CN109961015A - Image-recognizing method, device, equipment and storage medium - Google Patents
Image-recognizing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109961015A CN109961015A CN201910139045.XA CN201910139045A CN109961015A CN 109961015 A CN109961015 A CN 109961015A CN 201910139045 A CN201910139045 A CN 201910139045A CN 109961015 A CN109961015 A CN 109961015A
- Authority
- CN
- China
- Prior art keywords
- image
- target image
- type
- target
- bar code
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
- G06K7/1482—Methods for optical code recognition the method including quality enhancement steps using fuzzy logic or natural solvers, such as neural networks, genetic algorithms and simulated annealing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Electromagnetism (AREA)
- Evolutionary Biology (AREA)
- Automation & Control Theory (AREA)
- General Engineering & Computer Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The disclosure provides a kind of image-recognizing method, device, equipment and storage medium, is related to technical field of image processing, can solve the problems, such as that single image processing equipment can only be handled the image of single type.The specific technical proposal is: obtaining target image to be analyzed；Determine the image type of target image；According to the image type of target image, recognizer corresponding with the image type of target image is obtained from pre-set recognizer list；According to the corresponding recognizer of the image type of target image, target image is identified.The present invention is used for image recognition.
Description
Technical field
This disclosure relates to technical field of image processing more particularly to image-recognizing method, device, equipment and storage medium.
Background technique
With the continuous development of science and technology, barcode scanning equipment, face recognition device are as optics, machinery, electronics, software application etc.
The high-tech product that technology is combined closely has obtained swift and violent development and has been widely applied since birth, but barcode scanning equipment is only
Bar code, two dimensional code etc. can be handled, face recognition device can only identify face, when needs are realized to two dimensional code
Scan process and identification to face, then need to dispose barcode scanning equipment and face recognition device simultaneously, increase cost.In order to
Reduce cost, the equipment that the prior art used while including front camera and rear camera, wherein front camera is used for
Facial image is acquired, rear camera is still accounted for for being scanned to two dimensional code, bar code etc. using two cameras
Use the device space.
Summary of the invention
The embodiment of the present disclosure provides a kind of image-recognizing method, device, equipment and storage medium, is able to solve single image
The problem of processing equipment can only be handled the image of single type.The technical solution is as follows:
According to the first aspect of the embodiments of the present disclosure, a kind of image-recognizing method is provided, this method is applied to be provided with one
The image recognition apparatus of a acquisition module, this method comprises:
Obtain target image to be analyzed；
Determine that the image type of target image, image type include facial image or bar code image, bar code image includes item
Barcode image and image in 2 D code；
According to the image type of target image, the image with target image is obtained from pre-set recognizer list
The corresponding recognizer of type；
According to the corresponding recognizer of the image type of target image, target image is identified.
After being analyzed by the image type of the target image to acquisition, known using corresponding recognizer
Not, it can be realized single image processing equipment to handle different types of image, solve existing single image processing equipment
The problem of image of single type can only being handled.
In one embodiment, the image type for determining target image includes:
Obtain the number of colors of target image；
Judge whether the number of colors of target image is equal to the second preset threshold；
When the number of colors of target image is equal to the second preset threshold, determine that the image type of target image is bar code figure
Picture；
When the number of colors of target image is not equal to the second preset threshold, determine that the image type of target image is face
Image.
In one embodiment, the number of colors for obtaining target image includes:
Obtain the rgb value of each pixel in target image；
According to the rgb value of each pixel, the color of each pixel is determined；
According to the color of each pixel, statistics obtains the number of colors of target image.
In one embodiment, the graph style for determining target image includes:
Gray processing processing is carried out to target image, obtains the number of grey levels of target image；
Judge whether the number of grey levels of target image is equal to the first preset threshold；
When the number of grey levels of target image is equal to the first preset threshold, determine that the image type of target image is bar code
Image；
When the number of grey levels of target image is not equal to the first preset threshold, determine that the image type of target image is behaved
Face image.
