JP2016197362A - Range specification program, range specification method, and range specification device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce, when selecting character strings from a document image, selection of a part other than characters as characters by mistake.SOLUTION: A range specification device 101 receives specification of a position in a document image 110, and extracts character candidate areas from the document image 110. The range specification device 101 extracts, from the extracted character candidate areas, the number of colors in a character candidate area close to a position designated by a user. The range specification device 101 specifies, from character candidate areas continuing from the character candidate area corresponding to the designated position, a character candidate area having the number of colors equal to or less than the extracted number of colors. The range specification device 101 determines the character candidate area corresponding to the designated position and the specified character candidate area as a selection range.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a range specification program, a range specification method, and a range specification device.

  Conventionally, there are cases where it is desired to copy and use a character string displayed on a screen, such as when there is a character string to be examined in a text displayed on a PC (personal computer), a tablet terminal, or a smartphone. For this reason, there is a technique for selecting a displayed character string.

  As a prior art, for example, when a user designates a position of document data, a character attribute including the designated position is acquired, and a character having the same attribute as the acquired character attribute is selected.

Japanese Patent Laid-Open No. 08-137867

  However, in the prior art, when a character string is selected from a document image, a part other than a character may be erroneously selected as a character. For example, in the case of a document image that is an image of a document, since characters in the document in the document image do not have a character attribute, it is not possible to select a character based on the character attribute. On the other hand, when an area having the same size as the area specified by the user is selected as a character, an area such as an icon whose size approximates that of a character is also erroneously selected as a character.

  In one aspect, the present invention provides a range designating program, a range designating method, and a range designating device that reduce the erroneous selection of a part other than a character when selecting a character string from a document image. Objective.

  According to one aspect of the present invention, designation of a position in a document image is accepted, a character candidate area is extracted from the document image, and among the extracted character candidate areas, a character candidate area corresponding to the position where designation is accepted is extracted. The number of colors is extracted, and from among the character candidate areas connected to the character candidate area corresponding to the position where the designation is accepted, the character candidate area whose number of colors in the character candidate area is equal to or smaller than the extracted color number is identified and the designation is accepted. A range designating program, a range designating method, and a range designating device for selecting a character candidate region corresponding to a position and a specified character candidate region are proposed.

  According to an aspect of the present invention, when selecting a character string from a document image, there is an effect of reducing erroneous selection of a portion other than a character as a character.

FIG. 1 is an explanatory diagram of an example of a range specifying method according to the embodiment. FIG. 2 is an explanatory diagram showing the difference in the number of colors depending on the image. FIG. 3 is a block diagram illustrating a hardware configuration example of the range specifying device 101. FIG. 4 is a block diagram illustrating a functional configuration example of the range specifying device 101. FIG. 5 is a flowchart illustrating an example of a range specifying process procedure of the range specifying apparatus 101. FIG. 6 is a flowchart illustrating an example of a character candidate region extraction processing procedure of the range specifying device 101. FIG. 7 is a flowchart illustrating an example of the character image color number extraction processing procedure of the range specifying device 101. FIG. 8 is a flowchart illustrating an example of a character area search processing procedure of the range specifying device 101. FIG. 9 is an explanatory diagram showing the line width of a character image. FIG. 10 is an explanatory diagram showing a search for a character candidate area. FIG. 11 is an explanatory diagram showing coordinate generation of a character string area. FIG. 12 is an explanatory diagram illustrating the integration of adjacent regions of connected components. FIG. 13 is an explanatory diagram showing a positional relationship between character candidate areas.

  Exemplary embodiments of a range specifying program, a range specifying method, and a range specifying apparatus according to the present invention will be described below in detail with reference to the drawings.

(Embodiment)
FIG. 1 is an explanatory diagram of an example of a range specifying method according to the embodiment. 1 receives a designation of a position in a document image, and selects a character area including a character corresponding to the position where the designation is accepted. Specifically, the range specifying device 101 is a computer such as a PC or a tablet terminal.

  Here, the document image is an image showing a document. For example, the document image is a photograph including an electronic document displayed on a PC screen such as PDF (Portable Document Format), a paper document image obtained by a scanner, or a document photographed by a digital camera. The designation of the position is to determine one point in the document image. For example, the range designation device 101 can set a coordinate axis for a document image and designate a position by coordinates. The character area is an area where characters are continuous in the document. Specifically, for example, the character area is an area of a character string in which characters are arranged.

  Conventionally, there are cases where it is desired to copy and use a character string displayed on a screen, such as when there is a word to be examined in a character string displayed on a PC, tablet terminal, or smartphone. For this reason, there is a technique for selecting a character string to be displayed.

  For example, if the displayed document is an electronic document in which a character code is stored in the document, the character string of the word can be copied by placing the cursor on the start point of the target word and dragging with the mouse. it can.

