CN115146094B - Quick seal query method and system based on HOG characteristics - Google Patents
Quick seal query method and system based on HOG characteristics Download PDFInfo
- Publication number
- CN115146094B CN115146094B CN202210834508.6A CN202210834508A CN115146094B CN 115146094 B CN115146094 B CN 115146094B CN 202210834508 A CN202210834508 A CN 202210834508A CN 115146094 B CN115146094 B CN 115146094B
- Authority
- CN
- China
- Prior art keywords
- seal
- hog
- standard
- query
- features
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 57
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013461 design Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 230000006855 networking Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a seal quick query method and system based on HOG characteristics, comprising the steps of obtaining the initial information of a query seal of a current required seal which is sent by a current seal query main body and needs to be queried, generating a standard electronic seal image according to the seal query key words, and generating the standard HOG characteristics of the current query image according to the standard electronic seal image; generating initial specific HOG characteristics of a current query seal, and generating characteristics of the current determined query seal; comparing the currently determined query seal characteristics with the pre-stored standard HOG seal characteristics, and screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics. The application realizes flexible seal inquiry based on the seal inquiry key words and seal special requirement characteristics, and based on the pre-stored standard HOG seal characteristics, thereby ensuring the inquiry flexibility, reducing the retrieval time, improving the retrieval efficiency and improving the retrieval accuracy.
Description
Technical Field
The application relates to the technical field of seal inquiry, in particular to a seal quick inquiry method and system based on HOG characteristics.
Background
Along with the increase of the demands of people on the seals, the demands on seal inquiry are more important, and various methods are needed for seal inquiry, such as a seal networking inquiry realizing device based on the Internet of things and a cloud computing platform, which is disclosed in the patent of the invention with the application number of 201210155988.X, in particular to a seal networking inquiry realizing device using the Internet of things with information acquisition and the cloud computing platform. In order to solve the defect that the automatic information acquisition of the existing seal stamping system is insufficient, the target management of the use of the seal cannot be realized. Seal networking inquiry realizing device based on thing networking and cloud computing platform includes: the seal management cloud storage processing platform (101), a wireless or wired communication channel (102), GPRS or the Internet (103), an embedded processor (104), an infrared pair tube (105), a seal head (106) and a pressure sensor (107); the embedded processor (104) is connected with the infrared geminate transistors (105) and is used for sampling stamping information of the stamp head (106); the embedded processor (104) is connected with the pressure sensor (107) to confirm the stamping information of the stamp head (106).
Obviously, the hardware system adopted by the seal networking inquiry realizing device is too complex, the operation is complicated, no matter the device maintenance personnel or inquiry using personnel are brought great trouble, the inconvenient use is generated, in addition, at present, because more artistic words exist in the electronic seal, the artistic words are difficult to identify, when a merchant stores a plurality of available seals, the user cannot search through a method of searching keywords, and therefore, the problems of long searching time, low searching efficiency and poor searching accuracy are caused.
Disclosure of Invention
Accordingly, it is necessary to provide a method and a system for quickly searching a stamp based on HOG features, which can reduce the search time, improve the search efficiency and improve the search accuracy.
The technical scheme of the invention is as follows:
a method for quickly querying a seal based on HOG features, the method comprising:
step S100: acquiring inquiry seal initial information of a current required seal to be inquired, which is sent by a current seal inquiry main body, wherein the inquiry seal initial information comprises seal inquiry keywords and seal special requirement characteristics;
step S200: generating a standard electronic seal image according to the seal query keyword, and generating a current query image standard HOG characteristic according to the standard electronic seal image;
step S300: generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal;
step S400: comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
In detail, step S400: comparing the currently determined query seal characteristics with each pre-stored standard HOG seal characteristic, screening out a pre-stored standard seal corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seal to the currently determined seal query body, wherein the method further comprises the following steps:
step S001: obtaining standard seal initial images corresponding to other types of seals corresponding to pre-stored standard seals, wherein one pre-stored standard seal at least corresponds to two standard seal initial images, and the other types of seals corresponding to the pre-stored standard seal correspond to the same fonts;
step S002: similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated;
step S003: screening different types of features of at least two standard seal initial images, and respectively generating different types of tag image features, wherein one standard seal initial image is correspondingly provided with one different type of tag image feature;
step S004: generating common HOG specific features according to the common tag image features, respectively generating dissimilated tag HOG features according to the dissimilated tag image features, wherein one pre-stored standard seal correspondingly has one common HOG specific feature and one dissimilated tag HOG feature;
Step S005: and generating pre-stored standard HOG seal features according to the common HOG specific features and the dissimilated label HOG features corresponding to the pre-stored standard seals, wherein one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal.
To elaborate, step S002: similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated; the method specifically comprises the following steps:
step S0021: screening out the same basic stroke characteristics in the initial images of the standard seals, wherein the basic stroke characteristics comprise at least one of point stroke characteristics, horizontal stroke characteristics, vertical stroke characteristics, left-falling stroke characteristics, right-falling stroke characteristics, lifting stroke characteristics and folding stroke characteristics;
step S0022: carrying out artistic treatment according to the basic stroke characteristics and generating artistic image characteristics, wherein the artistic image characteristics at least comprise one of artistic point stroke characteristics, artistic horizontal stroke characteristics, artistic vertical stroke characteristics, artistic skimming stroke characteristics, artistic right-falling stroke characteristics, artistic lifting stroke characteristics and artistic folding stroke characteristics;
step S0023: and generating common label image features according to the basic stroke features and the artistic image features.
