the lens performance of the digital camera 100 whether or not it is legible in the entire area of the document image when photographed, whether or not legibility can be accurately judged. Further, since the user can arbitrarily set the reference for determining the legibility, it is possible to appropriately determine the legibility according to the user's preference and the accuracy of the character recognition process to be used.

  According to each of the above embodiments, the image quality of the document image at the time of document shooting is determined at the time of shooting and notified to the user, so that an image with low image quality is not taken and recorded unnecessarily. As a result, it is possible to prevent useless shooting operations and consumption of storage areas, and to save labor and improve shooting efficiency during shooting or post-processing.

  That is, it is not necessary to re-shoot many times at the time of shooting, and it is not necessary to select a legible one from the images that have been shot, and the user's labor can be reduced. In addition, although it is difficult to determine the image quality with a display device provided in the digital camera, in the above processing, control is performed using the detection value by the sensor unit 170 and the image data acquired by the image sensor 123. Since the unit 110 determines whether or not it can be read and notifies it, the image quality can be determined quickly and accurately.

  The document image acquired in the above embodiment is preferably converted into text data or the like by character recognition processing (machine recognition), but the execution form of such character recognition processing is arbitrary. For example, the character recognition process can be executed by a computer device such as a personal computer. In this case, the document image data recorded in the image recording unit 150 is transferred to the computer apparatus, but the transfer method is arbitrary. For example, a predetermined interface (for example, USB (Universal Serial Bus) provided in the digital camera 100 is used. The document image data can be transferred by connecting to a computer device via a) or the like. Further, when the image recording unit 150 is constituted by a removable memory card, the computer device can transfer the document image data by reading it from the memory card.

  Such a character recognition process may be executed by the digital camera 100. In this case, a program (character recognition program) for performing character recognition processing is stored in the storage unit 160 of the digital camera 100, and the control unit 110 executes this character recognition program to perform character recognition processing. When character recognition processing is executed by the digital camera 100, conversion to text data can be performed on the spot where the image is taken. Text data converted by the digital camera 100 can be recorded in the image recording unit 150 or transferred to a computer device or the like.

  In the above embodiment, the notification information is output according to the determination result of legibility. However, the photographing operation of the digital camera 100 is automatically controlled according to the determination result to assist the user. Good. For example, when it is determined that “unreadable”, the control unit 110 drives the lens unit 121 to control the character size to be increased by the zoom function, or automatically flashes when camera shake occurs due to insufficient light amount. May be controlled to emit light.

  In addition, by applying a program for realizing each process described above to a digital camera whose functions can be expanded by updating the operation program, the existing digital camera can function as the digital camera 100 according to the embodiment. it can. In this case, the operation program according to the above embodiment is installed in the digital camera, and is executed by the control unit of the digital camera. As a result, the above-described processes are executed, and it is possible to accurately determine the image quality at the time of document shooting and to determine and notify whether or not the document can be read. A method for distributing such an operation program is arbitrary. For example, the operation program can be distributed by being stored in a recording medium such as a CD-ROM or a memory card, and can also be distributed via a communication medium such as the Internet. it can.

  Furthermore, you may provide the sensor part 170 shown in the said Embodiment 1 as a retrofit apparatus (module). In this case, the existing digital camera functions as the digital camera 100 described in the first embodiment by mounting the sensor unit 170 via a predetermined interface of the digital camera and applying a program for driving and controlling the sensor unit 170. Can be made.

  In the first embodiment, whether or not the image can be read by camera shake is determined, and in the second embodiment, whether or not the image can be read based on the character size is determined. However, both determination processes may be executed as a series of processes. In this case, for example, it is possible to first determine the readability based on the hand shake according to the first embodiment, and to perform the readability determination based on the character size according to the second embodiment when there is no influence due to the camera shake. .

  As described above, by applying the present invention as in the above-described embodiment, it is possible to quickly determine and notify whether or not characters can be read by camera shake during shooting. Further, it is possible to accurately determine and notify whether or not the character can be read according to the lens performance or the like. Furthermore, it is possible to appropriately determine and notify whether or not the characters can be read according to the usage of the captured image. As a result, it is possible to save labor at the time of shooting and improve shooting efficiency, and to prevent the memory area from being wasted.

1 is a diagram illustrating a system configuration of a digital camera according to an embodiment of the present invention. It is a figure which shows the external appearance of the digital camera concerning embodiment of this invention, (a) is a front view, (b) is a rear view. FIG. 2 is a diagram illustrating an example of information recorded in a storage unit illustrated in FIG. 1, in which (a) illustrates an example of a “determination reference value table” according to the first embodiment, and (b) illustrates “hand” according to the first embodiment. An example of the “blur amount constant table” is shown, and (c) shows an example of the “notification information table” according to the first embodiment. It is a figure which shows the example of the display screen at the time of the setting to the "judgment reference value table" shown to Fig.3 (a). It is a flowchart (front stage) for demonstrating "document photographing processing (1)" concerning Embodiment 1 of this invention. It is a flowchart (after stage) for demonstrating "document photographing processing (1)" concerning Embodiment 1 of this invention. FIG. 7 is a diagram for explaining an example of “notification information” output in “document photographing process (1)” shown in FIG. 6, and each of (a) and (b) is a table of messages corresponding to determination results. An example is shown. It is a figure for demonstrating the determination criterion in Embodiment 2 of this invention, (a) shows the example of the "determination reference information table" concerning Embodiment 2, (b) shows to the "determination reference value table". The example of the display screen at the time of a setting is shown. It is a figure for demonstrating the "determination area | region" concerning Embodiment 2 of this invention, (a) shows the example of the determination area | region set to the center part and edge part on an image, (b) is determination. An application example of the area is shown. FIG. 3 is a diagram illustrating an example of information recorded in a storage unit illustrated in FIG. 1, in which (a) illustrates an example of a “notification information table” according to the second embodiment, and (b) illustrates a “character size” according to the second embodiment. An example of “correspondence table” is shown. It is a flowchart (previous stage) for demonstrating "document photographing processing (2)" concerning Embodiment 2 of this invention. It is a flowchart (middle stage) for demonstrating "document imaging | photography process (2)" concerning Embodiment 2 of this invention. It is a flowchart (after stage) for demonstrating the "document imaging | photography process (2)" concerning Embodiment 2 of this invention. It is a figure for demonstrating the example of the "notification information" output by "document imaging | photography process (2)" shown in FIG. 13, Each of (a)-(d) is the table | surface of the message according to the determination result. An example is shown.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 ... Digital camera, 110 ... Control part, 120 ... Imaging part, 121 ... Lens unit, 122 ... Ranging and photometry part, 123 ... Imaging device, 130 ... Input part, 131 ... Shutter button, 132 ... Operation input part, 140 ... Output unit 141 ... Display unit 142 ... Reporting unit 143 ... Indicator unit 150 ... Image recording unit 160 ... Storage unit 170 ... Sensor unit