In one embodiment, gray processing processing is carried out to target image, the number of grey levels for obtaining target image includes:
Gray processing processing is carried out to target image, obtains the gray value of each pixel in target image；
According to the gray value of each pixel, the grey level histogram of target image is counted；
According to the grey level histogram of target image, the number of grey levels of target image is obtained.
In one embodiment, the image type for determining target image includes:
Feature extraction is carried out to target image, obtains the image feature information of target image；
According to the image feature information of target image and pre-set image classification model, the image of target image is determined
Type, image classification model are obtained according to training sample training.
In one embodiment, according to the corresponding recognizer of the image type of target image, target image is known
Do not include:
When the image type of target image is facial image, target image is identified according to face recognition algorithms,
Obtain face characteristic；
When the image type of target image is graphic code image, target image is identified according to graphic code algorithm,
Obtain image code feature.
According to the second aspect of an embodiment of the present disclosure, a kind of pattern recognition device is provided, comprising:
First obtains module, for obtaining target image to be analyzed；
Determining module, for determining that the image type of target image, image type include facial image or bar code image, item
Code image includes bar code image and image in 2 D code；
Second acquisition module is obtained from pre-set recognizer list for the image type according to target image
Take recognizer corresponding with the image type of target image；
Identification module identifies target image for the corresponding recognizer of image type according to target image.
In one embodiment, determining module includes:
Acquisition submodule, for obtaining the number of colors of target image；
Judging submodule, for judging whether the number of colors of target image is equal to the second preset threshold；
It determines submodule, when being equal to the second preset threshold for the number of colors in target image, determines target image
Image type is bar code image；
It determines submodule, when being not equal to the second preset threshold for the number of colors in target image, determines target image
Image type be facial image.
In one embodiment, acquisition submodule is used for: obtaining the RGB value of each pixel in target image；According to every
The rgb value of a pixel determines the color of each pixel；According to the color of each pixel, statistics obtains target image
Number of colors.
In one embodiment, acquisition submodule obtains target image for carrying out gray processing processing to target image
Number of grey levels；
Judging submodule, for judging whether the number of grey levels of target image is equal to the first preset threshold；
It determines submodule, when being equal to the first preset threshold for the number of grey levels in target image, determines target image
Image type be bar code image；
It determines submodule, when being not equal to the first preset threshold for the number of grey levels in target image, determines target figure
The image type of picture is facial image.
In one embodiment, acquisition submodule is used for: being carried out gray processing processing to target image, is obtained in target image
The gray value of each pixel；According to the gray value of each pixel, the grey level histogram of target image is counted；According to target image
Grey level histogram obtains the number of grey levels of target image.
In one embodiment, acquisition submodule obtains the figure of target image for carrying out feature extraction to target image
As characteristic information；
Determine submodule, for the image feature information and pre-set image classification model according to target image, really
Set the goal the image type of image, and image classification model is obtained according to training sample training.
In one embodiment, identification module, for the image type in target image be facial image when, according to face
Recognizer identifies target image, obtains face characteristic；
Identification module, for the image type in target image be graphic code image when, according to graphic code algorithm to target
Image is identified, image code feature is obtained.
According to the third aspect of an embodiment of the present disclosure, a kind of image recognition apparatus is provided, which includes place
Device and memory are managed, is stored at least one computer instruction in memory, instruction is loaded by processor and executed to realize the
On the one hand performed step and in image-recognizing method described in any embodiment in first aspect.
According to a fourth aspect of embodiments of the present disclosure, a kind of computer readable storage medium is provided, which is characterized in that storage
At least one computer instruction is stored in medium, instruction is loaded by processor and executed to realize first aspect and first party
Performed step in image-recognizing method described in any embodiment in face.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is a kind of flow diagram for image-recognizing method that the embodiment of the present disclosure provides；
Fig. 2 is a kind of structural schematic diagram for pattern recognition device that the embodiment of the present disclosure provides；
Fig. 3 is a kind of structural schematic diagram for pattern recognition device that the embodiment of the present disclosure provides；
Fig. 4 is a kind of structural schematic diagram for image recognition apparatus that the embodiment of the present disclosure provides.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
The embodiment of the present disclosure provides a kind of image-recognizing method, and this method is applied at the image of only one acquisition module
Equipment is managed, acquisition module can be built-in camera, be also possible to other devices for having camera function.As shown in Figure 1, should
Image-recognizing method the following steps are included:
101, target image to be analyzed is obtained.