In detail, step S004: generating common HOG specific features according to the common tag image features, and respectively generating differentiated tag HOG features according to the differentiated tag image features, specifically comprising:
step S0041: generating basic stroke HOG features according to the basic stroke features;
step S0042: generating an artistic image HOG feature according to the artistic image feature;
step S0043: and generating common HOG specific features according to the basic stroke HOG features and the artistic image HOG features.
In detail, step S400: comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the method specifically comprises the following steps:
step S410: comparing the initial specific HOG characteristics of the current query seal in the common HOG specific characteristics with the basic stroke HOG characteristics and the artistic image HOG characteristics one by one and respectively generating current first characteristic matching values;
step S420: rejecting the basic strokes HOG features and the artistic image HOG features which are not matched according to the current first feature matching value, and generating standard HOG features after first screening;
Step S430: comparing the special requirement characteristics of the seal with the standard HOG characteristics after the first screening, and generating a second characteristic matching value;
step S440: rejecting the unmatched first-time screened standard HOG features according to the second feature matching value, and obtaining a pre-stored standard seal corresponding to the matched first-time screened standard HOG features;
step S450: and sending the screened pre-stored standard seal to the current seal inquiring body.
In detail, a seal rapid query system based on HOG features, the system comprising:
the initial information acquisition module is used for acquiring the initial information of the query seal of the current required seal which is transmitted by the current seal query main body and needs to be queried, wherein the initial information of the query seal comprises seal query keywords and seal special requirement characteristics;
the HOG feature generation module is used for generating a standard electronic seal image according to the seal query keyword and generating a standard HOG feature of the current query image according to the standard electronic seal image;
the query seal determining module is used for generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal;
The screening seal sending module is used for comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
In detail, the initial information acquisition module is further configured to: obtaining standard seal initial images corresponding to other types of seals corresponding to pre-stored standard seals, wherein one pre-stored standard seal at least corresponds to two standard seal initial images, and the other types of seals corresponding to the pre-stored standard seal correspond to the same fonts; similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated; screening different types of features of at least two standard seal initial images, and respectively generating different types of tag image features, wherein one standard seal initial image is correspondingly provided with one different type of tag image feature; generating common HOG specific features according to the common tag image features, respectively generating dissimilated tag HOG features according to the dissimilated tag image features, wherein one pre-stored standard seal correspondingly has one common HOG specific feature and one dissimilated tag HOG feature; and generating pre-stored standard HOG seal features according to the common HOG specific features and the dissimilated label HOG features corresponding to the pre-stored standard seals, wherein one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal.
In detail, the initial information acquisition module is further configured to: screening out the same basic stroke characteristics in the initial images of the standard seals, wherein the basic stroke characteristics comprise at least one of point stroke characteristics, horizontal stroke characteristics, vertical stroke characteristics, left-falling stroke characteristics, right-falling stroke characteristics, lifting stroke characteristics and folding stroke characteristics; carrying out artistic treatment according to the basic stroke characteristics and generating artistic image characteristics, wherein the artistic image characteristics at least comprise one of artistic point stroke characteristics, artistic horizontal stroke characteristics, artistic vertical stroke characteristics, artistic skimming stroke characteristics, artistic right-falling stroke characteristics, artistic lifting stroke characteristics and artistic folding stroke characteristics; and generating common label image features according to the basic stroke features and the artistic image features.
A computer device comprising a memory and a processor, said memory storing a computer program, said processor implementing the steps of the above-described HOG feature based stamp quick interrogation method when said computer program is executed.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above-described method for fast querying a stamp based on HOG features.
The invention has the following technical effects:
1. according to the method and the system for quickly inquiring the seal based on the HOG characteristics, the initial information of the seal to be inquired, which is sent by the main body of inquiring the current seal, is sequentially acquired, wherein the initial information of the seal to be inquired comprises key words of seal inquiry and special requirement characteristics of the seal; generating a standard electronic seal image according to the seal query keyword, and generating a current query image standard HOG characteristic according to the standard electronic seal image; generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal; comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature, so that flexible seal inquiry is achieved based on seal inquiry keywords and seal special requirement features, comparison with the currently determined inquiry seal features is achieved based on the pre-stored standard HOG seal features, and searching time can be shortened, searching efficiency can be improved, and searching accuracy can be improved while inquiring flexibility is guaranteed.
2. From the hardware required by seal inquiry, the operation steps can be carried out on the terminal equipment only by one terminal equipment without taking excessive complex hardware equipment as support, thereby realizing quick and low-cost seal inquiry.
3. From the aspect of operation feasibility, the user does not need to operate excessive hardware equipment, and only needs to search according to the key information of the seal required to be searched, so that the use convenience is greatly improved.
