CN102750514A - Method and device for determining categories of lists in input images - Google Patents
Method and device for determining categories of lists in input images Download PDFInfo
- Publication number
- CN102750514A CN102750514A CN2011101046988A CN201110104698A CN102750514A CN 102750514 A CN102750514 A CN 102750514A CN 2011101046988 A CN2011101046988 A CN 2011101046988A CN 201110104698 A CN201110104698 A CN 201110104698A CN 102750514 A CN102750514 A CN 102750514A
- Authority
- CN
- China
- Prior art keywords
- list
- classification
- input picture
- candidate
- line information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for determining categories of lists in input images. The method includes that candidate category lists are determined according to line information of the lists in the input images; if the candidate category lists are not empty, categories of the lists in the input images are determined further according to preprinting content; and if the candidate category lists are empty, and uses can determine that the lists of the input images are novel categories. The method and the device can automatically determine the categories of the lists in a simple and effective mode and distinguish in the lists with the same form structure.
Description
Technical field
Present invention relates in general to computer realm, specifically, relate to the classification of confirming list in the FormDoc disposal system, more specifically, relate to the method and apparatus of the classification of the list in a kind of definite input picture.
Background technology
The FormDoc disposal system is very general in present commercial application, for example in places such as bank, insurance, government bodies, often needs to handle the list of a large amount of electronic formats.
In the FormDoc disposal system, confirm that the classification of list (normally with the input of the form of input picture, the input picture that for example obtains through scanning) is a critical step, the list classification accomplishes because follow-up identification and analysis all are based on.
In a kind of class method for distinguishing of existing definite list, but adopted preparatory printing particular machines identification code on list, but identified different document classifications based on different identification codes.Thereby, but can confirm the classification of list through the identification code in the recognition image.In this method, but need identification code must be printed on the list in advance, and a system often can only discern preset preparatory printing sign indicating number.
Classify in the representational zone that the class method for distinguishing of definite list that another kind is known is based in the list, there is remarkable difference in these zones to inhomogeneous list.The user can artificially mark these representative areas, perhaps comes study automatically through machine.
Summary of the invention
Provided hereinafter about brief overview of the present invention, so that the basic comprehension about some aspect of the present invention is provided.Should be appreciated that this general introduction is not about exhaustive general introduction of the present invention.It is not that intention is confirmed key of the present invention or pith, neither be intended to limit scope of the present invention.Its purpose only is to provide some notion with the form of simplifying, with this as the preorder in greater detail of argumentation after a while.
The present invention aims to provide the method and apparatus of the classification of the list in a kind of definite input picture.Wherein, But also artificial sign of needs or training draw under the situation of representative area accurately invariably not needing preparatory printer device identification code; Can automatically confirm the classification of the list in the input picture with the advantages of simplicity and high efficiency mode; And scheme according to the present invention has extensive applicability and robustness preferably.In addition, in the method and apparatus of the classification of the list in definite input picture according to the present invention, can distinguish similar list (be that linear is identical, but the different list of content of text) exactly, further improve the accuracy of classification.
To achieve these goals, according to an aspect of the present invention, a kind of method is provided, has comprised: the line information according to the list in the input picture is confirmed candidate's list of categories; If said candidate's list of categories is not empty, then further confirm the classification of the list in the input picture according to preparatory print What; If said candidate's list of categories is empty, confirm that then the list in the said input picture is new classification.
According to another aspect of the present invention, a kind of method is provided, has comprised: line information and other line information of each main classes of the list in the input picture are compared, and wherein, each main classes does not comprise the list of at least one classification; If find main classes other, then confirm the classification of the list in the input picture according to preparatory print What with coupling line information; If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
According to another aspect of the present invention, a kind of device is provided also, has comprised: candidate's list of categories is confirmed portion, is configured to confirm candidate's list of categories according to the line information of the list in the input picture; The list classification is confirmed portion, is configured to: if said candidate's list of categories not for empty, is then further confirmed the classification of the list in the input picture according to preparatory print What; If said candidate's list of categories is empty, confirm that then the list in the said input picture is new classification.
According to another aspect of the present invention; A kind of device also is provided, has comprised: the other search section of main classes is configured to line information and other line information of each main classes of the list in the input picture are compared; Wherein, each main classes does not comprise the list of at least one classification; The list classification is confirmed portion, is configured to: if find the main classes with coupling line information other, then confirm the classification of the list in the input picture according to preparatory print What; If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
According to others of the present invention, corresponding computer programs code, computer-readable recording medium and computer program are provided also.
Through below in conjunction with the detailed description of accompanying drawing to most preferred embodiment of the present invention, these and other advantage of the present invention will be more obvious.
Description of drawings
The present invention can wherein use same or analogous Reference numeral to represent identical or similar parts in institute's drawings attached through with reference to hereinafter combining the given description of accompanying drawing to be better understood.Said accompanying drawing comprises in this manual and forms the part of this instructions together with following detailed description, and is used for further illustrating the preferred embodiments of the present invention and explains principle and advantage of the present invention.In the accompanying drawings:
Fig. 1 is the process flow diagram that the class method for distinguishing of the list of confirming according to an embodiment of the invention in the input picture is shown;
Fig. 2 illustrates the process flow diagram of confirming the processing of candidate's list of categories according to an embodiment of the invention according to the line information of the list in the input picture;
Fig. 3 illustrates according to an embodiment of the invention the process flow diagram of processing that comes further to confirm the classification of the list in the input picture according to print What in advance;
Fig. 4 shows according to an embodiment of the invention the process flow diagram of processing of confirming the classification of list based on similarity;
Fig. 5 shows the process flow diagram of the class method for distinguishing of the list of confirming in accordance with another embodiment of the present invention in the input picture;
Fig. 6 illustrates according to an embodiment of the invention the process flow diagram of processing of confirming the classification of the list in the input picture according to print What in advance;
Fig. 7 illustrates the schematic representation of apparatus of confirming the classification of the list in the input picture according to an embodiment of the invention;
Fig. 8 shows the synoptic diagram of confirming portion according to candidate's list of categories of this embodiment;
Fig. 9 illustrates the synoptic diagram that list classification according to an embodiment of the invention is confirmed portion;
Figure 10 shows the schematic representation of apparatus of confirming the classification of the list in the input picture in accordance with another embodiment of the present invention;
Figure 11 illustrates the synoptic diagram that list classification is according to an embodiment of the invention confirmed portion; And
Figure 12 is the block diagram that wherein can realize according to the exemplary configurations of the general purpose personal computer of the method for the embodiment of the invention and/or device.