In the embodiments of the present disclosure, obtaining target image to be analyzed includes: that target to be analyzed is obtained by camera
Image.It should be noted that target image refers to any one image, the disclosure is only indicated by taking target image as an example to target
How image, which is handled, is illustrated, and target does not represent any limitation.
102, the image type of target image is determined.
Image type includes facial image or bar code image, and bar code image includes bar code image or image in 2 D code.By
In there are many methods of determination to the image type of target image, several examples are set forth below and are illustrated.
In first example, determine that the image type of target image includes:
Obtain the number of colors of target image；
Judge whether the number of colors of target image is equal to the second preset threshold；
When the number of colors of target image is equal to the second preset threshold, determine that the image type of target image is bar code figure
Picture；
When the number of colors of target image is not equal to the second preset threshold, determine that the image type of target image is face
Image.
Since two dimensional code, bar code only have two kinds of colors of black and white, and in face figure include multiple color, it therefore, can be with
The image type of target image is determined according to the number of color data.It, can for how to obtain the number of colors of target image
To be obtained according to the rgb value of pixel each in target image, specifically, obtaining the RGB of each pixel in target image
Value；According to the rgb value of each pixel, the color of each pixel is determined；According to the color of each pixel, statistics obtains mesh
The number of colors of logo image.Since any color that naked eyes can be seen in nature can be by R (green), G (red), B
(blue) three kinds of coloured light is mixed according to different ratios, therefore, according to rgb value (i.e. the R value, G value, B of each pixel
Value) and color corresponding relationship, determine the color of each pixel, in turn, count obtain the number of colors of target image.With
Two preset thresholds are 2 to be illustrated, when the number of colors of target image is equal to 2, it is determined that the image type of target image is
Bar code image；When the number of colors of target image is not equal to 2, determine that the image type of target image is facial image.
In second example, determine that the image type of target image includes:
Gray processing processing is carried out to target image, obtains the number of grey levels of target image；
Judge whether the number of grey levels of target image is equal to the first preset threshold；
When the number of grey levels of target image is equal to the first preset threshold, determine that the image type of target image is bar code
Image；
When the number of grey levels of target image is not equal to the first preset threshold, determine that the image type of target image is behaved
Face image.
In the embodiments of the present disclosure, gray processing processing is carried out to target image, obtains the number of grey levels packet of target image
It includes: gray processing processing being carried out to target image, obtains the gray value of each pixel in target image；According to the gray scale of each pixel
Value, counts the grey level histogram of target image；According to the grey level histogram of target image, the number of greyscale levels of target image is obtained
Amount.
The image that gray processing processing is carried out to target image only includes luminance information, does not include color information, can pass through
To the method that the rgb value of pixel each in target image is averaged, the gray value of each pixel in target image is obtained, into
And count and obtain the grey level histogram of target image, grey level histogram is the function of gray level, it indicates there is certain in image
The number of the pixel of gray level, therefore, the number of grey levels for being included by the available target image of grey level histogram.For
The number of grey levels of bar code image is 2, is greater than 2 for the number of grey levels of facial image, therefore, is equal to the first preset threshold
For 2, when the number of grey levels of target image is equal to 2, determine that the image type of target image is bar code image；In target
When the number of grey levels of image is not equal to 2, determine that the image type of target image is facial image.
In third example, determine that the image type of target image includes:
Feature extraction is carried out to target image, obtains the image feature information of target image；
According to the image feature information of target image and pre-set image classification model, the image of target image is determined
Type.
In the embodiments of the present disclosure, image classification model is obtained according to training sample training, and training sample can be figure
Some or all of in the image crossed as handled by processing equipment, by machine learning, each training figure in training sample is obtained
The characteristic information of picture, and classified according to the characteristic information of each training image, and determine different classes of image type, it obtains
To image classification model.When needing to handle target image to be analyzed, the image feature information of target image is extracted,
It is matched with image classification model, determines the image type of target image.