Drawings
FIG. 1 is a flow diagram of a method for quickly querying a stamp based on HOG features in one embodiment;
FIG. 2 is a schematic illustration of a standard electronic stamp image provided in one embodiment;
FIG. 3 is a schematic diagram of a pre-stored standard stamp provided in one embodiment;
FIG. 4 is a schematic diagram of other types of stamps provided in one embodiment;
FIG. 5 is a block diagram of a stamp rapid query system based on HOG features in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In one embodiment, an application scenario of a seal quick query method based on HOG features is provided, the application scenario comprises an application terminal, the application terminal is used for obtaining query seal initial information of a current required seal to be queried, which is sent by a current seal query main body, wherein the query seal initial information comprises seal query keywords and seal special requirement features; generating a standard electronic seal image according to the seal query keyword, and generating a current query image standard HOG characteristic according to the standard electronic seal image; generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal; comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
The application terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.
In one embodiment, as shown in fig. 1, there is provided a method for quickly querying a stamp based on HOG features, the method comprising:
step S100: acquiring inquiry seal initial information of a current required seal to be inquired, which is sent by a current seal inquiry main body, wherein the inquiry seal initial information comprises seal inquiry keywords and seal special requirement characteristics;
further, in this embodiment, the current stamp inquiry body is a body that needs to inquire about a stamp currently, and if a customer needs to customize the stamp, the corresponding merchant can obtain, on site or remotely, the initial information of the stamp that needs to be inquired about and is sent by the current stamp inquiry body through the application terminal.
The seal inquiry keywords include, but are not limited to, keywords such as "good luck", "everything happy" and "healthy", "wish Yu Bo happy with graduation, and" doctor can smoothly customize the seal from Haw graduation "by clients.
The special requirement features of the seal include, but are not limited to, the format of the seal query keyword and design requirements, such as requirements of setting as artistic words.
By setting the seal inquiry keywords and the seal special requirement characteristics, the flexibility of the current seal inquiry main body in seal inquiry can be improved.
In addition, through the setting of the special requirement characteristics of the seal, the seal can be more accurately searched, and the search accuracy is further improved.
Step S200: generating a standard electronic seal image according to the seal query keyword, and generating a current query image standard HOG characteristic according to the standard electronic seal image;
further, in this embodiment, the standard electronic seal image is a seal image corresponding to a standard word corresponding to the seal query keyword, and specifically, taking the seal query keyword as a "congratulatory message" as an example, the corresponding standard electronic seal image is shown in fig. 2.
Further, for subsequent refined comparison, standard HOG features of the current query image are generated by a person skilled in the art according to the HOG feature extraction method according to the standard electronic seal image.
Step S300: generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal;
further, in this embodiment, the initial HOG feature of the current query stamp is a basic HOG feature for comparison, where the initial HOG feature of the current query stamp is an HOG feature corresponding to an indispensable image portion in the standard electronic stamp image, or, no matter what artistic word the standard electronic stamp image is changed to, a part of the initial HOG feature is an indispensable image, such as a "mouth" of a "Ji" word in luckiness, and then the HOG feature corresponding to the image of the part is the initial HOG feature of the current query stamp.
Furthermore, the accuracy of subsequent inquiry can be improved through the initial specific HOG characteristics of the current inquiry seal, and the accuracy and the range universality of seal inquiry can be improved through the initial specific HOG characteristics of the current inquiry seal based on one seal expression form and inquiring other seal expression forms.
Step S400: comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
Further, in this embodiment, the pre-stored standard HOG seal features are preset, and then the currently determined query seal features are compared with the pre-stored standard HOG seal features, a pre-stored standard seal corresponding to the pre-stored standard HOG seal features matched with the currently determined query seal features is screened out, and the screened pre-stored standard seal is sent to the current seal query body.
Therefore, the flexible seal query is realized based on the seal query key words and the seal special requirement characteristics, and the comparison with the currently determined query seal characteristics is realized based on the pre-stored standard HOG seal characteristics, so that the search time can be reduced, the search efficiency can be improved and the search accuracy can be improved while the query flexibility is ensured.
In addition, from the hardware required by seal inquiry, the operation steps can be carried out on the terminal equipment only by one terminal equipment without taking excessive complex hardware equipment as support, thereby realizing quick and low-cost seal inquiry.
Further, from the aspect of operation feasibility, users do not need to operate excessive hardware equipment, and only need to search according to key information of the seal required to be searched, so that the convenience of use is greatly improved.
In one embodiment, step S400: comparing the currently determined query seal characteristics with each pre-stored standard HOG seal characteristic, screening out a pre-stored standard seal corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seal to the currently determined seal query body, wherein the method further comprises the following steps:
step S001: obtaining standard seal initial images corresponding to other types of seals corresponding to pre-stored standard seals, wherein one pre-stored standard seal at least corresponds to two standard seal initial images, and the other types of seals corresponding to the pre-stored standard seal correspond to the same fonts;
Step S002: similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated;
further, in this embodiment, a "good luck" stamp is taken as an example of a pre-stored standard stamp, as shown in fig. 3. Next, the standard seal initial image corresponding to the other seal types is shown in fig. 4. Then shown in fig. 4 are standard stamp initial images corresponding to 3 other types of stamps.
Of course, the example of fig. 4 is merely for ease of understanding, and the present application is not limited to more abstract fonts and fonts that differ from those of pre-stored standard seals.