Embodiment
To combine accompanying drawing that example embodiment of the present invention is described hereinafter.In order to know and for simplicity, in instructions, not describe all characteristics of actual embodiment.Yet; Should understand; In the process of any this practical embodiments of exploitation, must make a lot of decisions, so that realize developer's objectives, for example specific to embodiment; Meet and system and professional those relevant restrictive conditions, and these restrictive conditions may change along with the difference of embodiment to some extent.In addition, might be very complicated and time-consuming though will also be appreciated that development, concerning the those skilled in the art that have benefited from present disclosure, this development only is customary task.
At this; What also need explain a bit is; For fear of having blured the present invention, only show in the accompanying drawings and closely-related apparatus structure of scheme according to the present invention and/or treatment step, and omitted other details little with relation of the present invention because of unnecessary details.
Fig. 1 is the process flow diagram that the class method for distinguishing of the list of confirming according to an embodiment of the invention in the input picture is shown.
As shown in Figure 1, at step S102 place, can confirm candidate's list classification according to the line information of the list in the input picture.
Wherein, input picture can be the image of locating to import from image acquiring device (for example, scanner, digital camera etc.), also can be the image of locating to import from external memory (for example, storing the storage card, CD, disk etc. of image).
In addition, can adopt various suitable image processing techniquess to come from input picture, to extract the line information of list.For example; The lines method for distilling that can propose through people such as Hiroaki Takebe, Katsuhito Fujimoto is (referring to the U.S. Pat 7 that is entitled as " Ruled line extracting program; ruled line extracting apparatus and ruled line extracting method "; 769,234 B2, its full content is herein incorporated by reference) obtain the line information of the list in the input picture.In a preferred embodiment, the line information of list can comprise the starting point coordinate and the terminal point coordinate of each lines in the list.In a further advantageous embodiment, the line information of list can comprise the length of each lines in the list and the proportionate relationship between the lines etc.
Thereby, at step S102 place, can search list according to the line information of the list in the input picture, and the list classification of the line information with coupling that will find out is as a classification in candidate's list of categories with coupling line information.
Wherein, in this article, the list with line information of coupling can refer to have the list of identical table lattice structure.
Specifically; In a preferred embodiment of the invention; When the starting point coordinate of all lines of two lists and terminal point coordinate is identical or the starting point coordinate of lines and/or the deviation between the terminal point coordinate in the acceptable error range, can think these two line informations that list has coupling.At this moment, if varying in size of two lists that compared at first will be carried out normalization to them, so that two lists that compared have identical size.
In addition; In another preferred embodiment of the present invention; When the ratio between the various lines in the list all with another list in various lines between identical or the deviation between them of ratio in the acceptable scope time, can think these two line informations that list has coupling.
Then, at step S104 place, judge whether candidate's list of categories is empty tabulation.
Specifically, just judge step S102 place whether find have with input picture in the list classification of the line information that is complementary of the line information of list.
If candidate's list of categories for empty (promptly step S102 place found have with input picture in the list classification of the line information that is complementary of the line information of list); Then, further utilize preparatory print What in candidate's list of categories, to confirm the classification of the list in the input picture at step S106 place.
Wherein, in this article, the preparatory print What of list refers to the foreground pixel that exists in the blank list for example, can comprise form line, character, tag mark etc.
On the other hand, if candidate's list of categories for empty (promptly step S102 place do not find have with input picture in the list classification of the line information that is complementary of the line information of list), then at step S108 place, confirm that the list in the input picture is new classification.
Can find out; In the class method for distinguishing of the list in definite input picture shown in Figure 1; But can do not need preparatory printer device identification code also invariably artificial sign of needs or training draw under the situation of representative area accurately, automatically confirm the classification of the list in the input picture.
In the class method for distinguishing of the list in above-mentioned definite input picture, confirm that according to the line information of the list in the input picture processing of candidate's list of categories can realize with various suitable manner.
In one embodiment of the invention, can confirm candidate's list of categories according to line information.Specifically, can utilize the line information of the list in the input picture to come search list individual character allusion quotation, and one or more list classifications of the line information of the line information coupling of the list in having of will searching out and the input picture constitute candidate's list of categories.
In this article, the list dictionary can refer to that the wherein said information relevant with the list classification can comprise the line information of list classification, the preparatory type information of list etc. at least according to the parts of each list classification storage information relevant with said list classification.
The above direct search list dictionary that passes through confirms that the processing of candidate's list of categories is merely example, the invention is not restricted to this.In an alternative embodiment of the invention, can be according to line information, confirm candidate's list of categories based on list dictionary and analog information.Wherein, in this article, analog information is to be used for showing that the list of which classification in the list dictionary has the information of identical tableau format (that is, having identical line information).
Fig. 2 illustrates to confirm the process flow diagram of the processing of candidate's list of categories according to this embodiment based on the line information of the list in the input picture.
As shown in Figure 2, search list individual character allusion quotation is to obtain the list classification of line information coupling at step S202 place.
Specifically, according to the line information of the list in the input picture in the list dictionary, search for have with input picture in the list classification of line information of line information coupling of list.
Then, at step S204 place, obtain analog information to the list classification that searches out at step S202 place.
As stated, analog information is to show that the list of which classification in the list dictionary has the information of identical tableau format.Analog information can be stored in the list dictionary, also can be stored in the outside separate, stored parts.
Thereby, when searching out the list classification of a line information with coupling at step S202 place, can from list dictionary or external storage component, obtain the analog information of the list classification that searches out corresponding to this.That is to say, from list dictionary or external storage component, obtain analog information, with the line information of knowing that which list classification in the list dictionary and the list classification that searches out have coupling.