103, it according to the image type of target image, is obtained from pre-set recognizer list and target image
The corresponding recognizer of image type.
In the embodiments of the present disclosure, recognizer list includes the corresponding relationship of image type with corresponding recognizer.
After determining the image type of target image, according to the corresponding relationship of image type and corresponding recognizer, mesh is determined
The corresponding recognizer of logo image.
104, according to the corresponding recognizer of the image type of target image, target image is identified.
In the embodiments of the present disclosure, when the image type of target image is facial image, according to face recognition algorithms pair
Target image is identified, face characteristic is obtained；When the image type of target image is graphic code image, calculated according to graphic code
Method identifies target image, obtains image code feature.Example is carried out by image in 2 D code of target image, by two dimension
The identification of code obtains content entrained in two dimensional code, as acquisition of information, website jump, advertisement pushing, mobile-phone payment, member
Management etc..
The image-recognizing method that the embodiment of the present disclosure provides, obtains target image to be analyzed；Determine the figure of target image
As type；According to the image type of target image, the image with target image is obtained from pre-set recognizer list
The corresponding recognizer of type；According to the corresponding recognizer of the image type of target image, target image is identified.It is logical
It crosses after analyzing the image type of the target image of acquisition, is identified, be can be realized using corresponding recognizer
Single image processing equipment handles different types of image, and solving existing single image processing equipment can only be to single class
The problem of image of type is handled.
Based on image-recognizing method described in the corresponding embodiment of above-mentioned Fig. 1, following is embodiment of the present disclosure,
It can be used for executing embodiments of the present disclosure.
The embodiment of the present disclosure provides a kind of pattern recognition device, as shown in Fig. 2, the pattern recognition device 20 includes: first
Obtain module 201, determining module 202, second obtains module 203 and identification module 204；
First obtains module 201, for obtaining target image to be analyzed；
Determining module 202, for determining that the image type of target image, image type include facial image or bar code figure
Picture, bar code image include bar code image and image in 2 D code；
Second obtains module 203, for the image type according to target image, from pre-set recognizer list
Obtain recognizer corresponding with the image type of target image；
Identification module 204 knows target image for the corresponding recognizer of image type according to target image
Not.
As shown in figure 3, determining module 202 includes: acquisition submodule 2021, judging submodule 2022 and determining submodule
2023。
In one embodiment, acquisition submodule 2021, for obtaining the number of colors of target image；
Judging submodule 2022, for judging whether the number of colors of target image is equal to the second preset threshold；
It determines submodule 2023, when being equal to the second preset threshold for the number of colors in target image, determines target figure
The image type of picture is bar code image；
It determines submodule 2023, when being not equal to the second preset threshold for the number of colors in target image, determines target
The image type of image is facial image.
In one embodiment, acquisition submodule 2021 is used for: obtaining the rgb value of each pixel in target image；Root
According to the rgb value of each pixel, the color of each pixel is determined；According to the color of each pixel, statistics obtains target figure
The number of colors of picture
In one embodiment, acquisition submodule 2021 obtain target figure for carrying out gray processing processing to target image
The number of grey levels of picture；
Judging submodule 2022, for judging whether the number of grey levels of target image is equal to the first preset threshold；
It determines submodule 2023, when being equal to the first preset threshold for the number of grey levels in target image, determines target
The image type of image is bar code image；
It determines submodule 2023, when being not equal to the first preset threshold for the number of grey levels in target image, determines mesh
The image type of logo image is facial image.
In one embodiment, acquisition submodule 2021 is used for: being carried out gray processing processing to target image, is obtained target figure
The gray value of each pixel as in；According to the gray value of each pixel, the grey level histogram of target image is counted；According to target figure
The grey level histogram of picture obtains the number of grey levels of target image.