Further, the specific step of similar feature screening, namely step S002: similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated; the method specifically comprises the following steps:
step S0021: screening out the same basic stroke characteristics in the initial images of the standard seals, wherein the basic stroke characteristics comprise at least one of point stroke characteristics, horizontal stroke characteristics, vertical stroke characteristics, left-falling stroke characteristics, right-falling stroke characteristics, lifting stroke characteristics and folding stroke characteristics;
As shown in fig. 4, taking "Ji" in the initial image of 3 standard seals as an example, the common label image features are "one" and "mouth" in "shi", the "one" in "shi" corresponds to the horizontal stroke feature, and the "mouth" can be split into the horizontal stroke feature and the vertical stroke feature.
In addition, besides the basic stroke characteristics, the specific character can be set as a basic character characteristic, such as the mouth, which has the characteristics of easy distinction and difficult avoidance, and is an essential basic character in Ji characters.
Furthermore, by setting the basic stroke characteristics and the basic font characteristics, the seal can be better compared and screened later, and the screening accuracy and reliability are improved.
Step S0022: carrying out artistic treatment according to the basic stroke characteristics and generating artistic image characteristics, wherein the artistic image characteristics at least comprise one of artistic point stroke characteristics, artistic horizontal stroke characteristics, artistic vertical stroke characteristics, artistic skimming stroke characteristics, artistic right-falling stroke characteristics, artistic lifting stroke characteristics and artistic folding stroke characteristics;
further, as shown in fig. 4, taking the example of "like" in good luck and happiness, different fonts have different writing methods and different artistic characteristics, but the same strokes, such as the first stroke, can be extracted, and the first stroke is a bent stroke regardless of changing the artistic word, so that the artistic image features can be formed, and the subsequent seal inquiry and screening can be facilitated.
Step S0023: and generating common label image features according to the basic stroke features and the artistic image features.
Furthermore, in the embodiment, the common label image features are generated according to the basic stroke features and the artistic image features, so that reliability and accuracy of subsequent seal inquiry and screening comparison are improved.
Step S003: screening different types of features of at least two standard seal initial images, and respectively generating different types of tag image features, wherein one standard seal initial image is correspondingly provided with one different type of tag image feature;
in this embodiment, the unique characteristic of the font of the differentiated label image features or the font in the stamp becomes a special place of the unique characteristic, and the unique characteristic can meet the requirements of different clients, such as the complex character required by the clients, so that the "meaning" word in the intermediate image in fig. 4 may meet the requirements, and further, the differentiated label image features can be comprehensively used to realize more accurate stamp inquiry and screening.
Step S004: generating common HOG specific features according to the common tag image features, respectively generating dissimilated tag HOG features according to the dissimilated tag image features, wherein one pre-stored standard seal correspondingly has one common HOG specific feature and one dissimilated tag HOG feature;
In one embodiment, step S004: generating common HOG specific features according to the common tag image features, and respectively generating differentiated tag HOG features according to the differentiated tag image features, specifically comprising:
step S0041: generating basic stroke HOG features according to the basic stroke features;
step S0042: generating an artistic image HOG feature according to the artistic image feature;
step S0043: and generating common HOG specific features according to the basic stroke HOG features and the artistic image HOG features.
In this embodiment, the basic stroke HOG feature is generated according to the basic stroke feature; then, generating artistic image HOG features according to the artistic image features; and finally, generating a common HOG specific feature according to the basic stroke HOG feature and the artistic image HOG feature, so that the basic stroke HOG feature and the artistic image HOG feature can be integrated, the common HOG specific feature is generated, and a data basis is provided for the subsequent seal screening.
Step S005: and generating pre-stored standard HOG seal features according to the common HOG specific features and the dissimilated label HOG features corresponding to the pre-stored standard seals, wherein one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal.
Further, in this embodiment, the pre-stored standard HOG seal features are generated according to the common HOG specific features and the differentiated label HOG features corresponding to the pre-stored standard seal, and one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal, so that the corresponding relationship between the pre-stored standard HOG seal features and the pre-stored standard seal is established, and data support is provided for subsequent accurate seal inquiry.
In one embodiment, step S400: comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the method specifically comprises the following steps:
step S410: comparing the initial specific HOG characteristics of the current query seal in the common HOG specific characteristics with the basic stroke HOG characteristics and the artistic image HOG characteristics one by one and respectively generating current first characteristic matching values;
step S420: rejecting the basic strokes HOG features and the artistic image HOG features which are not matched according to the current first feature matching value, and generating standard HOG features after first screening;
Further, in this embodiment, when the current first feature matching value is greater than or equal to a preset first standard matching value, it is determined that the corresponding basic stroke HOG feature and the artistic image HOG feature are matched, and then the matched basic stroke HOG feature and the artistic image HOG feature belong to the standard HOG feature after the first filtering.
Otherwise, if the current first feature matching value is smaller than a preset first standard matching value, judging that the corresponding basic stroke HOG features and artistic image HOG features are unmatched, and eliminating the unmatched basic stroke HOG features and artistic image HOG features.
