CN106709940A - Counting method and system - Google Patents
Counting method and system Download PDFInfo
- Publication number
- CN106709940A CN106709940A CN201611196027.8A CN201611196027A CN106709940A CN 106709940 A CN106709940 A CN 106709940A CN 201611196027 A CN201611196027 A CN 201611196027A CN 106709940 A CN106709940 A CN 106709940A
- Authority
- CN
- China
- Prior art keywords
- image
- picture
- reference picture
- target area
- target
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a counting method, which comprises the steps of acquiring a reference image and storing the reference image; searching target regions matched with the reference image on a target image according to the reference image; and counting and acquiring the total number of the matched target regions. By adopting the method, counting is performed on images of which regions can be determined according to the selected reference image, target regions matched with the reference image are found on the target image, and the number of the target regions is acquired, so that counting is performed quickly and simply. The technical scheme does not need to count manually, the burden of labor is relieved through automatic counting, and the work efficiency is improved.
Description
Technical field
The present invention relates to image identification technical field, more particularly to a kind of method of counting and system.
Background technology
In life, counting is often may require that, such as courier checks the number of packages of express delivery, go out outing establishment officer point people
Number, other check article number etc..In the prior art, in terms of counting, it is generally adopted by artificial points to count.
Artificial counting is easy to the situation for error count occur, and quantity it is more when it is cumbersome time-consuming.Also having in the prior art makes
Counted with calculator etc., manually put touch of key-press and counted, and put tactile counting manually and be easy to occur without operation, such as
After imprudence is without operation, just to count again.Count complicated, be also for a user pole heavy industry for the operation of big quantity
Make, it is simple unlike artificial counting.
Therefore, a kind of more intelligent automatic counting method how is provided, to mitigate the burden of artificial counting, as ability
The problem of domain urgent need to resolve.
The content of the invention
It is an object of the invention to provide a kind of more intelligent automatic counting method and system, to mitigate the negative of artificial counting
Load.
The purpose of the present invention is achieved through the following technical solutions:
A kind of method of counting, including:
Reference picture picture is obtained, and is stored;
Found on target image and the target area with reference to images match according to the reference picture picture;
Count and obtain the total quantity of the target area of matching.
Preferably, the step found on target image according to the reference picture picture with the target area with reference to images match
Suddenly further include:The target area that preset matching degree is reached with reference picture picture is found on target image according to reference picture picture.
Preferably, the step of total quantity of the target area for counting and obtaining matching is further included:According to target
The revision directive in region, obtains the total quantity of target area again.
Preferably, it is described acquisition reference picture as the step of specifically include:Reference picture picture is obtained by shooting or choosing image.
Preferably, obtaining reference picture picture, and the step of store after, methods described is further included:
The target image for shooting or importing is obtained, and is stored.
The present invention discloses a kind of number system, including:
Image typing module, for obtaining reference picture picture, and stores;
Image analysis module, for finding the mesh with the reference images match on target image according to the reference picture picture
Mark region;
Counting module, for counting and obtain matching target area total quantity.
Preferably, described image analysis module specifically for:Found and reference picture on target image according to reference picture picture
Target area as reaching preset matching degree.
Preferably, the counting module is further used for:According to the revision directive of target area, target area is obtained again
Total quantity.
Preferably, described image typing module by shooting or choosing image specifically for obtaining reference picture picture.
Preferably, the system also includes acquisition module, for obtaining the target image for shooting or importing, and stores.
A kind of method of counting of the invention is due to including:Reference picture picture is obtained, and is stored;According to the reference picture picture in target
Found on image and the target area with reference to images match;Count and obtain the total quantity of the target area of matching.Using this
Mode, it is possible to determined to want to count the image in which region according to the reference picture picture chosen, looked on target image
Go out the target area matched with reference picture picture, and target area quantity, so as to carry out quick and easy counting, the technology
Scheme manually need not one by one go points, and artificial burden is alleviated by automatic counting, improve operating efficiency.