Although it is pointed out that above to obtain analog information with the list classification that has the line information of coupling to of searching out be that example describes, above explanation is merely example, the invention is not restricted to this.In fact, also can in the list dictionary, search out (but needn't search complete list dictionary) after two or more list classifications, obtain analog information to said two or more list classifications that search out with coupling line information.Through such mode, can reduce the accuracy that error further improves candidate's list of categories of generation, and then improve the accuracy of classification.
Then, at step S206 place, generate candidate's list of categories based on the analog information that obtains.
Specifically, find list classification, and these list classifications with line information of coupling are constituted said candidate's list of categories with the line information that is complementary based on analog information.
Like this, through utilizing line information and analog information to generate candidate's list of categories.Owing to utilized analog information, can reduce the searching times in the list dictionary, can reduce operand thus, improve treatment effeciency.
In addition; In the class method for distinguishing of the list in above-mentioned definite input picture, can realize confirming the processing of the classification of the list in the input picture based on similarity between the preparatory print What of the list of the preparatory print What of the list of input picture and candidate's classification according to print What in advance.
Fig. 3 is the process flow diagram that illustrates according to the processing of the classification of the list in further definite input picture based on preparatory print What of the present invention.
As shown in Figure 3, at step S302 place, obtain the preparatory print What of candidate's classification.
In a preferred exemplary, can from the list dictionary, obtain the preparatory print What of the list of each the candidate's classification in candidate's list of categories.
Then, at step S304 place, utilize preparatory print What to calculate similarity.
Specifically, can utilize preparatory print What and the preparatory print What of the list in the input picture of the list of each candidate's classification to calculate similarity.
Wherein, similarity can be the parameter of degree of registration of preparatory print What that is used for characterizing preparatory print What and the list in the input picture of each candidate's classification.
Pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of candidate's classification that in one embodiment of the invention, can be foreground pixel according to the preparatory print What of the preparatory print What of the list of candidate's classification and the list in the input picture in the corresponding position is calculated similarity.
If the ratio that calculates is big more, show that then the degree of registration of preparatory print What of preparatory print What and the list in the input picture of list of candidate's classification is high more, thereby similarity is also high more.
Then, at step S306 place, confirm the classification of list based on similarity.
Specifically, can confirm the classification of the list in the input picture in the candidate's classification in candidate's list of categories according to the similarity between the preparatory print What of the preparatory print What of the list that calculates each candidate's classification and the list in the input picture.
In method shown in Figure 3, owing to utilized the preparatory print What of list to come in candidate's classification, to confirm further the classification of the list in the input picture, thereby can confirm the classification of list with higher precision.
In said method, confirm that based on similarity the processing of the classification of list can adopt various suitable manner to realize.In one embodiment of the invention, can adopt the classification of utilizing maximum comparability in candidate's classification, to confirm list.
Fig. 4 shows and confirms the process flow diagram of processing of the classification of list according to this embodiment based on similarity.
As shown in Figure 4, at step S402 place, judge earlier whether the maximum comparability in the similarity that calculates surpasses predetermined threshold.
Obviously, the candidate classification corresponding with maximum comparability be in candidate's list of categories with input picture in the most similar classification of list, promptly corresponding with maximum comparability candidate's classification most possibly is the classification of the list in the input picture.
In addition, if the list in the input picture belongs to certain candidate's classification, then the preparatory print What of the two is also should complete matching consistent, and promptly similarity degree should be 100%.Even consider to have some errors in scanning or the Flame Image Process, the similarity degree of the two also should be greater than predetermined threshold.
Preferably, said predetermined threshold for example can be 99%, 98%, 97%, 96%, 95% etc.
Thereby, if the maximum comparability in the similarity of confirming to calculate surpasses predetermined threshold,, can the candidate classification corresponding with maximum comparability be confirmed as the classification of the list in the input picture then at step S404 place.
On the other hand, if maximum comparability surpasses predetermined threshold, then at step S406 place, the classification that can confirm the list in the input picture and is confirmed as new classification with the classification of the list in the input picture not in candidate's list of categories.
Confirm the processing of the classification of list through this utilization based on the similarity of preparatory print What, can further improve the accuracy for processing of the classification of confirming list.For example, when similar list (promptly have identical tableau format but there is different lists in other part) situation occurring, can realize distinguishing accurately, realize the classification of list classification more accurately thus.
In addition, be merely example, the invention is not restricted to this, but can also retrofit or revise with other suitable manner according to the class method for distinguishing of the list in definite input picture of any the foregoing description.
In another embodiment of the present invention, the class method for distinguishing of confirming the list in the input picture can also be included in the update processing of carrying out when the classification of the list in the input picture confirmed as new classification.
For example, when in the list dictionary, do not find have with input picture in the list classification of the line information that is complementary of the line information of list the time, can the list in the input picture be confirmed as new classification (for example, referring to Fig. 1 step S108).
In this case, above-mentioned update processing can comprise said new classification is increased in the list dictionary.
Specifically, can with the line information of the list in the input picture and print What in advance as the information stores corresponding with said new classification in the list dictionary.
As another example, when the maximum comparability of candidate's classification in candidate's list of categories and the list in the input picture does not surpass predetermined threshold, also can the list in the input picture be confirmed as new classification.
In this case, update processing can comprise the processing that said new classification is increased to the list dictionary and upgrades analog information.
Specifically, the processing that said new classification is increased to the list dictionary can comprise with the line information of the list in the input picture and print What in advance as the information stores corresponding with said new classification in the list dictionary.The processing of upgrading analog information can comprise the analog information in updating form individual character allusion quotation or the external storage component, has identical line information to show said new classification with each candidate's classification.
Through such update processing, can discern the new list classification that did not occur before automatically according to the class method for distinguishing of the list in definite input picture of the embodiment of the invention, improved the popularity of using thus.
In method according to the above embodiment of the present invention, the line information of the list in the input picture and the classification that preparatory print What is confirmed list have been utilized.The foregoing description is merely example, the invention is not restricted to this, but can also otherwise utilize the line information of the list in the input picture and the classification that preparatory print What is confirmed list.
Fig. 5 shows the process flow diagram of the class method for distinguishing of the list of confirming in accordance with another embodiment of the present invention in the input picture.
As shown in Figure 5, at step S502 place, compare based on line information.
Specifically, can line information and other line information of each main classes of the list in the input picture be compared.