  On the other hand, in the case of a document displayed on a document image or a document displayed on the screen of an application that does not permit copying of the character code, the character code cannot be used. For this reason, for example, the user can select the area | region containing the character string to select based on an image by designating two vertexes of the area | region surrounding a character string. In this case, since the user designates two vertices of the area, the user operation becomes complicated. Further, when a small screen such as a smartphone is operated with a finger, it is difficult for the user to specify two vertices of an area surrounding a character string.

  For this reason, there is a technique in which the attribute of the position of the document data specified by the user is acquired instead of specifying the two vertices, and the character having the same attribute as the acquired character attribute is selected. Here, the attribute of the character is additional information indicating the character or setting of the character. For example, the character attributes include font properties of characters such as Gothic and Mincho, and character settings such as underline.

  However, in the case of a document image, since there is no character attribute, it is not possible to determine a character using the character attribute. For this reason, for example, the character region can be determined as a region having a size approximate to the region specified by the user. However, in this case, if the icons have the same size, an area other than a character such as an icon is erroneously recognized as a character.

  Therefore, in the embodiment, when selecting a character area from a document image, the range specifying device 101 selects a character candidate area that is connected to the specified character candidate area and is equal to or less than the number of colors of the character candidate area. Thereby, the range specifying device 101 can reduce erroneous selection of portions other than characters as characters when selecting characters from a document image. For this reason, even when the character code is not included and the character attribute cannot be extracted, the user can select the character region by designating one point in the document image.

  Hereinafter, an example of the range specifying device 101 according to the embodiment will be described. In the example of FIG. 1, the range specifying device 101 is an example of specifying the range of the character string “file1” of the document image 110.

  (1) The range designating device 101 accepts designation of a position in the document image 110. For example, the range designation device 101 accepts designation of a position by an operation in which the user touches and clicks a point on the document image 110 with a finger.

  In the example of FIG. 1, an icon and a character string “file1” are displayed on the document image 110, and the range specifying device 101 specifies a position having the shortest distance from the area where “l” is displayed in the document image 110. Accept.

  (2) The range specifying device 101 extracts a character candidate area from the document image 110. Here, the character candidate area is an area in the document image 110 where a character may exist. For example, the range specifying device 101 generates a connected component of the pixels of the document image 110 and extracts a character candidate region based on the size of the region obtained by integrating adjacent connected components.

  In the example of FIG. 1, the range specifying device 101 extracts character candidate areas 111 to character candidate areas 116 from the document image 110. Here, the range designating apparatus 101 extracts the icon area as the character candidate area 111 because the size of the icon area approximates that of the character area.

  (3) The range designating device 101 extracts the number of colors of the character candidate area corresponding to the position where the designation is accepted from the character candidate areas.

  In the example of FIG. 1, the range specifying device 101 calculates the distance between the character candidate area 111 to the character candidate area 116 and the position specified by the user, specifies the character candidate area 114 with the shortest distance, and sets the character candidate. The number of colors in the area 114 is extracted. FIG. 1 shows that the character candidate area 114 is specified by hatching. Here, since the character candidate area 114 is composed of white pixels and black pixels, 2 is extracted as the number of colors of the character candidate area 114.

  (4) The range designating device 101 identifies a character candidate area in which the number of colors of the character candidate area is equal to or less than the extracted number of colors among the character candidate areas connected to the character candidate area corresponding to the position where the designation is accepted. Here, the character candidate area connected to the character candidate area corresponding to the position where the designation is accepted is a character candidate area which continues adjacent to the character candidate area corresponding to the position where the designation is accepted.

  Here, the range specifying device 101 uses the fact that the number of colors is different between the case where there is a character in the character candidate region and the case where there is no character in the character candidate region, and whether or not there is a character in the character candidate region. Judging.

  FIG. 2 is an explanatory diagram showing the difference in the number of colors depending on the image. FIG. 2A shows a character image composed of two-color pixels surrounded by a circumscribed rectangular area. Here, the circumscribed rectangular area is a rectangular area surrounding the character image. The character image is an image including characters included in the document image. The character image has foreground pixels representing the character body and background pixels representing the background. Foreground pixels are often a single color. In addition, when various colors are used for the background pixels, it is difficult to read the characters, so the background pixels are often of a single color. For this reason, a character image often has two-color pixels.

  FIG. 2B is a character image having three color pixels surrounded by a circumscribed rectangular area. Here, a decorative expression such as a shadow may be used for the character. For this reason, the character may have two-color pixels including a shadow. In FIG. 2B, the first foreground pixel is a normal character pixel, and the second foreground pixel indicates a pixel representing a shadow. In this case, three-color pixels are used in the character image including background pixels.

  On the other hand, images other than character images often use more colors than character images. For example, FIG. 2C is an enlarged view of an icon placed in front of the file name. The icons are conspicuous in multiple colors so that the user can distinguish them from characters. For example, as shown in FIG. 2C, since the background pixel has gradation, the background pixel is divided into a dark region and a thin region. For this reason, the background pixel uses a plurality of colors.