Step S430: comparing the special requirement characteristics of the seal with the standard HOG characteristics after the first screening, and generating a second characteristic matching value;
in one embodiment, in order to obtain the query result more accurately, and compared with the prior art in which the search result is directly generated, in this step, the seal special requirement feature is compared with the standard HOG feature after the first screening, and a second feature matching value is generated, so that more refined and more accurate query is realized, and the query accuracy is improved.
Step S440: rejecting the unmatched first-time screened standard HOG features according to the second feature matching value, and obtaining a pre-stored standard seal corresponding to the matched first-time screened standard HOG features;
further, when the second feature matching value is greater than or equal to a preset second standard matching value, it is determined that the basic stroke HOG feature and the artistic image HOG feature in the corresponding first-time screened standard HOG features are matched, and then a pre-stored standard seal corresponding to the matched first-time screened standard HOG features is obtained.
Otherwise, when the second feature matching value is smaller than a preset second standard matching value, the basic stroke HOG features and the artistic image HOG features in the corresponding first-time screened standard HOG features are judged to be unmatched, and then the unmatched first-time screened standard HOG features are removed.
And finally, obtaining a pre-stored standard seal corresponding to the matched standard HOG characteristics after the first screening according to the information processing result.
Step S450: and sending the screened pre-stored standard seal to the current seal inquiring body.
In one embodiment, compared with the query mode of directly querying the latter and querying the latter in a common hundred degrees and then querying the result in the prior art, the method and the device realize more accurate and refined comparison, add personalized requirements of a query main body, and further utilize the high accuracy capability of HOG features in image comparison, thereby greatly improving the query accuracy and reliability.
Therefore, the method and the device realize more accurate, finer and more flexible seal inquiry compared with the prior art based on keyword inquiry results such as hundred-degree inquiry, and realize more flexible characteristic inquiry for the simple HOG characteristic inquiry adopted in the conventional arrangement in the prior art, thereby realizing the reduction of the retrieval time, the improvement of the retrieval efficiency and the improvement of the retrieval accuracy.
In one embodiment, in step S300: generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image; the method specifically comprises the following steps:
step S310: generating initial specific HOG characteristics according to the current query image standard HOG characteristics;
step S320: generating a first display interface according to the initial specific HOG characteristics, wherein the first display interface is used for displaying the initial specific HOG characteristics;
step S330: acquiring modification of the initial specific HOG characteristics by a seal management main body, and generating modified specific HOG characteristics;
Step S340: acquiring self-setting HOG characteristics set by the current seal inquiry main body;
step S350: and generating initial special HOG characteristics of the current query seal according to the modified special HOG characteristics and the self-setting HOG characteristics.
In one embodiment, by firstly generating the initial specific HOG feature, then displaying the generated initial specific HOG feature based on the first display interface, then acquiring the modified specific HOG feature generated by modifying the initial specific HOG feature by the seal management main body and the self-setting HOG feature set by self-definition, compared with the mode of setting the feature only by machine processing in the conventional technical means, the combination of a machine and a person is realized by combining the self-definition setting and modification of the seal management main body, the self-definition is realized, the accuracy can be ensured, and the reliability and the accuracy are further improved.
In summary, according to the method for quickly querying the seal based on the HOG feature, the initial information of the query seal of the current required seal which is sent by the query main body of the current seal and needs to be queried is sequentially obtained, wherein the initial information of the query seal comprises a seal query keyword and a seal special requirement feature; generating a standard electronic seal image according to the seal query keyword, and generating a current query image standard HOG characteristic according to the standard electronic seal image; generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal; comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature, so that flexible seal inquiry is achieved based on seal inquiry keywords and seal special requirement features, comparison with the currently determined inquiry seal features is achieved based on the pre-stored standard HOG seal features, and searching time can be shortened, searching efficiency can be improved, and searching accuracy can be improved while inquiring flexibility is guaranteed.
It should be noted that, regarding the extraction and generation of HOG features in the present application, color and gamma normalization, image gradient calculation, histogram of construction direction, cell unit combination into large bins, and HOG feature collection which are commonly used in the prior art can be used.
The HOG feature extraction is set by the person skilled in the art, and the present application is not particularly limited.
In one embodiment, as shown in fig. 5, a stamp rapid query system based on HOG features is provided, the system comprising:
the initial information acquisition module is used for acquiring the initial information of the query seal of the current required seal which is transmitted by the current seal query main body and needs to be queried, wherein the initial information of the query seal comprises seal query keywords and seal special requirement characteristics;
the HOG feature generation module is used for generating a standard electronic seal image according to the seal query keyword and generating a standard HOG feature of the current query image according to the standard electronic seal image;
the query seal determining module is used for generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal;
The screening seal sending module is used for comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
In one embodiment, the initial information acquisition module is further configured to:
obtaining standard seal initial images corresponding to other types of seals corresponding to pre-stored standard seals, wherein one pre-stored standard seal at least corresponds to two standard seal initial images, and the other types of seals corresponding to the pre-stored standard seal correspond to the same fonts; similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated; screening different types of features of at least two standard seal initial images, and respectively generating different types of tag image features, wherein one standard seal initial image is correspondingly provided with one different type of tag image feature; generating common HOG specific features according to the common tag image features, respectively generating dissimilated tag HOG features according to the dissimilated tag image features, wherein one pre-stored standard seal correspondingly has one common HOG specific feature and one dissimilated tag HOG feature; and generating pre-stored standard HOG seal features according to the common HOG specific features and the dissimilated label HOG features corresponding to the pre-stored standard seals, wherein one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal.