Brief description of the drawings
Fig. 1 is a kind of flow chart of method of counting of the embodiment of the present invention;
Fig. 2 is the schematic diagram of the reference picture picture of the embodiment of the present invention;
Fig. 3 is the schematic diagram of the target image of the embodiment of the present invention;
Fig. 4 is the schematic diagram of another reference picture picture of the embodiment of the present invention;
Fig. 5 is the schematic diagram of another target image of the embodiment of the present invention;
Fig. 6 is a kind of schematic diagram of number system of the embodiment of the present invention.
Specific embodiment
Although operations to be described as flow chart the treatment of order, many of which operation can by concurrently,
Concomitantly or simultaneously implement.The order of operations can be rearranged.Treatment when its operations are completed can be terminated,
It is also possible to have the additional step being not included in accompanying drawing.Treatment can correspond to method, function, code, subroutine, son
Program etc..
Computer equipment includes user equipment and the network equipment.Wherein, user equipment or client include but is not limited to electricity
Brain, smart mobile phone, PDA etc.;The network equipment includes but is not limited to single network server, the service of multiple webserver compositions
Device group or the cloud being made up of a large amount of computers or the webserver based on cloud computing.Computer equipment can isolated operation realize
The present invention, also can access network and realizes the present invention by with the interactive operation of other computer equipments in network.Calculate
Network residing for machine equipment includes but is not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN, VPN etc..
Term " first ", " second " etc. is may have been used herein to describe unit, but these units should not
When limited by these terms, it is used for the purpose of making a distinction a unit and another unit using these terms.Here institute
The term "and/or" for using includes any and all combination of the listed associated item of one of them or more.When one
Unit is referred to as " connection " or during " coupled " to another unit, and it can be connected or coupled to another unit, or
There may be temporary location.
Term used herein above is not intended to limit exemplary embodiment just for the sake of description specific embodiment.Unless
Context clearly refers else, and singulative " one " otherwise used herein above, " one " also attempt to include plural number.Should also
When understanding, term used herein above " including " and/or "comprising" specify stated feature, integer, step, operation,
The presence of unit and/or component, and do not preclude the presence or addition of one or more other features, integer, step, operation, unit,
Component and/or its combination.
The invention will be further described with preferred embodiment below in conjunction with the accompanying drawings.
Embodiment one
As shown in figure 1, the present invention discloses a kind of method of counting disclosed in the present embodiment, including:
S101, acquisition reference picture picture, and store;
S102, according to the reference picture picture found on target image with reference to images match target area;
S103, the total quantity of the target area for counting and obtaining matching.
A kind of method of counting of the invention is due to including:Reference picture picture is obtained, and is stored;According to the reference picture picture in target
Found on image and the target area with reference to images match;Count and obtain the total quantity of the target area of matching.Using this
Mode, it is possible to determined to want to count the image in which region according to the reference picture picture chosen, looked on target image
Go out the target area matched with reference picture picture, and target area quantity, so as to carry out quick and easy counting, the technology
Scheme manually need not one by one go points, and artificial burden is alleviated by automatic counting, improve operating efficiency.
In the present embodiment, for example, there is a white candle in piece image, user wants to choose the white candle in the image
Used as reference, it is reference picture picture then to select white candle region, after system acquisition after the reference picture picture, is just recorded,
Then user wants how many root white candle on the target image is known on a target image, it is possible to allow system according to just
Just the reference picture picture of record carries out the analyses and comparison of image, so as to find out in the target image with reference picture as corresponding target
Region, for example have found 15 with the white candle with reference to images match is target area, then system has just counted target
The quantity in region is 15, so as to complete countings, greatly facilitates the operation of counting, it is not necessary to it is artificial one by one go count
Number, alleviates artificial burden.In the present embodiment, after system acquisition after the reference picture picture, record can be to be stored temporarily in system
In, it is also possible to it is directly stored in system.Method in the present embodiment can carry shooting using in the terminal
Head, so can conveniently obtain image, and referring for example to image, target image etc., the image of acquisition can be graphic form,
It can be visual form.