  As described above, with the exception of specially designed characters, character images are represented by a single color, such as black characters, red characters, and blue characters. In addition, even when there is a shadow, the characters are expressed in two colors. Thus, the character image is expressed in two colors or three colors including the background.

  On the other hand, images that are not characters, such as icons, are rarely expressed in one color, and more colors are often used than character images. This is the same even when the image is, for example, a gray image having no color component. A character image is similar to a color image in that two or three kinds of brightness values are used, whereas a non-character image uses pixels of a plurality of brightness values.

  Returning to FIG. 1, in the example of FIG. 1, the range specifying device 101 obtains the number of colors of the character candidate areas 111 to 113, 115, and 116 that are connected to the character candidate area 114 corresponding to the position where the specification is accepted. . Here, since the character candidate area 111 is an icon and gradation is used for the background, the number of colors is larger than two colors. On the other hand, since the character candidate areas 112, 113, 115, and 116 are characters, the number of colors is two. For this reason, the range designating apparatus 101 identifies character candidate areas 112, 113, 115, and 116 that are not more than the number of colors in the character candidate area 114. FIG. 1 shows that the character candidate areas 112, 113, 115, and 116 are specified by hatching.

  (5) The range specifying device 101 sets the character candidate region corresponding to the position where the specification is received and the identified character candidate region as the selection range. Further, the range designating device 101 can select a region including the character candidate region corresponding to the position where the designation is received and the identified character candidate region as the selection range.

  In the example of FIG. 1, the range specifying device 101 selects a character candidate region 114 corresponding to the position where the specification is received and a region 117 including the specified character candidate regions 112, 113, 115, and 116 as the selection range.

  As described above, the range designating apparatus 101 accepts designation of a position in the document image 110, extracts character candidate areas 111 to 116 from the document image 110, and accepts designation from the character candidate areas 111 to 116. The number of colors of the character candidate area 114 corresponding to the position is extracted. Thereafter, the range designating apparatus 101 has the number of colors in the character candidate area of the character candidate areas 111 to 113, 115, 116 connected to the character candidate area 114 corresponding to the position where the designation is received being equal to or less than the extracted number of colors. Character candidate areas 112, 113, 115, and 116 are specified. Finally, the range designating apparatus 101 sets the character candidate area 114 corresponding to the position where the designation is accepted and the identified character candidate areas 112, 113, 115, and 116 as the selection range.

  As a result, the range specifying device 101 can easily select a character string in a document image by specifying with a mouse or a finger, which is inappropriate due to erroneous selection of a region that is not a character compared to the conventional case. Area selection can be reduced.

  Therefore, the user can select a character area by designating one point in the document image. Even when the user operates a small screen such as a smartphone with a finger, it is easy to select a character area.

(Hardware configuration example of range specification device 101)
FIG. 3 is a block diagram illustrating a hardware configuration example of the range specifying device 101. In FIG. 3, a range specifying device 101 includes a CPU (Central Processing Unit) 301, a memory 302, an I / F (Interface) 303, a disk drive 304, a disk 305, a display 306, an input device 307, Have Each component is connected by a bus 300.

  Here, the CPU 301 governs overall control of the range specifying device 101. The memory 302 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and a flash ROM. Specifically, for example, a flash ROM or ROM stores various programs, and the RAM is used as a work area of the CPU 301 as a storage unit. The program stored in the memory 302 is loaded into the CPU 301 to cause the CPU 301 to execute the coded process.

  The I / F 303 is connected to a network 310 such as a LAN, a WAN, or the Internet through a communication line, and is connected to another computer via the network 310. The I / F 303 controls an internal interface with the network 310 and controls input / output of data from other computers. For example, a modem or a LAN adapter may be employed as the I / F 303.

  The disk drive 304 controls reading / writing of data with respect to the disk 305 according to the control of the CPU 301. The disk 305 stores data written under the control of the disk drive 304. Examples of the disk 305 include a magnetic disk and an optical disk.

  A display 306 displays data such as a document, an image, and function information as well as a cursor, an icon, or a tool box. As the display 306, for example, a liquid crystal display, an organic EL (Electroluminescence) display, or the like can be adopted.

  The input device 307 has keys for inputting characters, numbers, various instructions, and the like, and inputs data. The input device 307 may be a keyboard or a mouse, or may be a touch panel type input pad or a numeric keypad.

  Note that the range specifying device 101 may not include the disk drive 304, the disk 305, and the like among the components described above. The range specifying device 101 may include, for example, an SSD (Solid State Drive), a scanner, and a printer in addition to the above-described components.

(Functional configuration example of range specification device 101)
FIG. 4 is a block diagram illustrating a functional configuration example of the range specifying device 101. In FIG. 4, the range specifying device 101 includes an extraction unit 401, an attribute extraction unit 402, a specification unit 403, and a generation unit 404. Specifically, the control unit including the extraction unit 401, the attribute extraction unit 402, the specifying unit 403, and the generation unit 404 is, for example, a program stored in a storage device such as the memory 302 illustrated in FIG. Is executed by causing the CPU 301 to execute the function. The processing result of each functional unit is stored in, for example, a storage device such as the memory 302 illustrated in FIG.

  The extraction unit 401 has a function of extracting a character candidate area from the input image. For example, the extraction unit 401 inputs a document image from the input device 307, displays the document image on the display 306, and receives coordinate designation from the input device 307. The extraction unit 401 can also input a document image from the network 310 via the I / F 303. The extraction unit 401 extracts a character candidate area from the image. Here, the extraction unit 401 can also set a partial area in the document image and extract a character candidate area from the partial area. Further, since the image input and processed by the range specifying device 101 is a document image, the document image may be abbreviated as an image in the following description.

  For example, the extraction unit 401 binarizes an image, generates a connected component, and extracts an image attribute of the connected component. The extraction unit 401 determines whether or not the connected component is a character partial region based on the image attribute, and integrates adjacent regions of the connected component that is the character partial region. Here, the character partial area is an area in which a character part may exist. The proximity region will be described later in detail with reference to FIG.

  For example, the extraction unit 401 determines whether or not the integrated region is a character candidate region, and extracts the integrated region that is determined to be a character candidate region.

  The attribute extraction unit 402 has a function of extracting an attribute of an image included in the character candidate region from the character candidate region extracted by the extraction unit 401. For example, the attribute extraction unit 402 selects a representative character candidate area, and extracts attributes from the selected character candidate area. Further, for example, the attribute extraction unit 402 extracts the number of colors, the character size, the black pixel density, the line width, or the complexity of the character candidate area as the attribute. Here, the attribute extraction unit 402 extracts attributes using the image before the extraction unit 401 performs the process of binarizing the image.

  The attribute extraction unit 402 uses the attribute of the image included in the character candidate area corresponding to the position of the coordinate received from the input device 307 as the representative attribute among the extracted image attributes. Here, for example, the attribute extraction unit 402 sets the attribute of the image included in the character candidate area closest to the coordinate position received from the input device 307 as the representative attribute.

  For example, the attribute extraction unit 402 cuts out a character image in the character candidate region, classifies pixels in the cut out character image by color clustering, removes noise from the character image, and counts the number of colors.

  The specifying unit 403 has a function of determining whether the character candidate area is a character area based on the attribute extracted by the attribute extracting unit 402. Here, the character region is a character candidate region including characters.

  For example, the specifying unit 403 sequentially searches for adjacent character candidate areas based on the relative positional relationship between the character candidate areas, and specifies the character areas constituting the character string. Also, the specifying unit 403 determines whether the character string is vertical writing or horizontal writing and determines the search direction. The identifying unit 403 searches upward and downward when the character string is vertically written, and searches rightward and leftward when horizontally written.

  For example, when the adjacent area is searched by the search, the specifying unit 403 determines whether an image included in the adjacent area is a character or a character. Here, the adjacent region is a region that satisfies a predetermined adjacent condition. Specifically, the adjacent region is a region including characters that may belong to the same character string.

  For example, the specifying unit 403 determines whether an image included in the adjacent area is a character or a character by comparing the attribute of the adjacent area with the representative attribute. Here, when the attribute is the number of colors, the specifying unit 403 determines that the image included in the adjacent area is a character when the number of colors of the adjacent area is equal to or less than the number of colors of the representative attribute.

  For example, when the number of colors of the representative attribute is two, the specifying unit 403 may determine that the image included in the adjacent area is a character when the number of colors of the adjacent area is three. it can.

  For example, the specifying unit 403 specifies a character candidate area determined to be a character as a character area. Thereafter, the specifying unit 403 can also update the representative attribute using the attribute of the character candidate area determined to be a character.

  The generation unit 404 has a function of generating character string coordinates from the character area determined by the specifying unit 403. For example, the generation unit 404 generates a rectangular area that encloses all circumscribed rectangles of the specified character candidate area, and generates upper left coordinates and lower right coordinates of the rectangular area.

(Example of range specification processing procedure)
FIG. 5 is a flowchart illustrating an example of a range specifying process procedure of the range specifying apparatus 101. In FIG. 5, first, the range designation device 101 inputs and displays an image (step S501). For example, the range specifying device 101 inputs an image scanned by a scanner or an image captured by a digital camera from the input device 307 or the I / F 303 and displays the image on the display 306.

  Next, the range specifying device 101 receives the coordinates in the image (step S502). For example, the range specifying device 101 receives the coordinates in the image from the input device 307. Specifically, when the input device 307 is a pointing device such as a mouse, the range specifying device 101 receives coordinates in the image by an operation in which the user clicks one point in the displayed image. When the input device 307 is a touch panel integrated with the display 306, the range specifying device 101 receives the coordinates in the image by an operation in which the user touch-clicks one point in the displayed image.

  Next, the range specifying device 101 extracts a character candidate area (step S503). Here, the character candidate region extraction processing procedure by the range specifying device 101 will be described later with reference to FIG.

  The range specifying device 101 can also set a partial area before extracting a character candidate area. Here, the partial area is an area within a preset range in the image. For example, an area within a predetermined distance from the received coordinates in the image can be set as a partial area. In this case, for example, since the range specifying apparatus 101 performs the subsequent processing in the partial area, the range specifying processing can be performed at high speed.

  Next, the range specifying device 101 extracts the attribute of the character image (step S504). Here, the character image is an image including characters included in the extracted character candidate area. In addition, the range specifying apparatus 101 extracts attributes using the image before performing the process of binarizing the image performed in step S503. The process of extracting the number of colors as the attribute of the character image by the range specifying device 101 will be described later with reference to FIG.

  Furthermore, the range specifying device 101 can further extract character size, black pixel density, line width, and complexity as attributes of the character image. For example, the range designation device 101 can calculate the character size from the vertical and horizontal sizes of the character candidate area. Further, for example, the range specifying device 101 can calculate the black pixel density by counting the number of white pixels and black pixels of the binary image in the character candidate area.

  Further, for example, the range designating device 101 can obtain the line width by scanning the binary image of the character candidate area vertically and horizontally and obtaining the average value of the lengths of continuous black pixels (run length). . Since bold and thin characters indicate different values depending on the line width, the line width can be used as information for determining whether or not the character is a character.

FIG. 9 is an explanatory diagram showing the line width of a character image. FIG. 9A shows an example in which a binary image is scanned in the horizontal direction to obtain a length of continuous black pixels. FIG. 9B shows a black image obtained by scanning the binary image in the vertical direction. It is an example which calculates | requires the length with which a pixel continues. Here, details of the line width are described in Reference Document 1 below.
(Reference 1: IEICE Transactions Vol. J96-D No. 4 pp1029-1038)

  Further, for example, the range specifying device 101 scans a binary image of a character candidate area vertically and horizontally, and based on the number of times of changing from a black pixel to a white pixel and the number of times of changing from a white pixel to a black pixel, The complexity of can be obtained.

  Next, the range specifying device 101 extracts representative attributes (step S505). For example, the range designating device 101 sets the character image attribute obtained from the character candidate area closest to the coordinates received from the user as the representative attribute. Here, the coordinates received from the user are (xr, yr), and the rectangular coordinates of one character candidate area are represented by the coordinates of the upper left corner and the lower right corner (x1, y1) − (x2, y2).

In this case, the range specifying device 101 determines the center coordinates (xc, yc) of the rectangle as
xc = (x1 + x2) / 2, yc = (y1 + y2) / 2
Can be obtained. The range specifying device 101 sets the distance d between the received coordinates and the character candidate area as d = √ ((xc−xr) ² + (yc−yr) ² ).
The character image attribute of the character candidate area having the smallest distance d can be used as the representative attribute.

Next, the range specifying device 101 searches for a character area (step S506). Here, the search of the character area is a process in which the range designating device 101 sequentially searches for adjacent character candidate areas based on the relative positional relationship of the character candidate areas, and specifies the character areas constituting the character string. For example, the range specifying device 101 can determine whether the character string is vertical writing or horizontal writing and determine the search direction. Here, details of a method for determining whether a character string is written vertically or horizontally are described in Reference Document 2 below.
(Reference 2: Japanese Patent Laid-Open No. 06-089330)

  FIG. 10 is an explanatory diagram showing a search for a character candidate area. As shown in FIG. 10A, the range designating device 101 first accepts designation of a character candidate area. Next, as shown in FIG. 10B, the range specifying device 101 first searches for a character candidate region in the right direction. Here, since the leftmost character candidate region in FIG. 10B is not an adjacent region which will be described later with reference to FIG. 13, the range specifying device 101 does not perform a search. In FIG. 10B, the character candidate area and the searched area are represented by a thick line square. Next, as shown in FIG. 10C, the range specifying device 101 searches for a character candidate region in the left direction. Here, the range specifying apparatus 101 searches from the right at the beginning, but may first search from the left.

  The process of searching for character candidates in the right direction by the range specifying device 101 will be described later with reference to FIG. Here, FIG. 8 illustrates the process of searching for a character candidate in the right direction, but the process of searching for a character candidate in the left direction, the upward direction, and the downward direction is performed in the same manner as the process of searching in the right direction. be able to.

  Finally, the range specifying device 101 generates the coordinates of the character string area (step S507). For example, the range specifying device 101 generates the coordinates of the circumscribed rectangle of the specified character area. For example, the range specifying device 101 generates the coordinates of a rectangular area that encloses all circumscribed rectangles of the specified character area. For example, the range specifying device 101 generates upper left coordinates and lower right coordinates of the rectangular area.

  FIG. 11 is an explanatory diagram showing coordinate generation of a character string area. Here, an area represented by a square is a character candidate area, and a thick line square is a specified character candidate area. The range specifying device 101 generates coordinates of a dotted rectangular area including a thick square.

  Thereby, a series of processing in this flowchart is completed. By executing this flowchart, the range specifying device 101 can generate the coordinates of the character string area corresponding to the received coordinates.

(Example of character candidate area extraction processing procedure)
FIG. 6 is a flowchart illustrating an example of a character candidate region extraction processing procedure of the range specifying device 101. First, the range specifying device 101 binarizes an image (step S601). Specifically, the range specifying device 101 classifies the pixels in the image as either white pixels or black pixels. Here, when a partial region is set in the image, the range specifying device 101 can binarize the partial region in the image.

  Next, the range specifying device 101 generates a connected component (step S602). Specifically, the range designating apparatus 101 groups black pixels adjacent in four neighborhoods (up, down, left, and right) as connected components.

  Next, the range specifying device 101 extracts the image attribute of the connected component (step S603). For example, the range designating device 101 obtains image attributes such as the rectangular size and the density of black pixels in the circumscribed rectangular area of the connected component. Here, the circumscribed rectangular area is, for example, a minimum rectangular area including a connected component. The rectangular size is the height and width of the circumscribed rectangular area.

  Next, the range designating apparatus 101 determines whether or not all connected components are character partial areas (step S604). For example, the range designating apparatus 101 determines that the image component attribute of the connected component is within a certain range as a character partial area as an element constituting a character or a part of the character.

  Next, the range specifying device 101 integrates the adjacent regions of the connected components determined to be character partial regions (step S605). For example, the range specifying device 101 integrates the circumscribed rectangular areas that overlap or those that are close to each other.

  FIG. 12 is an explanatory diagram illustrating the integration of adjacent regions of connected components. In the example of FIG. 12, FIG. 12A is an example in which circumscribed rectangular areas are close to each other, and FIG. 12B is an example in which circumscribed rectangular areas are overlapped. .

  Next, the range specifying device 101 determines whether or not the merged area is a character candidate area (step S606). For example, the range specifying device 101 determines whether or not it is a character candidate area based on the size of the integrated area. Specifically, the range specifying apparatus 101 determines the character size in advance such that the vertical size is H pixels and the horizontal size is W pixels, and “height = 0.2 × H to 2 × H pixels”, “width” = 0.1 × W to 2 × W pixels ”is determined as a character candidate region. Here, the character size is the number of vertical and horizontal pixels of a rectangle.

  When it determines with the integrated area | region being a character candidate area | region (step S606: Yes), the range designation | designated apparatus 101 extracts an integrated area | region as a character candidate area | region (step S607). When it determines with the integrated area | region not being a character candidate area | region (step S606: No), the process of the range designation | designated apparatus 101 progresses to step S608.

  Next, the range specifying device 101 determines whether or not the determination has been completed for all the integrated regions (step S608). If the determination is not completed for all the integrated regions (step S608: No), the process of the range specifying device 101 returns to step S606. When the determination is completed for all the integrated areas (step S608: Yes), the process of the range specifying device 101 ends.

  Thereby, a series of processing in this flowchart is completed. By executing this flowchart, the range specifying device 101 extracts a character candidate region from the image. Here, the details of the character candidate area extraction processing are described in Reference Document 2 described above.

(Example of character image color number extraction processing procedure)
FIG. 7 is a flowchart illustrating an example of the character image color number extraction processing procedure of the range specifying device 101. First, the range specifying device 101 cuts out a character image in the character candidate area (step S701).

  Next, the range specifying device 101 classifies the pixels in the cut out character image by color clustering (step S702). For example, the range specifying device 101 creates a group of colors that can be regarded as the same color in a character image.

  Next, the range specifying device 101 removes noise from the character image (step S703). For example, the range designating device 101 counts the number of pixels belonging to each color group and removes noise by deleting groups that do not satisfy a certain number of pixels. Here, the fixed number of pixels can be, for example, 5% of the total number of pixels. As a result, the range specifying device 101 can remove noise due to local fluctuations due to blurring or color misalignment of the character image.

  Next, the range specifying device 101 counts the number of colors of the character image (step S704). For example, the range specifying device 101 counts the number of color groups remaining after removing noise as the number of colors of the character image.

  Next, the range specifying device 101 determines whether or not the number of colors of all the character candidate areas has been extracted (step S705). When the number of colors of all the character candidate areas is not extracted (step S705: No), the process of the range specifying device 101 returns to step S701. When the number of colors of all the character candidate areas has been extracted (step S705: Yes), the process of the range specifying device 101 ends.

Thereby, a series of processing in this flowchart is completed. By executing this flowchart, the range specifying device 101 extracts the number of colors of the character image in the character candidate area. Here, details of a method of classifying pixels by color clustering are described in Reference Document 3 below.
(Reference 3: JP-A-2002-042055)

(Example of character area search processing procedure)
FIG. 8 is a flowchart illustrating an example of a character area search processing procedure of the range specifying device 101. First, the range specifying device 101 sets a current character area (step S801). For example, the range specifying device 101 sets a character candidate area from which representative attributes are extracted as the current character area.

  Next, the range specifying device 101 searches for an adjacent region in the right direction (step S802). Here, the adjacent region is a region including characters that may belong to the same character string. Specifically, the adjacent area is a character candidate area that satisfies the current character area and the adjacent condition described below.

  FIG. 13 is an explanatory diagram showing a positional relationship between character candidate areas. The adjacent condition will be described with reference to FIG. In FIG. 13, d is the distance between the character candidate areas, v is the length of the overlapping area of the character candidate areas, h1 is the height of the left character candidate area, h2 is the height of the right character candidate area, and h is 2. The average height of two character candidate areas (h = (h1 + h2) / 2). In this case, the character candidate area that satisfies the adjacent condition with the current character area is a character candidate area that satisfies d <h and v> h / 2.

  Next, the range specifying device 101 determines whether an adjacent area has been searched (step S803). When the adjacent area is not searched (step S803: No), the process of the range specifying device 101 ends.

  When the adjacent area is searched (step S803: Yes), the range designating apparatus 101 determines the character non-character (step S804). Here, the range specifying device 101 determines whether the image included in the searched adjacent area is a character or not.

  For example, the range specifying device 101 determines whether an image included in the adjacent region is a character or a character by comparing the attribute of the adjacent region with the representative attribute. For example, when the attribute is the number of colors, the range specifying device 101 determines that the image included in the adjacent area is a character when the number of colors in the adjacent area is equal to or less than the number of colors of the representative attribute.

  Further, for example, when the number of colors of the representative attribute is two colors, the range specifying device 101 determines that the image included in the adjacent area is a character when the number of colors of the adjacent area is two colors or three colors. It can also be determined. When the number of colors of the representative attribute is two colors, the range specifying device 101 determines that the two-color or three-color character candidate area is a character in consideration of the number of colors due to the shadow of the character. If the number of representative attribute colors is three, similarly, the range designating apparatus 101 determines that the two-color or three-color character candidate area is a character. When the number of colors of the representative attribute is four or more, the range specifying device 101 can determine that the character candidate area having the number of colors of the representative attribute or less is a character.

This is summarized as follows.
Number of representative attribute colors: Two colors → Number of colors determined as characters: Two to three colors Number of representative attribute colors: Three colors → Number of colors determined as characters: Two colors to three colors Number of representative attributes: N colors → Number of colors to be determined as characters: 2 to N colors

  Further, for example, the range designating device 101 further uses the attributes such as the character size, black pixel density, line width, and complexity for the image included in the adjacent area that satisfies the condition of the number of colors, It is also possible to determine whether an image included in is a character or not.

  When the non-character determination is made (step S804: non-character), the process of the range specifying device 101 returns to step S802. When the character is determined (step S804: character), the range designating apparatus 101 identifies the adjacent region as the character region (step S805).

  Next, the range specifying device 101 updates the current character area (step S806). For example, the range specifying device 101 sets the character area specified in step S805 as the current character area.

  Next, the range specifying device 101 updates the representative attribute (step S807). For example, the range specifying device 101 obtains the average or median attribute value of the identified character candidate area, and updates the representative attribute with the average or median value. In this case, even if the attribute of the character candidate area received first is special, it can gradually approach an appropriate representative attribute as the character string search is performed. Thereafter, the processing of the range specifying device 101 returns to step S802, and when the adjacent area is not searched, the processing of the range specifying device 101 ends.

  Thereby, a series of processing in this flowchart is completed. By executing this flowchart, the range specifying device 101 can search for a character candidate area of an image and specify a character area.

  As described above, the range specifying device 101 accepts designation of a position in a document image, extracts a character candidate area from the document image, and among the character candidate areas, a character candidate area corresponding to the position where designation is accepted. Extract the number of colors. Thereafter, the range designating device 101 identifies a character candidate area in which the number of colors of the character candidate area is equal to or less than the extracted number of colors among the character candidate areas connected to the character candidate area corresponding to the position where the designation is accepted. Finally, the range designating apparatus 101 sets the character candidate area corresponding to the position where the designation is accepted and the identified character candidate area as the selection range.

  As a result, the range specifying device 101 can easily select a character string in a document image by specifying with a mouse or a finger, which is inappropriate due to erroneous selection of a region that is not a character compared to the conventional case. Area selection can be reduced.

  For this reason, the range specification apparatus 101 can implement | achieve the function in which a user selects the character string displayed on screens, such as PC and a smart phone, by simple operation. In addition, since the range designating device 101 can select a character only by comparing the number of colors, the character can be selected without increasing the load on the range designating device 101. Here, the character string selected by the range specifying device 101 can be easily converted into text by the character recognition function. For example, a word to be examined is photographed with a camera, and recognition and Web search are executed with one touch. Can do. Furthermore, the range designation device 101 allows foreign travelers to easily know the meaning and pronunciation of character strings such as guidebooks, signboards, menus, etc., and enables effective use of real-world character image information.

  Here, the range specifying device 101 first extracts a character candidate area, and compares the number of colors of the character candidate area with the number of colors extracted from the character candidate area corresponding to the position where the designation is accepted. For this reason, even if there is a noise in the character candidate area connected to the character candidate area corresponding to the position where the designation is received and there is a character candidate area exceeding the number of extracted colors, the character candidate area ahead of the character candidate area Can be selected.

  In addition, the range designating device 101 can also update the extracted number of colors based on the number of colors of the specified character candidate area in response to specifying the number of character candidate areas equal to or less than the number of colors.

  Thereby, even when the number of colors of the character candidate area received first is special, the range designation device 101 gradually approaches the number of colors to the number of colors of the appropriate representative attribute as the character string search is performed. be able to.

  Further, the range designating device 101 has a character candidate in which the number of colors in the character candidate area is equal to or less than the extracted number of colors, and the complexity of the character candidate area or the line width in the character candidate area satisfies a predetermined condition. An area can be specified.

  Thereby, the range designation | designated apparatus 101 can determine more correctly whether a character candidate area | region is a character area by using complexity or a line | wire width.

  In addition, when the number of extracted colors is 2, the range designating device 101 can specify a character candidate area with the number of colors of 3 or less.

  Thereby, even if the number of colors of the character candidate area received first is 2, the range specifying device 101 can specify a character having decorations such as a shadow and having a color number of 3 or more.

  The range specifying method described in this embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. The range specifying program is recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, an MO, and a DVD, and is executed by being read from the recording medium by the computer. Further, the range specifying program may be distributed via a network such as the Internet.

  The following additional notes are disclosed with respect to the embodiment described above.

(Appendix 1) Accepting the designation of the position in the document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A range specification program for causing a computer to execute processing.

(Additional remark 2) According to having specified the character candidate area | region below the number of colors, the process to specify updates the color number based on the color number of the specified character candidate area | region, and updated the color The range designation program according to appendix 1, wherein character candidate areas of a number equal to or less are specified.

(Additional remark 3) The said process to specify is that the number of colors of a character candidate area is below the said number of colors among the character candidate area | regions connected to the character candidate area | region corresponding to the position which received the said specification, and a character candidate area | region The range designation program according to appendix 1 or 2, wherein a character candidate region that satisfies a predetermined condition of a complexity of the line or a line width of a line in the character candidate region is specified.

(Supplementary note 4) When the number of colors is two, the specifying process specifies a character candidate area having a number of colors of three or less. The range designation according to any one of Supplementary notes 1 to 3 program.

(Appendix 5) Accepting designation of position in document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A computer-readable recording medium in which a range specifying program for causing a computer to execute processing is recorded.

(Appendix 6) Accepting designation of position in document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A range specifying method, wherein the computer executes the processing.

(Appendix 7) Accepting designation of position in document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A range designating device comprising a processing unit.

101 range designation device 401 extraction unit 402 attribute extraction unit 403 identification unit 404 generation unit

Claims (6)

Accepts the specification of the position in the document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A range specification program for causing a computer to execute processing.   The specifying process updates the number of colors based on the specified number of colors of the character candidate area in response to specifying the number of character candidate areas equal to or less than the number of colors, and updates the number of characters equal to or less than the updated number of colors. The range designation program according to claim 1, wherein a candidate area is specified.   In the process of specifying, the number of colors of the character candidate area is equal to or less than the number of colors among the character candidate areas connected to the character candidate area corresponding to the position where the designation is received, and the complexity of the character candidate area or The range designation program according to claim 1 or 2, wherein a character candidate region in which a line width of a line in the character candidate region satisfies a predetermined condition is specified.   The range specifying program according to any one of claims 1 to 3, wherein when the number of colors is 2, the specifying process specifies a character candidate area having a color number of 3 or less. Accepts the specification of the position in the document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A range specifying method, wherein the computer executes the processing. Accepts the specification of the position in the document image,
Extracting a character candidate area from the document image,
Among the extracted character candidate regions, extract the number of colors of the character candidate region corresponding to the position where the designation is received,
Among the character candidate areas connected to the character candidate area corresponding to the position where the designation has been received, the number of colors of the character candidate area is specified to be equal to or less than the extracted number of colors,
The selected character candidate area corresponding to the position where the designation is received and the identified character candidate area are selected.
A range designating device comprising a processing unit.

Images