In one embodiment, the initial information acquisition module is further configured to: screening out the same basic stroke characteristics in the initial images of the standard seals, wherein the basic stroke characteristics comprise at least one of point stroke characteristics, horizontal stroke characteristics, vertical stroke characteristics, left-falling stroke characteristics, right-falling stroke characteristics, lifting stroke characteristics and folding stroke characteristics; carrying out artistic treatment according to the basic stroke characteristics and generating artistic image characteristics, wherein the artistic image characteristics at least comprise one of artistic point stroke characteristics, artistic horizontal stroke characteristics, artistic vertical stroke characteristics, artistic skimming stroke characteristics, artistic right-falling stroke characteristics, artistic lifting stroke characteristics and artistic folding stroke characteristics; and generating common label image features according to the basic stroke features and the artistic image features.
In one embodiment, the initial information acquisition module is further configured to: generating basic stroke HOG features according to the basic stroke features; generating an artistic image HOG feature according to the artistic image feature; and generating common HOG specific features according to the basic stroke HOG features and the artistic image HOG features.
In one embodiment, the screening stamp sending module is further configured to: comparing the initial specific HOG characteristics of the current query seal in the common HOG specific characteristics with the basic stroke HOG characteristics and the artistic image HOG characteristics one by one and respectively generating current first characteristic matching values; rejecting the basic strokes HOG features and the artistic image HOG features which are not matched according to the current first feature matching value, and generating standard HOG features after first screening; comparing the special requirement characteristics of the seal with the standard HOG characteristics after the first screening, and generating a second characteristic matching value; rejecting the unmatched first-time screened standard HOG features according to the second feature matching value, and obtaining a pre-stored standard seal corresponding to the matched first-time screened standard HOG features; and sending the screened pre-stored standard seal to the current seal inquiring body.
In one embodiment, the query stamp determining module is further configured to: generating initial specific HOG characteristics according to the current query image standard HOG characteristics; generating a first display interface according to the initial specific HOG characteristics, wherein the first display interface is used for displaying the initial specific HOG characteristics; acquiring modification of the initial specific HOG characteristics by a seal management main body, and generating modified specific HOG characteristics; acquiring self-setting HOG characteristics set by the current seal inquiry main body; and generating initial special HOG characteristics of the current query seal according to the modified special HOG characteristics and the self-setting HOG characteristics.
In one embodiment, as shown in fig. 6, a computer device includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps described in the above-described method for quickly querying a stamp based on HOG features when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above-described method for fast querying a stamp based on HOG features.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A seal quick query method based on HOG features is characterized by comprising the following steps:
step S100: acquiring inquiry seal initial information of a current required seal to be inquired, which is sent by a current seal inquiry main body, wherein the inquiry seal initial information comprises seal inquiry keywords and seal special requirement characteristics; the special requirement characteristics of the seal comprise formats and design requirements of the seal query keywords, in particular artistic word requirements;
Step S200: generating a standard electronic seal image according to the seal query keyword, and generating a current query image standard HOG characteristic according to the standard electronic seal image;
step S300: generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal; the initial specific HOG characteristic of the current query seal refers to an image of which a part is indispensable no matter what type of artistic word the standard electronic seal image is changed into; the HOG characteristic corresponding to the indispensable image part is the initial specific HOG characteristic of the current query seal;
step S400: comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
2. The method for quickly querying a stamp based on HOG features according to claim 1, wherein step S400: comparing the currently determined query seal characteristics with each pre-stored standard HOG seal characteristic, screening out a pre-stored standard seal corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seal to the currently determined seal query body, wherein the method further comprises the following steps:
step S001: obtaining standard seal initial images corresponding to other types of seals corresponding to pre-stored standard seals, wherein one pre-stored standard seal at least corresponds to two standard seal initial images, and the other types of seals corresponding to the pre-stored standard seal correspond to the same fonts;
step S002: similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated;
step S003: screening different types of features of at least two standard seal initial images, and respectively generating different types of tag image features, wherein one standard seal initial image is correspondingly provided with one different type of tag image feature;
Step S004: generating common HOG specific features according to the common tag image features, respectively generating dissimilated tag HOG features according to the dissimilated tag image features, wherein one pre-stored standard seal correspondingly has one common HOG specific feature and one dissimilated tag HOG feature;
step S005: and generating pre-stored standard HOG seal features according to the common HOG specific features and the dissimilated label HOG features corresponding to the pre-stored standard seals, wherein one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal.
3. The method for quickly querying a stamp based on HOG features according to claim 2, wherein step S002: similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated; the method specifically comprises the following steps:
step S0021: screening out the same basic stroke characteristics in the initial images of the standard seals, wherein the basic stroke characteristics comprise at least one of point stroke characteristics, horizontal stroke characteristics, vertical stroke characteristics, left-falling stroke characteristics, right-falling stroke characteristics, lifting stroke characteristics and folding stroke characteristics;
step S0022: carrying out artistic treatment according to the basic stroke characteristics and generating artistic image characteristics, wherein the artistic image characteristics at least comprise one of artistic point stroke characteristics, artistic horizontal stroke characteristics, artistic vertical stroke characteristics, artistic skimming stroke characteristics, artistic right-falling stroke characteristics, artistic lifting stroke characteristics and artistic folding stroke characteristics;
Step S0023: and generating common label image features according to the basic stroke features and the artistic image features.