Wherein, main classes can not be based on the classification of the line information realization of list.Each main classes can not comprise that at least one has the list of coupling line information.Different main classes can not have different line informations and list with identical line information is ranged same main classes Xia not.
Then, at step S504 place, judge whether to find main classes other.
If find main classes other,, can further confirm the classification of the list in the input picture according to preparatory print What then at step S506 place with coupling line information.
If do not find main classes (for example, not exist the main classes that matees line information not or still not exist the main classes other),, the classification of the list in the input picture confirmed as new classification then at step S508 place with coupling line information.
Can find out; In the class method for distinguishing of the list in definite input picture shown in Figure 5; But can do not need preparatory printer device identification code also invariably artificial sign of needs or training draw under the situation of representative area accurately, automatically realize the identification of the list classification in the input picture.
In the class method for distinguishing of the list in above-mentioned definite input picture, can adopt various suitable manner to realize confirming the processing of the classification of the list in the input picture according to preparatory print What.
Fig. 6 illustrates according to an embodiment of the invention the process flow diagram of processing of confirming the classification of the list in the input picture according to print What in advance.
As shown in Figure 6, at step S602 place, calculate similarity based on preparatory print What.
Specifically, can based on main classes not in preparatory print What and the preparatory print What of the list in the input picture of list of each classification calculate the similarity between the two.
Pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of said each classification that wherein, can be foreground pixel according to the preparatory print What of the preparatory print What of the list of each classification of main classes in not and the list in the input picture in the corresponding position is calculated similarity.
About the detailed calculated of similarity, can repeat no more so that instructions keeps succinct at this referring to the detailed description among the embodiment that mentions hereinbefore.
Then, at step S604 place, can confirm the list classification based on similarity.
Specifically; To main classes not in each classification list preparatory print What and the list in the input picture preparatory print What and in the similarity that calculates; If the maximum comparability that calculates then can be with the classification of the classification with maximum comparability as the list in the input picture more than predetermined threshold; If the maximum comparability that calculates does not surpass predetermined threshold, then can the list in the input picture be confirmed as new classification.
About confirm the detailed process of list classification based on similarity, can repeat no more so that instructions keeps succinct at this referring to the detailed description among the embodiment that mentions hereinbefore.
Confirm the processing of the classification of list through this utilization based on the similarity between the preparatory print What, can further improve the accuracy for processing of the classification of confirming list.For example, when similar list (promptly have identical tableau format but there is different lists in other part) situation occurring, can realize distinguishing accurately, realize the classification of list classification more accurately thus.
The line information that utilizes the list in the input picture that more than combines Fig. 5 and Fig. 6 to describe confirms that with preparatory print What the embodiment of the classification of list is merely example, the invention is not restricted to this, but can also otherwise retrofit or revise.
In another embodiment of the present invention, the class method for distinguishing of Fig. 5 or definite list shown in Figure 6 can further include the update processing of when the classification of the list in the input picture is confirmed as new classification, carrying out.
As stated, when not finding main classes other, can the list in the input picture be confirmed as new classification (for example, referring to Fig. 5 step S508).
In this case; Above-mentioned update processing can comprise said new classification other as a new main classes; Said new main classes comprises the list in the input picture in not, and with the line information of the list in the input picture as said other line information of new main classes.
In addition, as stated, when the maximum comparability of list and the list in input picture of the main classes that finds in not surpasses predetermined threshold, also can the list in the input picture be confirmed as new classification.
In this case, above-mentioned update processing can comprise with said new classification add to the main classes that finds not in, realized thus other renewal of main classes.
Through such update processing, can not automatically perform under the manual intervention ground situation having according to the class method for distinguishing of the list in definite input picture of the embodiment of the invention, improved the popularity of using thus.
Corresponding with the class method for distinguishing according to the list in definite input picture of the foregoing description, embodiments of the invention also provide the corresponding device of confirming the classification of the list in the input picture.
Fig. 7 illustrates the schematic representation of apparatus of confirming the classification of the list in the input picture according to an embodiment of the invention.
As shown in Figure 7, comprise that according to the device of the classification of the list in definite input picture of the embodiment of the invention candidate's list of categories confirms that portion 702 and list classification confirm portion 704.
Wherein, candidate's list of categories confirms that portion 702 can confirm candidate's list of categories according to the line information of the list in the input picture.
Specifically; Candidate's list of categories confirms that portion 702 can search the list classification with coupling line information according to the line information of the list in the input picture, and the list classification of the line information with coupling that will find out is as a classification in candidate's list of categories.
The list classification confirms that portion 704 can carry out following processing: if candidate's list of categories not for empty, is then further confirmed the classification of the list in the input picture according to preparatory print What; If candidate's list of categories is empty, confirm that then the list in the input picture is new classification.
Specifically, the list classification confirm portion 704 can judge candidate's list of categories confirm portion 702 whether find have with input picture in the list classification of the line information that is complementary of the line information of list.
If candidate's list of categories for empty (be candidate's list of categories confirm portion 702 found have with input picture in the list classification of the line information that is complementary of the line information of list), then the list classification confirms that portion 704 can further utilize preparatory print What in candidate's list of categories, to confirm the classification of the list in the input picture.
On the other hand; If candidate's list of categories for empty (be candidate's list of categories confirm portion 702 do not find have with input picture in the list classification of the line information that is complementary of the line information of list), then the list classification confirms that portion 704 can confirm that the list in the input picture is new classification.
Can find out; But the device of the classification of the list in definite input picture shown in Figure 7 can do not need preparatory printer device identification code also invariably artificial sign of needs or training draw under the situation of representative area accurately, automatically confirm the classification of the list in the input picture.
In the device of the classification of the list in definite input picture shown in Figure 7, candidate's list of categories confirms that portion can realize with various suitable manner.
In one embodiment of the invention; Candidate's list of categories confirm portion can according to line information from the list dictionary, search for have with input picture at least one list classification of the line information that is complementary of the line information of list, constitute said candidate's list of categories.
In another embodiment of the present invention, candidate's list of categories confirm portion can be according to line information, confirm candidate's classification list based on list dictionary and analog information.。
Fig. 8 shows the synoptic diagram of confirming portion according to candidate's list of categories of this embodiment.