The picture recognition technology applied in the present embodiment is existing picture recognition technology, and such as recognition of face, fingerprint is known
Not, images match etc., the application for having maturation in the prior art.Image recognition technology is probably with the principal character of image
Based on.Each image has its feature, and such as letter A has a point, and P has a circle and there is individual acute angle etc. at the center of Y.To figure
The dynamic research of eye shows that sight line is always concentrated in the principal character of image during as identification, that is, concentrates on image outline song
The place of degree maximum or contour direction suddenly change, these local information content are maximum.And the scanning route of eyes is also always
Gone in another feature from a feature successively.As can be seen here, in image recognition processes, perceptual mechanism must exclude input
Redundant information, extract crucial information out.Meanwhile, must have a mechanism for responsible integration information in brain, it can point
The finish message that stage obtains is into a complete consciousness map.In mankind's image identification system, the identification to complicated image
Could often be realized by the Information procession of different levels.For familiar figure, due to having grasped its principal character, just
It can be recognized as a unit, without it is further noted that its details.This entirety being made up of the unit material for isolating
Unit is called chunk, and each chunk is simultaneously perceived.In the identification of written material, people not only can be a Chinese
The units such as the stroke or radical of word constitute a chunk, and can the word or phrase for often occurring together in groups block unit come
Recognized.
The basic process of image recognition includes:
(1) acquisition of information:It is, by sensor, the information such as light or sound to be converted into power information.Information can be two
The image of dimension such as word, image etc.;Can be one-dimensional waveform such as sound wave, electrocardiogram, electroencephalogram;Can also be physical quantity and patrol
Collect value.
(2) pre-process:Including A D, binaryzation, smooth, the conversion of image, enhancing recovers, and filtering etc. refers mainly to image
Treatment;
(3) feature extraction and selection:, it is necessary to carry out the extraction and selection of feature in pattern-recognition, for example, a width
The image of 64x64 can obtain 4096 data, and this initial data in measurement space is obtained in feature space by converting
The feature of classification essence can most be reflected.Here it is the process of feature extraction and selection;
(4) classifier design:The major function of classifier design is by training determination decision rule, making by such judgement
During rule classification, error rate is minimum;
(5) categorised decision:Identified object is classified in feature space.
According to other in which example, it is described according to the reference picture as found on target image with reference to images match
The step of target area, further includes:Found on target image according to reference picture picture and reach preset matching degree with reference picture picture
Target area.
According to above-mentioned image recognition technology, according to reference picture as recognition target image target area when, be relatively to be defined
True carrying out matches, and can set matching degree, only target area is just designated as in the region for reaching matching degree, for example, matching degree
80% is set to, only the region of the identification can just be counted when the region of identification reaches 80% with the matching degree of reference picture picture
It is target area, certainly, matching degree is all designated as target area more than or equal to 80%, so matching degree is 90%, 100% is also
Target area.
According to one of example, obtain reference picture as the step of specifically include:Ginseng is obtained by shooting or choosing image
According to image.So by the region in choosing image after camera shooting image as reference picture picture, or can directly move
Piece image is selected in the equipment such as dynamic terminal, the subregion of the image is chosen as reference picture picture.Can certainly direct access
The piece image that the image that camera shoots is stored as reference picture picture, or directly in selected equipment is used as reference picture picture.This reality
Apply in example, the region chosen after shooting image in image selects one as reference picture picture, or directly in the equipment such as mobile terminal
Width image, the subregion for choosing the image can more accurately define reference as the mode of reference picture picture, so that statistics
It is more accurate during the quantity of target area.
According to one of example, the reference picture picture on reference picture picture is obtained, and the step of store after, methods described
Further include:
The target image for shooting or importing is obtained, and is stored.Thus target image can be photographed by camera, or
Target image is obtained by the importing of image, so as to be counted to target image, counted.