4. The method for quickly querying a stamp based on HOG features according to claim 3, wherein step S004: generating common HOG specific features according to the common tag image features, and respectively generating differentiated tag HOG features according to the differentiated tag image features, specifically comprising:
step S0041: generating basic stroke HOG features according to the basic stroke features;
step S0042: generating an artistic image HOG feature according to the artistic image feature;
step S0043: and generating common HOG specific features according to the basic stroke HOG features and the artistic image HOG features.
5. The method for quickly querying a stamp based on HOG features according to claim 4, wherein step S400: comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the method specifically comprises the following steps:
Step S410: comparing the initial specific HOG characteristics of the current query seal with the HOG characteristics of the basic strokes and the HOG characteristics of the artistic image one by one and respectively generating current first characteristic matching values;
step S420: rejecting the basic strokes HOG features and the artistic image HOG features which are not matched according to the current first feature matching value, and generating standard HOG features after first screening;
step S430: comparing the special requirement characteristics of the seal with the standard HOG characteristics after the first screening, and generating a second characteristic matching value;
step S440: rejecting the unmatched first-time screened standard HOG features according to the second feature matching value, and obtaining a pre-stored standard seal corresponding to the matched first-time screened standard HOG features;
step S450: and sending the screened pre-stored standard seal to the current seal inquiring body.
6. A rapid seal inquiry system based on HOG features, the system comprising:
the initial information acquisition module is used for acquiring the initial information of the query seal of the current required seal which is transmitted by the current seal query main body and needs to be queried, wherein the initial information of the query seal comprises seal query keywords and seal special requirement characteristics; the special requirement characteristics of the seal comprise formats and design requirements of the seal query keywords, in particular artistic word requirements;
The HOG feature generation module is used for generating a standard electronic seal image according to the seal query keyword and generating a standard HOG feature of the current query image according to the standard electronic seal image;
the query seal determining module is used for generating initial specific HOG characteristics of the current query seal according to the standard HOG characteristics of the current query image, and generating current determined query seal characteristics according to the special requirement characteristics of the seal and the initial specific HOG characteristics of the current query seal; the initial specific HOG characteristic of the current query seal refers to an image of which a part is indispensable no matter what type of artistic word the standard electronic seal image is changed into; the HOG characteristic corresponding to the indispensable image part is the initial specific HOG characteristic of the current query seal;
the screening seal sending module is used for comparing the currently determined query seal characteristics with all pre-stored standard HOG seal characteristics, screening out pre-stored standard seals corresponding to the pre-stored standard HOG seal characteristics matched with the currently determined query seal characteristics, and sending the screened pre-stored standard seals to the current seal query body; the pre-stored standard HOG seal features are pre-stored, and each pre-stored standard seal corresponds to at least one pre-stored standard HOG seal feature.
7. The HOG feature based stamp rapid query system according to claim 6, wherein the initial information acquisition module is further configured to: obtaining standard seal initial images corresponding to other types of seals corresponding to pre-stored standard seals, wherein one pre-stored standard seal at least corresponds to two standard seal initial images, and the other types of seals corresponding to the pre-stored standard seal correspond to the same fonts; similar feature screening is carried out on at least two standard seal initial images, and common tag image features are generated; screening different types of features of at least two standard seal initial images, and respectively generating different types of tag image features, wherein one standard seal initial image is correspondingly provided with one different type of tag image feature; generating common HOG specific features according to the common tag image features, respectively generating dissimilated tag HOG features according to the dissimilated tag image features, wherein one pre-stored standard seal correspondingly has one common HOG specific feature and one dissimilated tag HOG feature; and generating pre-stored standard HOG seal features according to the common HOG specific features and the dissimilated label HOG features corresponding to the pre-stored standard seals, wherein one pre-stored standard HOG seal feature corresponds to one pre-stored standard seal.