In one embodiment, acquisition submodule 2021 obtain target image for carrying out feature extraction to target image
Image feature information；
Submodule 2023 is determined, for the image feature information and pre-set image classification mould according to target image
Type determines that the image type of target image, image classification model are obtained according to training sample training.
In one embodiment, identification module 204, for the image type in target image be facial image when, according to
Face recognition algorithms identify target image, obtain face characteristic；
Identification module 204, for the image type in target image be graphic code image when, according to graphic code algorithm to mesh
Logo image is identified, image code feature is obtained.
The pattern recognition device that the embodiment of the present disclosure provides, obtains target image to be analyzed；Determine the figure of target image
As type；According to the image type of target image, the image with target image is obtained from pre-set recognizer list
The corresponding recognizer of type；According to the corresponding recognizer of the image type of target image, target image is identified.It is logical
It crosses after analyzing the image type of the target image of acquisition, is identified, be can be realized using corresponding recognizer
Single image processing equipment handles different types of image, and solving existing single image processing equipment can only be to single class
The problem of image of type is handled.
Refering to what is shown in Fig. 4, the embodiment of the present disclosure additionally provides a kind of image recognition apparatus, which includes connecing
Receive device 401, transmitter 402, memory 403 and processor 404, the transmitter 402 and memory 403 respectively with processor 404
It connects, at least one computer instruction is stored in memory 403, processor 404 is for loading and executing at least one calculating
Machine instruction, to realize image-recognizing method described in the corresponding embodiment of above-mentioned Fig. 1.
Based on image-recognizing method described in the corresponding embodiment of above-mentioned Fig. 1, the embodiment of the present disclosure also provides one kind
Computer readable storage medium, for example, non-transitorycomputer readable storage medium can be read-only memory (English: Read
Only Memory, ROM), random access memory (English: Random Access Memory, RAM), CD-ROM, tape,
Floppy disk and optical data storage devices etc..At least one computer instruction is stored on the storage medium, for executing above-mentioned Fig. 1 pairs
Image-recognizing method described in the embodiment answered.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
Those skilled in the art will readily occur to its of the disclosure after considering specification and practicing disclosure disclosed herein
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
Claims (10)
1. a kind of image-recognizing method, which is characterized in that the method is applied to be provided with the image recognition of an acquisition module
Equipment, which comprises
Obtain target image to be analyzed；
Determine the image type of the target image, described image type includes facial image or bar code image, the bar code figure
As including bar code image and image in 2 D code；
According to the image type of the target image, obtained from pre-set recognizer list and the target image
The corresponding recognizer of image type；
According to the corresponding recognizer of the image type of the target image, the target image is identified.
2. the method according to claim 1, wherein the image type of the determination target image includes:
Obtain the number of colors of the target image；
Judge whether the number of colors of the target image is equal to the second preset threshold；
When the number of colors of the target image is equal to second preset threshold, the image type of the target image is determined
For bar code image；
When the number of colors of the target image is not equal to second preset threshold, the image class of the target image is determined
Type is facial image.
3. according to the method described in claim 2, it is characterized in that, the number of colors for obtaining the target image includes:
Obtain the rgb value of each pixel in the target image；
According to the rgb value of each pixel, the color of each pixel is determined；
According to the color of each pixel, statistics obtains the number of colors of the target image.
4. the method according to claim 1, wherein the graph style of the determination target image includes:
Gray processing processing is carried out to the target image, obtains the number of grey levels of target image；
Judge whether the number of grey levels of the target image is equal to the first preset threshold；
When the number of grey levels of the target image is equal to first preset threshold, the image class of the target image is determined
Type is bar code image；
When the number of grey levels of the target image is not equal to first preset threshold, the image of the target image is determined
Type is facial image.
5. according to the method described in claim 4, it is characterized in that, it is described to the target image carry out gray processing processing, obtain
The number of grey levels for taking target image includes:
Gray processing processing is carried out to the target image, obtains the gray value of each pixel in the target image；
According to the gray value of each pixel, the grey level histogram of the target image is counted；
According to the grey level histogram of the target image, the number of grey levels of the target image is obtained.