In the present embodiment, as can be chosen from target image, i.e., reference picture seems the one of target image to reference picture
Such as, in above-mentioned case, there are some white candles part in an image, user wonders the white candle number in this image
Amount, it is possible to the region of one of white candle is selected in this image as reference picture picture, so as to according to the reference picture
As matching target area, the target area for for example matching is 15, if target area does not count reference picture picture, that
The total quantity of the white candle in image should add the candle of reference picture picture, so being 16.Certainly, in the target image
Reference picture itself is also counted during middle matching, or in matching, if so target area for matching
It it is 15, then total quantity is also 15, when reference picture seems a part for target image, if calculate reference zone
It is interior, can be according to being configured the need for user.
In the present embodiment, reference picture is chosen as can not be from target image, i.e., reference picture picture is not target image
A part, reference picture picture chooses from other images or shoots or import etc..Specifically, such as in above-mentioned case, reference picture
Image as that can be the independent white candle for shooting, the image for so showing becomes apparent from, so as to be more prone to matching.
Further wrapped according to other in which example, the step of the total quantity of the statistics and the target area for obtaining matching
Include:According to the revision directive of target area, the total quantity of target area is obtained again.
Adopt in this way, it is possible to reduce the error rate of statistical magnitude, more accurately to obtain statistical magnitude.Amendment
Mode can be modified by the way of artificial correction, correct statistics, naturally it is also possible to use other modes, for example, weigh
New statistics mode once carries out the counting again so as to be proofreaded of quantity;Or counted again after modification matching degree, change
Matching degree can improve matching degree, such as the matching degree that sets is 70% when counting for the first time, can be by when counting for second
Matching degree is set to 75% so that more accurate statistics, naturally it is also possible to reduce matching degree, such as second when counting will
66% is set to degree, so as to the target area supplement for missing first time is entered.In addition, reference picture picture can be from target figure
Chosen as in, i.e., when reference picture seems a part for target image, need to count reference zone itself in matching,
Directly can also now Jia one in statistical magnitude and be total quantity by the way of amendment.Certainly in this case,
Initial number can be set in the setting of statistical magnitude for 2, or Jia one in quantity during statistics after statistics.
According to above-described embodiment, example, as shown in Fig. 2 marking subregion in the image of Fig. 2 and being set as reference picture
The part in oval frame in picture, i.e. figure, system is stored to this.Afterwards, as shown in figure 3, Fig. 3 is target image, according to
The reference picture picture selected in Fig. 2 will in figure 3 find the target area that matching degree reaches, and such as matching degree is set to 70%,
Therefore system will in figure 3 find the region for reaching 70% as matching degree with reference picture, target area is designated as, so as to count mesh
The quantity in region is marked, is counted, the quantity for counting on is 28.
Example, as shown in figure 4, Fig. 4 is reference picture picture, while subregion will be marked in Fig. 4 and is set as reference picture
Region in picture, i.e. figure in rectangle frame, system is stored to this.Afterwards, as shown in figure 5, Fig. 5 is target image, according to Fig. 4
In reference picture picture will in Figure 5 find the target area that matching degree reaches, such as matching degree is set to 60%, therefore system
The region for reaching 60% as matching degree with reference picture will be in figure 3 found, target area is designated as, so as to count target area
Quantity, is counted, and the quantity for counting on is 11.
According to one of example of the invention, as shown in fig. 6, a kind of number system disclosed in the present embodiment, including:
Image typing module 101, for obtaining reference picture picture, and stores;
Image analysis module 102, for being found on target image and the reference images match according to the reference picture picture
Target area;
Counting module 103, for counting and obtain matching target area total quantity.
Which adopt in this way, it is possible to determined to want to count the image in region according to the reference picture picture chosen
Number, finds out the target area matched with reference picture picture on target image, and target area quantity, it is quick so as to carry out
Simple to count, the technical scheme manually need not one by one go points, and artificial burden is alleviated by automatic counting, improve
Operating efficiency.
In the present embodiment, for example, there is a white candle in piece image, user wants to choose the white candle in the image
Used as reference, it is reference picture picture then to select white candle region, after system acquisition after the reference picture picture, is just recorded,
Then user wants how many root white candle on the target image is known on a target image, it is possible to allow system according to just
Just the reference picture picture of record carries out the analyses and comparison of image, so as to find out in the target image with reference picture as corresponding target
Region, for example have found 15 with the white candle with reference to images match is target area, then system has just counted target
The quantity in region is 15, so as to complete countings, greatly facilitates the operation of counting, it is not necessary to it is artificial one by one go count
Number, alleviates artificial burden.In the present embodiment, after system acquisition after the reference picture picture, record can be to be stored temporarily in system
In, it is also possible to it is directly stored in system.Method in the present embodiment can carry shooting using in the terminal
Head, so can conveniently obtain image, and referring for example to image, target image etc., the image of acquisition can be graphic form,
It can be visual form.
According to other in which example, described image analysis module specifically for:According to reference picture picture on target image
Find the target area that preset matching degree is reached with reference picture picture.
According to above-mentioned image recognition technology, according to reference picture as recognition target image target area when, be relatively to be defined
True carrying out matches, and can set matching degree, only target area is just designated as in the region for reaching matching degree, for example, matching degree
80% is set to, only the region of the identification can just be counted when the region of identification reaches 80% with the matching degree of reference picture picture
It is target area, certainly, matching degree is all designated as target area more than or equal to 80%, so matching degree is 90%, 100% is also
Target area.
According to one of example, image typing module by shooting or choosing image specifically for obtaining reference picture picture.
So can be by the region in choosing image after camera shooting image as reference picture picture or direct in mobile terminal etc.
Piece image is selected in equipment, the subregion of the image is chosen as reference picture picture.Can certainly the bat of direct access camera
The piece image that the image taken the photograph is stored as reference picture picture, or directly in selected equipment is used as reference picture picture.In the present embodiment, clap
Take the photograph the region chosen in image after image and piece image is selected in the equipment such as mobile terminal as reference picture picture, or directly, select
The subregion for taking the image can more accurately define reference as the mode of reference picture picture, so that statistics target area number
It is more accurate during amount.
According to one of example, the system also includes acquisition module, for obtaining the target image for shooting or importing,
And store.Thus target image can be photographed by camera, or target image is obtained by the importing of image, so that
Target image is counted, is counted.
In the present embodiment, as can be chosen from target image, i.e., reference picture seems the one of target image to reference picture
Such as, in above-mentioned case, there are some white candles part in an image, user wonders the white candle number in this image
Amount, it is possible to the region of one of white candle is selected in this image as reference picture picture, so as to according to the reference picture
As matching target area, the target area for for example matching is 15, if target area does not count reference picture picture, that
The total quantity of the white candle in image should add the candle of reference picture picture, so being 16.Certainly, in the target image
Reference picture itself is also counted during middle matching, or in matching, if so target area for matching
It it is 15, then total quantity is also 15, when reference picture seems a part for target image, if calculate reference zone
It is interior, can be according to being configured the need for user.
In the present embodiment, reference picture is chosen as can not be from target image, i.e., reference picture picture is not target image
A part, reference picture picture chooses from other images or shoots or import etc..Specifically, such as in above-mentioned case, reference picture
Image as that can be the independent white candle for shooting, the image for so showing becomes apparent from, so as to be more prone to matching.
According to other in which example, counting module is further used for:According to the revision directive of target area, obtain again
The total quantity of target area.