As shown in Figure 8, candidate's list of categories confirms that portion can comprise list dictionary search section 802, analog information acquisition portion 804, tabulation generation portion 806.
List dictionary search section 802 can from the list dictionary, search for have with input picture at least one list classification of the line information that is complementary of the line information of list.
Specifically, list dictionary search section 802 can according to the line information of the list in the input picture in the list dictionary, search for have with input picture in the list classification of line information of line information coupling of list.
Analog information acquisition portion 804 can search have with input picture at least one list classification of the line information that is complementary of the line information of list the time, obtain the analog information of said at least one list classification.
Specifically, analog information acquisition portion 804 can obtain the analog information of the list classification that searches out corresponding to this from list dictionary or external storage component.That is to say, from list dictionary or external storage component, obtain analog information, with the line information of knowing that which list classification in the list dictionary and the list classification that searches out have coupling
Tabulation generation portion 806 can obtain similar list classification based on said analog information, and said at least one list classification is constituted said candidate's list of categories with similar list classification.
Specifically, find list classification, and these list classifications with line information of coupling are constituted said candidate's list of categories with the line information that is complementary based on analog information.
Like this, through utilizing line information and analog information to generate candidate's list of categories.Owing to utilized analog information, can reduce the searching times in the list dictionary, can reduce operand thus, improve treatment effeciency.
In addition; In the device of the classification of the list in above-mentioned definite input picture, the list classification confirms that portion can come further to confirm according to print What in advance the classification of the list in the input picture based on similarity between the preparatory print What of the list of the preparatory print What of the list of input picture and candidate's classification.
Fig. 9 illustrates the synoptic diagram that list classification according to an embodiment of the invention is confirmed portion.
As shown in Figure 9, the list classification confirms that portion can comprise: print What acquisition portion 902, similarity calculating part 904, classification are confirmed portion 906 in advance.
Print What acquisition portion 902 can obtain the preparatory print What of each the candidate's classification candidate's list of categories from the list dictionary in advance.
Specifically, similarity calculating part 904 pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of candidate's classification that can be foreground pixel according to the preparatory print What of the preparatory print What of the list of candidate's classification and the list in the input picture in the corresponding position is calculated similarity.
Classification confirms that portion 906 can confirm the classification of the list in the input picture according to similarity.
Specifically, can confirm the classification of the list in the input picture in the candidate's classification in candidate's list of categories according to the similarity between the preparatory print What of the preparatory print What of the list that calculates each candidate's classification and the list in the input picture.
More particularly, if the maximum comparability that calculates more than predetermined threshold, then classification confirms that portion 906 can be with the classification of the candidate's classification with maximum comparability as the list in the input picture; If the maximum comparability that calculates does not surpass predetermined threshold, then classification confirms that portion 906 confirms as new classification with the list in the input picture.
Confirm the processing of the classification of list through this utilization based on the similarity of preparatory print What, can further improve the accuracy for processing of the classification of confirming list.For example, when similar list (promptly have identical tableau format but there is different lists in other part) situation occurring, can realize distinguishing accurately, realize the classification of list classification more accurately thus.
In addition, because the classification of having utilized the preparatory print What of list to come in candidate's classification, to confirm further the list in the input picture, thereby can be with the identification of higher precision realization list classification.
Device according to the classification of the list in definite input picture of any the foregoing description is merely example, the invention is not restricted to this, but can also retrofit or revise with other suitable manner.
In another embodiment of the present invention, the device of confirming the classification of the list in the input picture can also comprise the updating component (not shown).
For example, when in the list dictionary, do not find have with input picture in the list classification of the line information that is complementary of the line information of list the time, the list in the input picture is confirmed as new classification.In this case, said update processing can be increased to said new classification in the list dictionary.Specifically, can with the line information of the list in the input picture and print What in advance as the information stores corresponding with said new classification in the list dictionary.
As another example, when the maximum comparability of candidate's classification in candidate's list of categories and the list in the input picture did not surpass predetermined threshold, the list in the input picture also can be confirmed as new classification.In this case, said updating component can be increased to said new classification the list dictionary and upgrade analog information.Specifically; Said updating component can with the line information of the list in the input picture and print What in advance as the information stores corresponding with said new classification in the list dictionary; And the analog information in updating form individual character allusion quotation or the external storage component, have identical line information to show said new classification with each candidate's classification.
Through such updating component, the new list classification that did not occur before can discerning automatically according to the device of the classification of the list in definite input picture of the embodiment of the invention has improved the popularity of using thus.
In device according to the above embodiment of the present invention, the line information of the list in the input picture and the classification that preparatory print What is confirmed list have been utilized.The foregoing description is merely example, the invention is not restricted to this, but can also otherwise utilize the line information of the list in the input picture and the classification that preparatory print What is confirmed list.
Figure 10 shows the schematic representation of apparatus of confirming the classification of the list in the input picture in accordance with another embodiment of the present invention.
Shown in figure 10, the device 1000 of confirming the classification of the list in the input picture can comprise that the other search section 1002 of main classes confirms portion 1004 with the list classification.
The other search section 1002 of main classes can compare line information and other line information of each main classes of the list in the input picture.
Wherein, main classes can not be based on the classification of the line information realization of list.Each main classes can not comprise that at least one has the list of coupling line information.Different main classes can not have different line informations and list with identical line information is ranged same main classes Xia not.
The list classification confirms that portion 1004 can carry out following processing: if find the main classes with coupling line information other, then confirm the classification of the list in the input picture according to preparatory print What; If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
Can find out; But the classification device of the list in definite input picture shown in Figure 10 can do not need preparatory printer device identification code also invariably artificial sign of needs or training draw under the situation of representative area accurately, automatically realize the identification of the list classification in the input picture.
In above-mentioned device, the list classification confirms that portion can confirm with various suitable manner.
Figure 11 illustrates the synoptic diagram that list classification is according to an embodiment of the invention confirmed portion.
Shown in figure 11, the list classification confirms that portion can comprise that similarity calculating part 1104 and classification confirm portion 1106.
Pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of said each classification that specifically, can be foreground pixel according to the preparatory print What of the preparatory print What of the list of each classification of main classes in not and the list in the input picture in the corresponding position is calculated similarity.