8. The HOG feature based stamp rapid query system according to claim 6, wherein the initial information acquisition module is further configured to: screening out the same basic stroke characteristics in the initial images of the standard seals, wherein the basic stroke characteristics comprise at least one of point stroke characteristics, horizontal stroke characteristics, vertical stroke characteristics, left-falling stroke characteristics, right-falling stroke characteristics, lifting stroke characteristics and folding stroke characteristics; carrying out artistic treatment according to the basic stroke characteristics and generating artistic image characteristics, wherein the artistic image characteristics at least comprise one of artistic point stroke characteristics, artistic horizontal stroke characteristics, artistic vertical stroke characteristics, artistic skimming stroke characteristics, artistic right-falling stroke characteristics, artistic lifting stroke characteristics and artistic folding stroke characteristics; and generating common label image features according to the basic stroke features and the artistic image features.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210834508.6A CN115146094B (en) | 2022-07-14 | 2022-07-14 | Quick seal query method and system based on HOG characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210834508.6A CN115146094B (en) | 2022-07-14 | 2022-07-14 | Quick seal query method and system based on HOG characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115146094A CN115146094A (en) | 2022-10-04 |
| CN115146094B true CN115146094B (en) | 2023-11-21 |
Family
ID=83412149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210834508.6A Active CN115146094B (en) | 2022-07-14 | 2022-07-14 | Quick seal query method and system based on HOG characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115146094B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116010642B (en) * | 2023-03-27 | 2023-06-20 | 北京滴普科技有限公司 | Quick seal query method and system based on HOG characteristics |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000231626A (en) * | 1998-12-07 | 2000-08-22 | Hitachi Ltd | Electronic writing instrument and electronic entering method |
| JP2007072978A (en) * | 2005-09-09 | 2007-03-22 | Oki Electric Ind Co Ltd | Seal inquiry system |
| CN103268363A (en) * | 2013-06-06 | 2013-08-28 | 哈尔滨工业大学 | Elastic HOG (histograms of oriented gradient) feature-based Chinese calligraphy image retrieval method matched with DDTW (Derivative dynamic time wrapping) |
| CN104850961A (en) * | 2015-06-01 | 2015-08-19 | 周绍华 | Intelligent seal system |
| CN107992759A (en) * | 2017-12-13 | 2018-05-04 | 重庆金融资产交易所有限责任公司 | Realize device, method and the computer-readable recording medium of E-seal |
| CN112866205A (en) * | 2020-12-31 | 2021-05-28 | 杭州甘道智能科技有限公司 | Intelligent seal credible verification platform and method based on block chain |
| CN114663899A (en) * | 2022-04-20 | 2022-06-24 | 中国工商银行股份有限公司 | Financial bill processing method, device, equipment and medium |
-
2022
- 2022-07-14 CN CN202210834508.6A patent/CN115146094B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000231626A (en) * | 1998-12-07 | 2000-08-22 | Hitachi Ltd | Electronic writing instrument and electronic entering method |
| JP2007072978A (en) * | 2005-09-09 | 2007-03-22 | Oki Electric Ind Co Ltd | Seal inquiry system |
| CN103268363A (en) * | 2013-06-06 | 2013-08-28 | 哈尔滨工业大学 | Elastic HOG (histograms of oriented gradient) feature-based Chinese calligraphy image retrieval method matched with DDTW (Derivative dynamic time wrapping) |
| CN104850961A (en) * | 2015-06-01 | 2015-08-19 | 周绍华 | Intelligent seal system |
| CN107992759A (en) * | 2017-12-13 | 2018-05-04 | 重庆金融资产交易所有限责任公司 | Realize device, method and the computer-readable recording medium of E-seal |
| CN112866205A (en) * | 2020-12-31 | 2021-05-28 | 杭州甘道智能科技有限公司 | Intelligent seal credible verification platform and method based on block chain |
| CN114663899A (en) * | 2022-04-20 | 2022-06-24 | 中国工商银行股份有限公司 | Financial bill processing method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115146094A (en) | 2022-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214385B (en) | Data acquisition method, data acquisition device and storage medium | |
| CN109753653B (en) | Entity name recognition method, entity name recognition device, computer equipment and storage medium | |
| US8788930B2 (en) | Automatic identification of fields and labels in forms | |
| US20130238968A1 (en) | Automatic Creation of a Table and Query Tools | |
| CN107885430B (en) | Audio playing method and device, storage medium and electronic equipment | |
| CN110377558B (en) | Document query method, device, computer equipment and storage medium | |
| CN109446521B (en) | Named entity recognition method, named entity recognition device, electronic equipment and machine-readable storage medium | |
| US9767088B2 (en) | Stroke autocompletion in a form | |
| CN115146094B (en) | Quick seal query method and system based on HOG characteristics | |
| CN104899560A (en) | Character recognition method and stylus | |
| CN110705233A (en) | Note generation method and device based on character recognition technology and computer equipment | |
| CN112633423B (en) | Training method of text recognition model, text recognition method, device and equipment | |
| WO2022105003A1 (en) | Medical information processing method and apparatus, and electronic device | |
| CN110197238A (en) | A kind of recognition methods, system and the terminal device of font classification | |
| CN111291741B (en) | Receipt identification method and device, computer equipment and storage medium | |
| CN111357015A (en) | Speech synthesis method, apparatus, computer device and computer-readable storage medium | |
| CN113033165A (en) | Spreadsheet file parsing method and device and computer readable storage medium | |
| US20230023636A1 (en) | Methods and systems for preparing unstructured data for statistical analysis using electronic characters | |
| CN110956043A (en) | Domain professional vocabulary word embedding vector training method, system and medium based on alias standardization | |
| CN116225956A (en) | Automated testing method, apparatus, computer device and storage medium | |
| CN115017256A (en) | Power data processing method and device, electronic equipment and storage medium | |
| US20210342556A1 (en) | Foreign language machine translation of documents in a variety of formats | |
| CN111177999A (en) | Text box-based text display method and device and computer equipment | |
| CN115114412B (en) | Method for retrieving information in document, electronic device and storage medium | |
| CN110070020B (en) | Method and system for reading position coding form data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |