Image reading device, image reading method, and image forming apparatus

Abstract

To provide an image reading device that can effectively use image information.SOLUTION: An image reading device 1 comprises a reading unit 2 and an object extraction unit 3. The reading unit 2 reads an input image P from a sheet S on which images P including one or more items I are formed. The extraction unit extracts an object B from the input image P. The object extraction unit 3 comprises an identification unit 4, an identification information providing unit 33, and a storage unit 34. The identification unit 4 identifies the items I from the input image P. The identification unit 4 identifies, as the object B, one or more items I that are determined to be approximate to each other on the basis of the degree of approximation related to a form calculated on the basis of information related to the form of the items I. The identification information providing unit 33 provides identification information to the object B identified by the identification unit 4. The storage unit 34 stores the object B together with the identification information and the items I constituting the object B.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an image reading apparatus, an image reading method, and an image forming apparatus. [Background technology]

[0002] A conventional image reading device is described in Patent Document 1. The image reading device described in Patent Document 1 extracts text information in an area specified by the user from an image read from a sheet, and makes the text information available for later use. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Korean Patent Publication No. 10-2016-0097394 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the image reading device described in Patent Document 1 only extracts text information as a whole from an image read from a sheet. Also, the image reading device described in Patent Document 1 cannot extract information other than text information. Therefore, the image reading device described in Patent Document 1 may not be able to effectively utilize the information of the image, which is an information asset read from a sheet.

[0005] The present invention has been made in view of the above-mentioned problems, and has as its object to provide an image reading apparatus, an image reading method, and an image forming apparatus that can effectively utilize information on the image read from a sheet. [Means for solving the problem]

[0006] According to a first aspect of the present invention, an image reading device includes a reading unit and an object extraction unit. The reading unit reads an input image from a sheet on which an image including one or more items is formed. The object extraction unit extracts an object from the input image. The object extraction unit includes an identification unit, an identification information assignment unit, and a storage unit. The identification unit identifies the item from the input image. The identification unit identifies one or more items that are determined to be similar to each other based on a degree of similarity regarding the shape calculated from information about the shape of the item as the object. The identification information assignment unit assigns identification information to the object identified by the identification unit. The storage unit stores the object together with the identification information and the items that constitute the object.

[0007] According to a second aspect of the present invention, an image forming apparatus includes an image reading device and an image forming unit. The image reading device is described in the first aspect. The image forming unit forms an image on a recording medium. The image forming unit forms the combined image on the recording medium.

[0008] According to a third aspect of the present invention, an image reading method includes reading an input image from a sheet on which an image including one or more items is formed, identifying the items from the input image, and identifying one or more items that are determined to be similar to each other based on a degree of similarity regarding their shapes calculated based on information about the shapes of the items as objects, assigning identification information to the identified objects, and saving the identification information and the objects. [Effects of the Invention]

[0009] According to the present invention, the image reading device, the image reading method, and the image forming device can effectively utilize the information of the image read from the sheet. [Brief explanation of the drawings]

[0010] [Figure 1]3A and 3B are diagrams illustrating an example of an image of a sheet read by an image reading apparatus according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing the configuration of the image reading device. [Figure 3] FIG. 2 is a diagram illustrating an example of the configuration of an identification unit of the image reading device. [Figure 4] 10 is a flowchart showing an object extraction process of the image reading device. [Figure 5] 10 is a flowchart showing an object processing process of the image reading device. [Figure 6] FIG. 10 is a diagram showing an example of a processed object. [Figure 7] 10 is a flowchart showing a process of combining objects in the image reading device. [Figure 8] FIG. 10 is a diagram showing an example of a combined image in which objects are combined. DETAILED DESCRIPTION OF THE INVENTION

[0011] An image reading device 1 according to an embodiment of the present invention will be described below with reference to the drawings. In the drawings, identical or corresponding parts are designated by the same reference numerals, and description thereof will not be repeated. In the following description, terms indicating positions or directions, such as "upper," "lower," "horizontal," and "vertical," may also be used. These terms are used for convenience to facilitate understanding of the embodiment, and are not limited to positions or directions when actually implemented.

[0012] [About the composition of Sheet S] An example of an image P read from a sheet S by an image reading device 1 according to an embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of an image P (an example of an input image) read from a sheet S by the image reading device 1.

[0013] As shown in FIG. 1, image P includes multiple items I. Here, item I is a collection of elements (e.g., pixels) that form a certain form (shape, pattern, color, etc.) in image P, and is defined as the smallest unit of components of image P. Item I is divided into text items It and graphic items Is. Text items It are components whose form is text and that make up words, clauses, etc. Each text item It includes one or more characters. Graphic items Is are components that have a form other than text.

[0014] As will be explained in more detail later, for each item I, a group of one or more items I that are similar in shape to one another is defined as an object B. Object B is divided into text objects Bt, which are a group of text items It, and graphic objects Bs, which are a group of graphic items Is.

[0015] The present invention extracts an object B from an image P and makes the extracted object B available for later use.

[0016] [Configuration of image reading device 1] Next, the configuration of an image reading device 1 according to an embodiment of the present invention will be described with reference to Figures 1 and 2. Figure 2 is a diagram showing the configuration of the image reading device 1.

[0017] 2, the image reading device 1 includes a reading unit 2, an object extraction unit 3, a control unit 10, and an input / output unit 5. The image reading device 1 in FIG. 2 further includes an object processing unit 6 and an object combining unit 7, which will be described later. The reading unit 2 is typically a scanner, and optically reads an image P of a sheet S and converts it into digital data. One or more items I are formed on the sheet S.

[0018] The object extraction unit 3 is a computer program, and includes an identification unit 4, an identification information assignment unit 33, a grouping unit 31, a separation unit 32, and a storage unit 34. The identification unit 4 identifies, as object B, one or more items I that are determined to be similar to each other based on the degree of similarity in shape calculated based on information about the shape of the items I.

[0019] The grouping unit 31 groups one or more items I identified by the identification unit 4 as a group of objects B as items I included in the same object B. The separation unit 32 separates the items I included in the object B grouped by the grouping unit 31 into individual items I that make up the object B so that the items I can be selected collectively as the object B and can be edited individually.

[0020] The identification information assigning unit 33 assigns identification information to the object B that has been identified by the identifying unit 4 and grouped by the grouping unit 31.

[0021] The storage unit 34 stores object B together with its identification information as a collection of items I that make up object B. Specifically, the storage unit 34 is configured as a system that stores and manages object B, and is equipped with functions to assist the user in using object B, such as searching for and selecting stored object B. With the above configuration, the object extraction unit 3 extracts object B from image P.

[0022] The control unit 10 controls the communication unit and memory unit (not shown). The control unit 10 includes a processor such as a CPU (Central Processing Unit). The memory unit includes a storage device such as a ROM (Read Only Memory) or RAM (Random Access Memory). The storage device of the memory unit stores data and computer programs. For example, the memory unit stores data of the image P read by the reading unit 2, information about operations received from the input / output unit 5, and computer programs constituting the object extraction unit 3, object processing unit 6, and object combination unit 7. In addition, a portion of the memory area of ​​the memory unit functions as a storage unit 34. The processor of the control unit 10 executes the computer program stored in the storage device to process the data of the image P stored in the storage device. The control unit 10 then displays the processing results on the input / output unit 5.

[0023] The input / output unit 5 is a user interface that has an input function for receiving operations to the image reading device 1 as input, and an output function for outputting various information from the image reading device 1. The input / output unit 5 is, for example, a touch panel display that combines an input function and a display function. The input / output unit 5 displays the results of operations performed by the image reading device 1 as output under the control of the control unit 10.

[0024] [Configuration of the recognition unit 4] Next, a configuration example of the recognition unit 4 of the image reading device 1 will be described with reference to Fig. 1 and Fig. 3. Fig. 3 is a diagram showing a configuration example of the recognition unit 4. (Layer identification unit 41) 3, the identification unit 4 includes a layer identification unit 41, a text identification unit 42, a color identification unit 43, and an arrangement pattern identification unit 44. The layer identification unit 41 includes, for example, a depth detection processing unit 41b.

[0025] The depth detection processing unit 41b performs depth detection processing to detect how the items I overlap in the image P as depth information using information about the shapes of the items I. For example, the depth detection processing unit 41b estimates the position in a virtual depth direction for each item I included in the image P. Then, the depth detection processing unit 41b sets a predetermined reference position in the depth direction of the image P and estimates the distance from the reference position to each item I as depth information (an example of approximation) for each item I, thereby estimating how the items I overlap in the image P. The depth detection processing unit 41b may be configured to perform depth detection processing on the image P using a neural network model obtained in advance by machine learning.