Adopt in this way, it is possible to reduce the error rate of statistical magnitude, more accurately to obtain statistical magnitude.Amendment
Mode can be modified by the way of artificial correction, correct statistics, naturally it is also possible to use other modes, for example, weigh
New statistics mode once carries out the counting again so as to be proofreaded of quantity;Or counted again after modification matching degree, change
Matching degree can improve matching degree, such as the matching degree that sets is 70% when counting for the first time, can be by when counting for second
Matching degree is set to 75% so that more accurate statistics, naturally it is also possible to reduce matching degree, such as second when counting will
66% is set to degree, so as to the target area supplement for missing first time is entered.In addition, reference picture picture can be from target figure
Chosen as in, i.e., when reference picture seems a part for target image, need to count reference zone itself in matching,
Directly can also now Jia one in statistical magnitude and be total quantity by the way of amendment.Certainly in this case,
Initial number can be set in the setting of statistical magnitude for 2, or Jia one in quantity during statistics after statistics.
According to above-described embodiment, example, as shown in Fig. 2 marking subregion in the image of Fig. 2 and being set as reference picture
The part in oval frame in picture, i.e. figure, system is stored to this.Afterwards, as shown in figure 3, Fig. 3 is target image, according to
The reference picture picture selected in Fig. 2 will in figure 3 find the target area that matching degree reaches, and such as matching degree is set to 70%,
Therefore system will in figure 3 find the region for reaching 70% as matching degree with reference picture, target area is designated as, so as to count mesh
The quantity in region is marked, is counted, the quantity for counting on is 28.
Example, as shown in figure 4, Fig. 4 is reference picture picture, while subregion will be marked in Fig. 4 and is set as reference picture
Region in picture, i.e. figure in rectangle frame, system is stored to this.Afterwards, as shown in figure 5, Fig. 5 is target image, according to Fig. 4
In reference picture picture will in Figure 5 find the target area that matching degree reaches, such as matching degree is set to 60%, therefore system
The region for reaching 60% as matching degree with reference picture will be in figure 3 found, target area is designated as, so as to count target area
Quantity, is counted, and the quantity for counting on is 11.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to assert
Specific implementation of the invention is confined to these explanations.For general technical staff of the technical field of the invention,
On the premise of not departing from present inventive concept, some simple deduction or replace can also be made, should be all considered as belonging to of the invention
Protection domain.
Claims (10)
1. a kind of method of counting, it is characterised in that including:
Reference picture picture is obtained, and is stored;
Found on target image and the target area with reference to images match according to the reference picture picture;
Count and obtain the total quantity of the target area of matching.
2. method according to claim 1, it is characterised in that it is described according to the reference picture picture found on target image with
With reference to images match target area the step of further include:Found and reference picture picture on target image according to reference picture picture
Reach the target area of preset matching degree.
3. method according to claim 1, it is characterised in that the statistics and obtain matching target area total quantity
The step of further include:According to the revision directive of target area, the total quantity of target area is obtained again.
4. method according to claim 1, it is characterised in that the acquisition reference picture as the step of specifically include:Pass through
Shoot or choose image and obtain reference picture picture.
5. method according to claim 1, it is characterised in that described after the step of obtaining reference picture picture, and store
Method is further included:
The target image for shooting or importing is obtained, and is stored.
6. a kind of number system, it is characterised in that including:
Image typing module, for obtaining reference picture picture, and stores;
Image analysis module, for finding the target area with the reference images match on target image according to the reference picture picture
Domain;
Counting module, for counting and obtain matching target area total quantity.
7. system according to claim 6, it is characterised in that described image analysis module specifically for:According to reference picture
The target area of preset matching degree is reached with reference picture picture as being found on target image.
8. system according to claim 6, it is characterised in that the counting module is further used for:According to target area
Revision directive, again obtain target area total quantity.
9. system according to claim 6, it is characterised in that described image typing module specifically for, by shooting or
Choose image and obtain reference picture picture.
10. system according to claim 6, it is characterised in that the system also includes acquisition module, shoots for obtaining
Or the target image for importing, and store.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611196027.8A CN106709940A (en) | 2016-12-22 | 2016-12-22 | Counting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611196027.8A CN106709940A (en) | 2016-12-22 | 2016-12-22 | Counting method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106709940A true CN106709940A (en) | 2017-05-24 |
Family
ID=58939539
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611196027.8A Pending CN106709940A (en) | 2016-12-22 | 2016-12-22 | Counting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106709940A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1607547A (en) * | 2003-10-16 | 2005-04-20 | 中南大学 | Rods on-line counting method and device |
JP2005326966A (en) * | 2004-05-12 | 2005-11-24 | Mitsubishi Electric Corp | Person counting apparatus |
US20130266184A1 (en) * | 2009-12-23 | 2013-10-10 | General Electric Company | Methods for Automatic Segmentation and Temporal Tracking |
CN104751109A (en) * | 2013-12-31 | 2015-07-01 | 西门子医疗保健诊断公司 | Method and device for identifying consumable |
CN105224913A (en) * | 2015-09-01 | 2016-01-06 | 上海斐讯数据通信技术有限公司 | A kind of number of articles detection method and device |
-
2016
- 2016-12-22 CN CN201611196027.8A patent/CN106709940A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1607547A (en) * | 2003-10-16 | 2005-04-20 | 中南大学 | Rods on-line counting method and device |
JP2005326966A (en) * | 2004-05-12 | 2005-11-24 | Mitsubishi Electric Corp | Person counting apparatus |
US20130266184A1 (en) * | 2009-12-23 | 2013-10-10 | General Electric Company | Methods for Automatic Segmentation and Temporal Tracking |
CN104751109A (en) * | 2013-12-31 | 2015-07-01 | 西门子医疗保健诊断公司 | Method and device for identifying consumable |
CN105224913A (en) * | 2015-09-01 | 2016-01-06 | 上海斐讯数据通信技术有限公司 | A kind of number of articles detection method and device |
Non-Patent Citations (1)
Title |
---|
骆志坚: "一种棒材自动计数检测系统的研究与应用", 《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111950723B (en) | Neural network model training method, image processing method, device and terminal equipment | |
CN110119673B (en) | Non-inductive face attendance checking method, device, equipment and storage medium | |
CN103870516B (en) | Retrieve the method for image, paint in real time reminding method and its device | |
EP2902941B1 (en) | System and method for visually distinguishing faces in a digital image | |
CN109376596A (en) | Face matching process, device, equipment and storage medium | |
CN109858384B (en) | Face image capturing method, computer readable storage medium and terminal device | |
CN109035246B (en) | Face image selection method and device | |
US9613296B1 (en) | Selecting a set of exemplar images for use in an automated image object recognition system | |
CN108898579A (en) | A kind of image definition recognition methods, device and storage medium | |
CN110427895A (en) | A kind of video content similarity method of discrimination based on computer vision and system | |
CN108897757B (en) | Photo storage method, storage medium and server | |
WO2005109344A1 (en) | Method for registering iris, device for registering iris and program for registering iris | |
CN108781252B (en) | Image shooting method and device | |
CN110717058B (en) | Information recommendation method and device and storage medium | |
CN108287833A (en) | It is a kind of for the art work identification to scheme to search drawing method | |
CN102567716A (en) | Face synthetic system and implementation method | |
CN108182252A (en) | A kind of Personnel disputes arbitration information storage system and method | |
CN109815823B (en) | Data processing method and related product | |
CN106056138A (en) | Picture processing device and method | |
CN112328345A (en) | Method and device for determining theme color, electronic equipment and readable storage medium | |
CN110175990A (en) | Quality of human face image determination method, device and computer equipment | |
CN110322418A (en) | A kind of super-resolution image generates the training method and device of confrontation network | |
CN111598176B (en) | Image matching processing method and device | |
CN108171231A (en) | A kind of communication means and device based on image identification | |
CN112200844A (en) | Method, device, electronic equipment and medium for generating image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170524 |
|
RJ01 | Rejection of invention patent application after publication |