Classification confirms that portion 1106 can confirm the classification under the list in the input picture according to similarity.
Specifically; To main classes not in each classification list preparatory print What and the list in the input picture preparatory print What and in the similarity that calculates; If the maximum comparability that calculates then can be with the classification of the classification with maximum comparability as the list in the input picture more than predetermined threshold; If the maximum comparability that calculates does not surpass predetermined threshold, then can the list in the input picture be confirmed as new classification.
Confirm the processing of the classification of list through this utilization based on the similarity between the preparatory print What, can further improve the accuracy for processing of the classification of confirming list.For example, when similar list (promptly have identical tableau format but there is different lists in other part) situation occurring, can realize distinguishing accurately, realize the classification of list classification more accurately thus.
The line information that utilizes the list in the input picture that more than combines Figure 10 and Figure 11 to describe confirms that with preparatory print What the embodiment of the classification of list is merely example, the invention is not restricted to this, but can also otherwise retrofit or revise.
In another embodiment of the present invention, the device of the classification of Figure 10 or definite list shown in Figure 11 can further include the updating component (not shown).
For example, when in the list dictionary, do not find have with input picture in the list classification of the line information that is complementary of the line information of list the time, the list in the input picture is confirmed as new classification.In this case, said update processing can be increased to said new classification in the list dictionary.Specifically, can with the line information of the list in the input picture and print What in advance as the information stores corresponding with said new classification in the list dictionary.
As another example, when the maximum comparability of candidate's classification in candidate's list of categories and the list in the input picture did not surpass predetermined threshold, the list in the input picture also can be confirmed as new classification.In this case, said updating component can be increased to said new classification the list dictionary and upgrade analog information.Specifically; Said updating component can with the line information of the list in the input picture and print What in advance as the information stores corresponding with said new classification in the list dictionary; And the analog information in updating form individual character allusion quotation or the external storage component, have identical line information to show said new classification with each candidate's classification.
Through such updating component, the new list classification that did not occur before can discerning automatically according to the device of the classification of the list in definite input picture of the embodiment of the invention has improved the popularity of using thus.
About the corresponding description that can carry out referring to the preceding text associated methods according to the further details of the device of the classification of definite list of above-mentioned any embodiment and parts thereof, repeat no more so that instructions keeps succinct at this.
In addition, it will be appreciated that various examples as herein described and embodiment all are exemplary, the invention is not restricted to this.In this manual, statements such as " first ", " second " only are for described characteristic is distinguished on literal, clearly to describe the present invention.Therefore, should it be regarded as having any determinate implication.
Each forms module in the said apparatus, the unit can be configured through the mode of software, firmware, hardware or its combination.Dispose spendable concrete means or mode and be well known to those skilled in the art, repeat no more at this.Under situation about realizing through software or firmware; From storage medium or network the program that constitutes this software is installed to the computing machine with specialized hardware structure (multi-purpose computer 1200 for example shown in Figure 12); This computing machine can be carried out various functions etc. when various program is installed.
In Figure 12, CPU (CPU) 1201 carries out various processing according to program stored among ROM (read-only memory) (ROM) 1202 or from the program that storage area 1208 is loaded into random-access memory (ram) 1203.In RAM 1203, also store data required when CPU 1201 carries out various processing or the like as required.CPU 1201, ROM 1202 and RAM 1203 are connected to each other via bus 1204.Input/output interface 1205 also is connected to bus 1204.
Following parts are connected to input/output interface 1205: importation 1206 (comprising keyboard, mouse or the like), output 1207 (comprise display; Such as cathode ray tube (CRT), LCD (LCD) etc. and loudspeaker etc.), storage area 1208 (comprising hard disk etc.), communications portion 1209 (comprising that NIC is such as LAN card, modulator-demodular unit etc.).Communications portion 1209 is handled such as the Internet executive communication via network.As required, driver 1210 also can be connected to input/output interface 1205.Detachable media 1211 is installed on the driver 1210 such as disk, CD, magneto-optic disk, semiconductor memory or the like as required, makes the computer program of therefrom reading be installed to as required in the storage area 1208.
Realizing through software under the situation of above-mentioned series of processes, such as detachable media 1211 program that constitutes software is being installed such as the Internet or storage medium from network.
It will be understood by those of skill in the art that this storage medium is not limited to shown in Figure 12 wherein having program stored therein, distribute so that the detachable media 1211 of program to be provided to the user with equipment with being separated.The example of detachable media 1211 comprises disk (comprising floppy disk (registered trademark)), CD (comprising compact disc read-only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk (comprising mini-disk (MD) (registered trademark)) and semiconductor memory.Perhaps, storage medium can be hard disk that comprises in ROM 1202, the storage area 1208 or the like, computer program stored wherein, and be distributed to the user with the equipment that comprises them.
The present invention also proposes a kind of program product that stores the instruction code of machine-readable.When said instruction code is read and carried out by machine, can carry out above-mentioned method according to the embodiment of the invention.
Correspondingly, the storage medium that is used for carrying the program product of the above-mentioned instruction code that stores machine-readable is also included within of the present invention open.Said storage medium includes but not limited to floppy disk, CD, magneto-optic disk, storage card, memory stick or the like.
At last; Also need to prove; Term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability; Thereby make to comprise that process, method, article or the equipment of a series of key elements not only comprise those key elements, but also comprise other key elements of clearly not listing, or also be included as this process, method, article or equipment intrinsic key element.In addition, under the situation that do not having much more more restrictions, the key element that limits by statement " comprising ... ", and be not precluded within process, method, article or the equipment that comprises said key element and also have other identical element.
Though more than combine accompanying drawing to describe embodiments of the invention in detail, should be understood that top described embodiment just is used to explain the present invention, and be not construed as limiting the invention.For a person skilled in the art, can make various modifications and change to above-mentioned embodiment and do not deviate from essence of the present invention and scope.Therefore, scope of the present invention is only limited appended claim and equivalents thereof.
According to above description, the application provides technical scheme:
The class method for distinguishing of the list in 1. 1 kinds of definite input pictures of remarks comprises:
Line information according to the list in the input picture is confirmed candidate's list of categories;
If said candidate's list of categories is not empty, then further confirm the classification of the list in the input picture according to preparatory print What;
If said candidate's list of categories is empty, confirm that then the list in the said input picture is new classification.