Claims (15)

In a digital camera that acquires image data by converting incident light into digital data,
Detecting means for detecting movement of the digital camera at the time of shooting;
Determination means for determining whether or not the character shown in the image to be acquired can be read based on at least the detection result of the detection means;
Execution means for executing a predetermined operation based on the determination result of the determination means,
The determination means includes
A camera shake amount calculating means for calculating a camera shake amount on the acquired image based on at least the detection result of the detecting means;
A determination criterion storage means for storing determination criterion information indicating a criterion for determination;
Determining whether or not the character can be read based on the camera shake amount calculated by the camera shake amount calculating unit and the criterion information stored in the criterion storage unit;
The execution unit further includes an output unit that outputs predetermined notification information based on a determination result of the determination unit.
A digital camera characterized by that. The determination criterion storage means stores a plurality of determination criterion information according to the use of the image to be acquired,
The determination means determines whether or not the character can be read based on the use of the image based on the camera shake amount calculated by the camera shake amount calculation means and the determination reference information stored in the determination reference storage means. ,
The digital camera according to claim 1. The camera shake amount calculating means calculates a camera shake amount based on at least the detection result of the detecting means and the shutter speed set at the time of shooting.
The digital camera according to claim 1, wherein the digital camera is a digital camera. The camera shake amount calculating means calculates a camera shake amount according to the size of the image to be acquired.
The digital camera according to claim 1, wherein the digital camera is a digital camera. The detecting means detects shaking of the digital camera;
The digital camera according to claim 1, wherein the digital camera is a digital camera. The determination means includes
Area setting means for setting a predetermined area on the acquired image;
Character specifying means for specifying the character shown in the acquired image for each area set by the area setting means;
Character size specifying means for specifying the size of the character specified by the character specifying means on the image, and
Based on the character size specified by the character size specifying means and the determination reference information stored in the determination reference storage means, determine whether or not the characters shown in the image can be read;
The digital camera according to any one of claims 1 to 5, wherein: The area setting means sets the area based on lens performance of the digital camera.
The digital camera according to claim 6. The determination criterion storage means stores a plurality of determination criterion information according to the use of the acquired image and the position on the image,
The determination means determines whether or not the character shown in the image is legible based on the character size specified by the character size specification means and the determination reference information stored in the determination reference storage means according to the application. To
The digital camera according to claim 6 or 7, wherein The character size specifying means specifies the character size on the image according to the size of the image to be acquired.
The digital camera according to claim 6, wherein the digital camera is a digital camera. It further comprises an input means for inputting an instruction from the user,
The determination criterion storage unit updates the determination criterion information in accordance with a user instruction input to the input unit.
The digital camera according to claim 1, wherein the digital camera is a digital camera. The output means outputs information indicating whether or not the characters in the acquired image are readable according to the determination result of the determination means,
The digital camera according to claim 1, wherein the digital camera is a digital camera. The output means, according to the determination result of the determination means, whether or not the characters shown in the acquired image can be visually read, whether or not the characters can be read by computer recognition, and / or Information indicating whether or not the entire image can be read is output as the notification information.
The digital camera according to claim 1, wherein the digital camera is a digital camera. The determination criterion storage means includes a determination criterion for determining whether or not the characters shown in the acquired image can be visually read and a determination criterion for determining whether or not character recognition by a computer is possible And storing criterion information indicating
The digital camera according to claim 1, wherein the digital camera is a digital camera. To a computer that controls a digital camera that converts incident light into digital data and acquires image data,
A step of setting and storing determination criterion information indicating a criterion for determining whether or not the character shown in the image to be acquired can be read, according to the use of the image;
Obtaining information indicating movement of the digital camera that causes camera shake;
Calculating the amount of camera shake on the acquired image based on the movement of the digital camera according to the size of the image;
Based on the calculated amount of camera shake and the determination criterion information, determining whether or not the character shown in the acquired image is readable according to the application;
Outputting predetermined notification information according to the determination result;
A program characterized by having executed. To a computer that controls a digital camera that converts incident light into digital data and acquires image data,
Setting and storing determination criterion information indicating a criterion for determining whether or not the character shown in the acquired image is readable according to the use of the image and the position on the image;
Setting a predetermined area based on the lens performance of the digital camera on the image to be acquired; and
Specifying the characters shown in the image to be acquired for each of the set areas, and specifying the character size on the image;
Based on the specified character size and the determination criterion information, determining whether or not the character shown on the acquired image is readable according to the application;
Outputting predetermined notification information according to the determination result;
A program characterized by having executed.

Images