[0026] A CNN (Convolutional Neural Network) is typically used as the neural network. CNN is a type of neural network that is widely used in fields such as image recognition. CNN is one method for realizing deep learning. In this embodiment, the CNN extracts features of each item I from information about the shape of the item I. By using the CNN, the depth detection processing unit 41b can recognize that the item I is the same item I even if the position of the item I in the image P changes, the item I is rotated, or the item I is flipped over.

[0027] When a neural network model (CNN model) using CNN as the neural network is constructed, machine learning is performed in advance. For example, a set of input / output relationship data is made up of an image as input and information about the shape of each item in the image and depth information as output. The CNN model is obtained as a neural network model that can estimate the depth information and shape type of each item I from an arbitrary image P by performing machine learning in advance using multiple sets of different input / output relationship data as training data. The depth detection processing unit 41b uses the CNN model to estimate depth information from information about the shape of the item I and estimate how the items I overlap. Note that by performing machine learning in advance using combinations of images P with different shape types (text or graphics) and depth information as training data, the CNN model can estimate whether each item I is a text item It or a graphic item Is.

[0028] Based on the depth information estimated by the depth detection processing unit 41b, the layer identification unit 41 identifies items I in the image P that are determined to overlap similarly as belonging to the same layer L. The layer identification unit 41 also identifies whether the form of each item I included in each layer L is text. That is, the layer identification unit 41 identifies a text item It, a text layer Lt including the text item It, a graphic item Is, and a graphic layer Ls including the graphic item Is from the image P. Note that in FIG. 1, the layer identification unit 41 estimates that, in an overlapping portion K where the text item It and the graphic item Is overlap, the text layer Lt including the text item It is above the graphic layer Ls including the graphic item Is. Based on the overlapping portion between the text layer Lt and the graphic layer Ls, the layer identification unit 41 estimates that a missing portion M, where an element is missing, is formed in the graphic item Is included in the graphic layer Ls.

[0029] (Text Identification Unit 42) The text identification unit 42 includes, for example, a typography analysis processing unit 42b and a character detail analysis processing unit 42c.

[0030] The typography analysis processing unit 42b performs typography analysis processing to calculate the degree of similarity in the form, composition, etc. of each text item It in the text layer Lt by analyzing elements including the shape, size, placement, font, color, background, etc. of the text. The typography analysis processing unit 42b may be configured to perform this processing in combination with OCR (Optical Character Recognition) processing. By combining OCR processing, such as edge detection and shape recognition, with typography analysis processing, the text identification unit 42 can analyze the shapes of characters more accurately.

[0031] The character detail analysis processing unit 42c calculates the degree of similarity regarding the font style of the text item It by identifying the font family, font style, and the like.

[0032] The text identification unit 42 identifies, as text objects Bt, one or more text items It whose forms are determined to be similar to each other based on the similarity degrees of the text items It obtained by the typography analysis processing unit 42b and the character detail analysis processing unit 42c. That is, the text identification unit 42 identifies, from the text layer Lt, one or more text items It whose forms are similar to each other as text objects Bt. In FIG. 1, the text identification unit 42 identifies, for each text item It included in the text layer Lt, groups of text items It in the upper and central portions that are similar to each other. Then, from the text layer Lt, the text identification unit 42 identifies the group of text items It in the upper portion as a first text object Bt1, and the group of text items It in the central portion as a second text object Bt2.

[0033] (Color identification unit 43) The color identification unit 43 includes, for example, a color clustering processing unit 43b. The color clustering processing unit 43b performs color clustering processing to group each item I in the image P into multiple clusters (a collection of items I, i.e., objects B) based on differences in color. The color of the item I can be characterized by attributes such as hue, saturation, and brightness. The color clustering processing unit 43b groups the items I in the image P using the attributes of the item I.

[0034] The color clustering processing unit 43b may be configured to perform processing using a machine learning model that performs clustering processing, such as k-means. The machine learning model that performs clustering processing is constructed, for example, by unsupervised learning, which repeatedly groups various sample data into multiple clusters based on the k-means. The color clustering processing unit 43b, for example, quantitatively calculates an average color (an example of similarity) that is the average color of each item I in the image P. Then, for each item I, the color clustering processing unit 43b groups one or more items I that are determined to be similar to each other based on the average color into the same cluster. That is, the color identification unit 43 uses color clustering processing to classify multiple items I into multiple colors, and identifies one or more items I with similar colors from the text layer Lt and the graphic layer Ls as objects B.