Remarks 2. wherein, confirms that according to the line information of the list in the input picture processing of candidate's list of categories comprises according to remarks 1 described method:
From the list dictionary search have with input picture at least one list classification of the line information that is complementary of the line information of list, constitute said candidate's list of categories.
Remarks 3. wherein, confirms that according to the line information of the list in the input picture processing of candidate's list of categories also comprises according to remarks 2 described methods:
Search have with input picture at least one list classification of the line information that is complementary of the line information of list the time, obtain the analog information of said at least one list classification;
Obtain similar list classification based on said analog information, and with said at least one list classification with similar list classification, constitute said candidate's list of categories.
Remarks 4. wherein, confirms that according to preparatory print What the processing of the classification of the list in the input picture comprises according to remarks 1 described method:
The preparatory print What of each the candidate's classification from list dictionary acquisition candidate list of categories;
Calculate the similarity between the preparatory print What of preparatory print What and the list in the input picture of each candidate's classification;
Confirm the classification of the list in the input picture according to similarity.
Remarks 5. is according to remarks 4 described methods; Wherein, the pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of candidate's classification that is foreground pixel in the corresponding position according to the preparatory print What of the preparatory print What of the list of candidate's classification and the list in the input picture is calculated similarity.
Remarks 6. wherein, confirms that according to similarity the processing of the classification of the list in the input picture comprises according to remarks 4 described methods:
If the maximum comparability that calculates more than predetermined threshold, then will have the classification of candidate's classification of maximum comparability as the list in the input picture;
If the maximum comparability that calculates does not surpass predetermined threshold, then the list in the input picture is confirmed as new classification.
The class method for distinguishing of the list in 7. 1 kinds of definite input pictures of remarks comprises:
Line information and other line information of each main classes of list in the input picture are compared, and wherein, each main classes does not comprise the list of at least one classification;
If find main classes other, then confirm the classification of the list in the input picture according to preparatory print What with coupling line information;
If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
Remarks 8. wherein, confirms that according to preparatory print What the processing of the classification of the list in the input picture comprises according to remarks 7 described methods:
Calculate main classes not in similarity between the preparatory print What of preparatory print What and the list in the input picture of list of each classification;
Confirm the classification under the list in the input picture according to similarity.
Remarks 9. is according to remarks 8 described methods; Wherein, the pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of said each classification that is foreground pixel in the corresponding position according to the preparatory print What of the preparatory print What of the list of each classification and the list in the input picture is calculated similarity.
Remarks 10. is according to remarks 8 described methods, wherein, confirms that according to similarity the processing of the classification under the list in the input picture comprises:
If the maximum comparability that calculates more than predetermined threshold, then will have the classification of the classification of maximum comparability as the list in the input picture;
If the maximum comparability that calculates does not surpass predetermined threshold, then the list in the input picture is confirmed as new classification.
The device of the classification of the list in 11. 1 kinds of definite input pictures of remarks comprises:
Candidate's list of categories is confirmed portion, is configured to confirm candidate's list of categories according to the line information of the list in the input picture;
The list classification is confirmed portion, is configured to: if said candidate's list of categories not for empty, is then further confirmed the classification of the list in the input picture according to preparatory print What; If said candidate's list of categories is empty, confirm that then the list in the said input picture is new classification.
Remarks 12. is according to remarks 11 described devices, and wherein, said candidate's list of categories confirms that portion comprises:
List dictionary search section, be configured to from the list dictionary search have with input picture at least one list classification of the line information that is complementary of the line information of list, constitute said candidate's list of categories.
Remarks 13. is according to remarks 12 described devices, and wherein, said candidate's list of categories confirms that portion also comprises:
Analog information acquisition portion, be configured to search have with input picture in the list classification of the line information that is complementary of the line information of list the time, obtain the analog information of said at least one list classification;
Tabulation generation portion is configured to obtain similar list classification based on said analog information, and said at least one list classification is constituted said candidate's list of categories with similar list classification.
Remarks 14. is according to remarks 11 described devices, and wherein, the list classification confirms that portion comprises:
Preparatory print What acquisition portion is configured to obtain from the list dictionary the preparatory print What of each the candidate's classification candidate's list of categories;
The similarity calculating part is configured to calculate the similarity between the preparatory print What of preparatory print What and the list in the input picture of each candidate's classification;
Classification is confirmed portion, is configured to confirm according to similarity the classification of the list in the input picture.
Remarks 15. is according to remarks 14 described devices; Wherein, said similarity calculating part is configured to preparatory print What according to the preparatory print What of the list of candidate's classification and the list in the input picture is foreground pixel in the corresponding position pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of candidate's classification and calculates similarity.
Remarks 16. is according to remarks 14 described devices, and wherein, classification confirms that portion further is configured to:
If the maximum comparability that calculates more than predetermined threshold, then will have the classification of candidate's classification of maximum comparability as the list in the input picture;
If the maximum comparability that calculates does not surpass predetermined threshold, then the list in the input picture is confirmed as new classification.
The device of the classification of the list in 17. 1 kinds of definite input pictures of remarks comprises:
The other search section of main classes is configured to line information and other line information of each main classes of the list in the input picture are compared, and wherein, each main classes does not comprise the list of at least one classification;
The list classification is confirmed portion, is configured to: if find the main classes with coupling line information other, then confirm the classification of the list in the input picture according to preparatory print What; If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
Remarks 18. is according to remarks 17 described devices, and wherein, the list classification confirms that portion comprises:
The similarity calculating part, be configured to calculate main classes not in similarity between the preparatory print What of preparatory print What and the list in the input picture of list of each classification;
Classification is confirmed portion, is configured to confirm the classification under the list in the input picture according to similarity.
Remarks 19. is according to remarks 18 described devices; Wherein, the similarity calculating part is configured to preparatory print What according to the preparatory print What of the list of each classification and the list in the input picture is foreground pixel in the corresponding position pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of said each classification and calculates similarity.
Remarks 20. is according to remarks 18 described devices, and wherein, classification confirms that portion is configured to:
If the maximum comparability that calculates more than predetermined threshold, then will have the classification of the classification of maximum comparability as the list in the input picture; If the maximum comparability that calculates does not surpass predetermined threshold, then the list in the input picture is confirmed as new classification.
Claims (10)
1. the class method for distinguishing of the list in the definite input picture comprises:
Line information according to the list in the input picture is confirmed candidate's list of categories;
If said candidate's list of categories is not empty, then further confirm the classification of the list in the input picture according to preparatory print What;
If said candidate's list of categories is empty, confirm that then the list in the said input picture is new classification.
2. method according to claim 1, wherein, confirm that according to the line information of the list in the input picture processing of candidate's list of categories comprises:
From the list dictionary search have with input picture at least one list classification of the line information that is complementary of the line information of list, constitute said candidate's list of categories.
3. method according to claim 2, wherein, confirm that according to the line information of the list in the input picture processing of candidate's list of categories also comprises:
Search have with input picture at least one list classification of the line information that is complementary of the line information of list the time, obtain the analog information of said at least one list classification;
Obtain similar list classification based on said analog information, and with said at least one list classification with similar list classification, constitute said candidate's list of categories.
4. method according to claim 1, wherein, confirm that according to preparatory print What the processing of the classification of the list in the input picture comprises:
The preparatory print What of each the candidate's classification from list dictionary acquisition candidate list of categories;
Calculate the similarity between the preparatory print What of preparatory print What and the list in the input picture of each candidate's classification;
Confirm the classification of the list in the input picture according to similarity.
5. method according to claim 4; Wherein, the pixel quantity shared ratio in the foreground pixel of the preparatory print What of the list of candidate's classification that is foreground pixel in the corresponding position according to the preparatory print What of the preparatory print What of the list of candidate's classification and the list in the input picture is calculated similarity.
6. method according to claim 4, wherein, confirm that according to similarity the processing of the classification of the list in the input picture comprises:
If the maximum comparability that calculates more than predetermined threshold, then will have the classification of candidate's classification of maximum comparability as the list in the input picture;
If the maximum comparability that calculates does not surpass predetermined threshold, then the list in the input picture is confirmed as new classification.
7. the class method for distinguishing of the list in the definite input picture comprises:
Line information and other line information of each main classes of list in the input picture are compared, and wherein, each main classes does not comprise the list of at least one classification;
If find main classes other, then confirm the classification of the list in the input picture according to preparatory print What with coupling line information;
If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
8. method according to claim 7, wherein, confirm that according to preparatory print What the processing of the classification of the list in the input picture comprises:
Calculate main classes not in similarity between the preparatory print What of preparatory print What and the list in the input picture of list of each classification;
Confirm the classification under the list in the input picture according to similarity.
9. the device of the classification of the list in the definite input picture comprises:
Candidate's list of categories is confirmed portion, is configured to confirm candidate's list of categories according to the line information of the list in the input picture;
The list classification is confirmed portion, is configured to: if said candidate's list of categories not for empty, is then further confirmed the classification of the list in the input picture according to preparatory print What; If said candidate's list of categories is empty, confirm that then the list in the said input picture is new classification.
10. the device of the classification of the list in the definite input picture comprises:
The other search section of main classes is configured to line information and other line information of each main classes of the list in the input picture are compared, and wherein, each main classes does not comprise the list of at least one classification;
The list classification is confirmed portion, is configured to: if find the main classes with coupling line information other, then confirm the classification of the list in the input picture according to preparatory print What; If do not find main classes other, confirm that then the list in the said input picture is new classification with coupling line information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101046988A CN102750514A (en) | 2011-04-20 | 2011-04-20 | Method and device for determining categories of lists in input images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101046988A CN102750514A (en) | 2011-04-20 | 2011-04-20 | Method and device for determining categories of lists in input images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102750514A true CN102750514A (en) | 2012-10-24 |
Family
ID=47030681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011101046988A Pending CN102750514A (en) | 2011-04-20 | 2011-04-20 | Method and device for determining categories of lists in input images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102750514A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101354703A (en) * | 2007-07-23 | 2009-01-28 | 夏普株式会社 | Apparatus and method for processing document image |
-
2011
- 2011-04-20 CN CN2011101046988A patent/CN102750514A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101354703A (en) * | 2007-07-23 | 2009-01-28 | 夏普株式会社 | Apparatus and method for processing document image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11580763B2 (en) | Representative document hierarchy generation | |
| US8150156B2 (en) | Automated processing of paper forms using remotely-stored templates | |
| US9684843B2 (en) | Video capture in data capture scenario | |
| CN112016304A (en) | Text error correction method and device, electronic equipment and storage medium | |
| US11348330B2 (en) | Key value extraction from documents | |
| US10049096B2 (en) | System and method of template creation for a data extraction tool | |
| CN109784146B (en) | Font type identification method, electronic equipment and storage medium | |
| CN109598228B (en) | Method and system for electronically recording and archiving paper files | |
| US9286526B1 (en) | Cohort-based learning from user edits | |
| US8855421B2 (en) | Methods and apparatuses for Embedded Media Marker identification | |
| CN103703461A (en) | Detecting source languages of search queries | |
| CN113268615A (en) | Resource label generation method and device, electronic equipment and storage medium | |
| CN117725170A (en) | Policy question-answering method and system based on large language model and knowledge graph technology | |
| US11080808B2 (en) | Automatically attaching optical character recognition data to images | |
| CN113841156A (en) | Control method and device based on image recognition | |
| US11797551B2 (en) | Document retrieval apparatus, document retrieval system, document retrieval program, and document retrieval method | |
| KR102159336B1 (en) | Apparatus and method for searching text/image on document | |
| CN107861931B (en) | Template file processing method and device, computer equipment and storage medium | |
| CN102750514A (en) | Method and device for determining categories of lists in input images | |
| JP2022075467A (en) | Data processing device, data processing method, and program | |
| US11989693B2 (en) | Image-processing device, image processing method, and storage medium on which program is stored | |
| JP5445740B2 (en) | Image processing apparatus, image processing system, and processing program | |
| CN113703759B (en) | Code generation method, device, medium and equipment | |
| JP2019125966A (en) | Image communication device, control method, and program | |
| CN117493712B (en) | PDF document navigable directory extraction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20121024 |