[0035] (Arrangement pattern identification unit 44)

[0036] The arrangement pattern identification unit 44 has, for example, an object processing unit 44b and a median filtering processing unit 44c. The object processing unit 44b and median filtering processing unit 44c perform an arrangement pattern analysis process that analyzes the arrangement pattern of items I in the image P. The object processing unit 44b calculates a degree of approximation as to whether or not the items I are similar to an arrangement pattern in which the items I are arranged locally in a part of the image P. The median filtering processing unit 44c calculates a degree of approximation as to whether or not the items I are similar to an arrangement pattern in which the items I are arranged over the entire image P.

[0037] The object processing unit 44b and the median filtering processing unit 44c may be configured to perform processing using the CNN model described above. The CNN model is machine-learned in advance using multiple training data sets with different arrangement patterns, thereby enabling it to calculate the degree of similarity between the arrangement patterns. The arrangement pattern identification unit 44 identifies one or more items I whose arrangement patterns are determined to be similar to each other as a group of objects B based on the degree of similarity between the arrangement patterns calculated by the object processing unit 44b and the median filtering processing unit 44c. In other words, the arrangement pattern processing unit identifies one or more items I whose arrangement patterns are similar from the text layer Lt and the graphic layer Ls as objects B.

[0038] 1, the color identification unit 43 and the layout pattern identification unit 44 calculate the similarity of the color and layout pattern of each graphic item Is in the graphic layer Ls. As a result, a first graphic object Bs1 and a second graphic object Bs2 are identified as a set of one or more items I that have similar colors and layout patterns.

[0039] [About the extraction process of object B] Next, the process of extracting object B in image reading device 1 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the process of extracting object B.

[0040] 4, first, the reading unit 2 reads an image P from a sheet S (step S11). Then, a user selects a range of the read image P that requires processing via the user interface of the input / output unit 5 and crops it (step S12). Steps S13, S14, S16, and S17 are performed on the cropped image P, and a set of one or more items I that are determined to be similar to each other in the image P is identified as a group of objects B. Specifically, in step S13, the layer identification unit 41 of the identification unit 4 identifies a layer L. In step S14, the text identification unit 42 identifies text. In step S16, the color identification unit 43 identifies colors. In step S17, the arrangement pattern identification unit 44 identifies an arrangement pattern. Steps S13, S14, S16, and S17 may be performed in parallel. As a process preceding the color identification (step S16), a correction is performed to correct the color of the entire image P (step S15).

[0041] Thereafter, one or more items I identified as object B are grouped by the grouping unit 31 as items I included in the same object B (step S18). The items I included in the grouped object B are again separated by the separating unit 32 as individual items I within the group so that each item I can be edited later (step S19). Then, identification information is assigned to object B by the identification information assigning unit 33 (step S20). The object B to which the identification information has been assigned is stored in the storage unit 34 together with the identification information (step S21).

[0042] Therefore, the image reading device 1 extracts one or more items I in the image P that are determined to be similar to one another as objects B. Objects B are assigned identification information and stored in an identifiable state in the storage unit 34. Therefore, the image reading device 1 can read object B, which has been stored in an identified state, from the storage unit 34 in accordance with a user's operation and utilize it as an information asset. As a result, the image reading device 1 can effectively utilize the information in the image P.

[0043] The image reading device 1 identifies whether the form of each item I in the image P is text or not, and further identifies one or more items I that have different colors and similar arrangement patterns as objects B and stores them in the storage unit 34.

[0044] Furthermore, by configuring the identification unit 4 of the image reading device 1 as described above, items I that are similar in terms of the overlapping of layers L, text shape and composition, color, and placement pattern can be identified as objects B with high accuracy and stored in the storage unit 34.

[0045] Therefore, the user can select an appropriate object B depending on the purpose of use, since the object B is classified and saved according to the form of the item I contained in the object B. As a result, the image reading device 1 can effectively utilize the information in the image P.

[0046] The image reading device 1 may be configured to extract object B every time the reading unit 2 reads the image P. Alternatively, the image reading device 1 may be configured to extract object B only when a user issues an instruction to extract object B via the user interface of the input / output unit 5.

[0047] [Regarding processing of object B] Next, processing of object B in image reading device 1 will be described with reference to Fig. 2, Fig. 5, and Fig. 6. Fig. 5 is a flowchart of processing of object B. Fig. 6 is a diagram showing an example of processed object B.

[0048] As shown in Fig. 2, the image reading device 1 further includes an object processing unit 6. The object processing unit 6 is, for example, a computer program stored in a storage device, and processes the object B extracted by the object extraction unit 3. In the object processing unit 6, the object B stored in the storage unit 34 is selected for each item I, and processed for each item I. The storage unit 34 stores the object B together with the identification information of the object B and the item I after processing.

[0049] The processing of processing object B will be described with reference to FIG. 5. First, object extraction unit 3 described above extracts and stores object B (step S31). Then, image reading device 1 accepts a user's operation to select object B to be subjected to output processing such as printing or transmission from among the objects B stored in storage unit 34 (step S32). Next, image reading device 1 accepts a user's selection of whether or not to perform processing such as correction or modification on object B to be subjected to output processing (step S33). If the user selects to process object B (Yes in step S33), image reading device 1 processes object B (step S34). Then, image reading device 1 extracts the processed object B (step S35). Furthermore, image reading device 1 performs output processing on the extracted object B (step S36). If the user selects not to process object B in step S33 (No in step S33), the image reading device 1 proceeds to step S36, and performs output processing on object B selected in step S32 (step S36). After the output processing on object B is completed, the image reading device 1 accepts the user's selection as to whether or not to end the output processing on object B (step S37). If the user selects to end the output processing on object B (Yes in step S37), the processing ends (END). If the user selects not to end the output processing on object B (No in step S37), the image reading device 1 accepts the user's operation to select a new object B to be output processed (step S32).

[0050] By the above-described processing, the object B stored in the storage unit 34 of the image reading device 1 can be processed later and stored again. For example, as shown in Fig. 6, in the second graphics object Bs2 extracted from the image P, the missing portion M that overlaps with the second text object Bt2 is corrected (filled in) to generate a corrected object B. The corrected object B is stored in the storage unit 34 as a third graphics object Bs3.

[0051] [About the joining process of object B] Next, the process of combining objects B in the image reading device 1 will be described with reference to FIGS. 2, 7, and 8. FIG. 7 is a flowchart of the process of combining objects B. FIG. 8 is a diagram showing an example of a combined image P1 to which objects B have been combined. As shown in FIG. 2, the image reading device 1 further includes an object combining unit 7. The object combining unit 7 is, for example, a computer program stored in a storage device, and combines objects B extracted by the object extraction unit 3 to form a new combined image P1.

[0052] The combining process for combining objects B will be described with reference to FIG. 7. First, the image reading device 1 accepts a user operation to select a new sheet S1 on which the combined image P1 obtained by combining the objects B is to be formed (step S41). The new sheet S1 may be a physical sheet of paper or an electronic file (document data). The image reading device 1 accepts an operation to select objects B to be included in the combined image P1 (step S42). The selected objects B are read from the storage unit 34. The combined image P1 is formed by combining all the selected objects B (step S43). Thereafter, output processing, such as printing and transmission, is performed on the new sheet S1 on which the combined image P1 has been formed (step S44). After the output processing for the new sheet S1 is completed, the image reading device 1 accepts a selection as to whether to complete the output processing (step S45). If the user selects to complete the processing (Yes in step S45), the combining processing ends (END). If the user selects not to complete the output process (No in step S45), the image reading device 1 returns to step S42 and accepts a user operation to select a new object B to be combined.

[0053] Through the above-described combining process, the image reading device 1 later reads out the object B stored in the storage unit 34 and combines it with other objects B to form a new combined image P1. For example, as shown in FIG. 8, a first graphic object Bs1, a first text object Bt1, a fourth graphic object Bs4, and a fifth graphic object Bs5 are combined to form the new combined image P1. Of the objects B included in the combined image P1, the first graphic object Bs1 and the first text object Bt1 are objects B extracted from the image P. The fourth graphic object Bs4 is an object B generated by rotating the first graphic object Bs1. The fifth graphic object Bs5 is an object B extracted from an image other than the image P. After the combined image P1 is formed, the user selects any process (printing, sending, etc.) for the new sheet S1 on which the combined image P1 is formed.

[0054] As described above, when using the stored object B in response to a user's operation, the image reading device 1 can process the object B appropriately and combine it with other objects B according to the purpose of use. As a result, the image reading device 1 can effectively utilize the information in the image P.

[0055] [Image forming apparatus 100] 2, image reading device 1 may be configured to be included in image forming device 100 having image forming unit 20. Image forming unit 20 forms image P on a recording medium such as paper. Image forming unit 20 forms combined image P1 formed by image reading device 1 on the recording medium.

[0056] An example of the image forming apparatus 100 is a multifunction peripheral such as an MFP (Multi-Function Peripheral). When the image reading apparatus 1 is included in the multifunction peripheral that is the image forming apparatus 100, the image reading apparatus 1 can print the formed combined image P1 on paper in response to a user operation, thereby enabling general use. As a result, the image reading apparatus 1 can effectively utilize the image P information.

[0057] The embodiments of the present invention have been described above with reference to the drawings. However, the present invention is not limited to the above embodiments and can be embodied in various forms without departing from the spirit and scope of the present invention. The drawings mainly show each component in a schematic manner for ease of understanding, and the thickness, length, number, spacing, etc. of each component shown in the drawings may differ from the actual ones due to the convenience of creating the drawings. Furthermore, the materials, shapes, dimensions, etc. of each component shown in the above embodiments are merely examples and are not particularly limited, and various modifications are possible within a scope that does not substantially deviate from the configuration of the present invention. [Industrial Applicability]

[0058] The present invention is useful in the fields of, for example, image reading devices, image reading methods, and image forming devices, and has industrial applicability. [Explanation of symbols]

[0059] S seat P Image B Object Bt Text Object Bs Shape Object I Item It text item Is Shape Item L Layer Lt Text Layer Ls Shape Layer 1. Image reader 2 Reading unit 3. Object Extraction 31 Grouping section 32 Separation section 33 Identification information assignment unit 34 Preservation Department 4 Identification unit 41 Layer Identification Unit 42 Text Identification Unit 43 Color Identification Unit 44 Placement pattern identification unit 5 Input / output section 6. Object Processing Department 7 Object Joint

Claims

1. a reading unit that reads an input image from a sheet on which an image including one or more items is formed; an object extraction unit that extracts an object from the input image; Equipped with The object extraction unit an identification unit that identifies the items from the input image and identifies, as the object, one or more of the items that are determined to be similar to each other based on the degree of similarity regarding the shapes calculated based on information regarding the shapes of the items; an identification information assigning unit that assigns identification information to the object identified by the identifying unit; a storage unit for storing the identification information and the object; An image reading device comprising:

2. The identification unit a layer identification unit that identifies, from the input image, a text layer including the items whose form is text and a graphics layer including the items whose form is other than text; a text identifying unit that identifies one or more of the items from the text layer that have similar shapes as the object; a color identification unit that identifies one or more items from the text layer and the graphics layer that have similar colors as the object; an arrangement pattern identification unit that identifies, from the text layer and the graphics layer, one or more items having similar arrangement patterns as the object; The image reading device according to claim 1 , further comprising:

3. The layer identification unit distinguishing between the text layer and the graphic layer using a neural network model obtained in advance through machine learning; The image reading device according to claim 2 , wherein the neural network model performs a depth detection process that detects how the items are stacked as depth information using the information about the shapes of the items.

4. The text identification unit 3. The image reading device according to claim 2, wherein the object is identified using a typographic analysis process that analyzes elements including the shape and size of the text.

5. The image reading device according to claim 2 , wherein the color identification unit identifies the object using a color clustering process that classifies the items into a plurality of colors.

6. The arrangement pattern identification unit The image reading device according to claim 2 , wherein the object is identified using a layout pattern analysis process that analyzes a layout pattern of the item in the input image using the information about the shape of the item.

7. further comprising an object processing unit that processes the object extracted by the object extraction unit, the object processing unit processes the object stored in the storage unit, The image reading device according to claim 1 , wherein the storage unit stores the object together with the identification information of the object.

8. 3. The image reading device according to claim 1, further comprising an object combining unit that combines the objects extracted by the object extracting unit to form a new combined image.

9. The image reading device according to claim 8; an image forming unit that forms an image on a recording medium; and The image forming unit forms the combined image on the recording medium.

10. An input image is read from a sheet having an image formed thereon that includes one or more items; the item is identified from the input image; and One or more of the items that are determined to be similar to each other based on the similarity in shape calculated based on information about the shapes of the items are identified as objects; The image reading method further comprises the steps of: providing the identified object with identification information; and storing the identification information and the object.

Images