6. the method according to claim 1, wherein the image type of the determination target image includes:
Feature extraction is carried out to the target image, obtains the image feature information of the target image；
According to the image feature information of the target image and pre-set image classification model, the target image is determined
Image type, described image disaggregated model are obtained according to training sample training.
7. the method according to claim 1, wherein the image type according to the target image is corresponding
Recognizer, carrying out identification to the target image includes:
When the image type of the target image is facial image, the target image is known according to face recognition algorithms
Not, face characteristic is obtained；
When the image type of the target image is graphic code image, the target image is known according to graphic code algorithm
Not, image code feature is obtained.
8. a kind of pattern recognition device characterized by comprising
First obtains module, for obtaining target image to be analyzed；
Determining module, for determining the image type of the target image, described image type includes facial image or bar code figure
Picture, the bar code image include bar code image and image in 2 D code；
Second acquisition module is obtained from pre-set recognizer list for the image type according to the target image
Take recognizer corresponding with the image type of the target image；
Identification module carries out the target image for the corresponding recognizer of image type according to the target image
Identification.
9. a kind of image recognition apparatus, which is characterized in that described image identifies that equipment includes processor and memory, the storage
Be stored at least one computer instruction in device, described instruction loaded by the processor and executed with realize claim 1 to
Performed step in the described in any item image-recognizing methods of claim 7.
10. a kind of computer readable storage medium, which is characterized in that be stored at least one computer in the storage medium and refer to
It enables, described instruction is loaded by processor and executed to realize claim 1 to the described in any item image recognition sides of claim 7
Performed step in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910139045.XA CN109961015A (en) | 2019-02-25 | 2019-02-25 | Image-recognizing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910139045.XA CN109961015A (en) | 2019-02-25 | 2019-02-25 | Image-recognizing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109961015A true CN109961015A (en) | 2019-07-02 |
Family
ID=67023617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910139045.XA Pending CN109961015A (en) | 2019-02-25 | 2019-02-25 | Image-recognizing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961015A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021128966A1 (en) * | 2019-12-24 | 2021-07-01 | 同方威视技术股份有限公司 | Empty tray identification and apparatus therefor |
| WO2021127963A1 (en) * | 2019-12-24 | 2021-07-01 | Intel Corporation | Image content classification |
| WO2023207995A1 (en) * | 2022-04-26 | 2023-11-02 | Wuhan United Imaging Healthcare Co., Ltd. | Systems and methods for image analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932776A (en) * | 2018-07-11 | 2018-12-04 | 石数字技术成都有限公司 | A kind of two dimensional code access control system and operation method based on face characteristic value |
| CN109325333A (en) * | 2018-09-24 | 2019-02-12 | 刘兴丹 | A kind of method, apparatus that double identifications are logged in, paid |
-
2019
- 2019-02-25 CN CN201910139045.XA patent/CN109961015A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932776A (en) * | 2018-07-11 | 2018-12-04 | 石数字技术成都有限公司 | A kind of two dimensional code access control system and operation method based on face characteristic value |
| CN109325333A (en) * | 2018-09-24 | 2019-02-12 | 刘兴丹 | A kind of method, apparatus that double identifications are logged in, paid |
Non-Patent Citations (2)
| Title |
|---|
| 刘国华: "《HALCON数字图像处理》", 30 June 2018 * |
| 申时凯 等: "《物联网的技术开发与应用研究》", 31 October 2017 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021128966A1 (en) * | 2019-12-24 | 2021-07-01 | 同方威视技术股份有限公司 | Empty tray identification and apparatus therefor |
| WO2021127963A1 (en) * | 2019-12-24 | 2021-07-01 | Intel Corporation | Image content classification |
| WO2023207995A1 (en) * | 2022-04-26 | 2023-11-02 | Wuhan United Imaging Healthcare Co., Ltd. | Systems and methods for image analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103617432B (en) | A kind of scene recognition method and device | |
| US8675960B2 (en) | Detecting skin tone in images | |
| AU2011253980B2 (en) | Method, apparatus and system for identifying distracting elements in an image | |
| CN109961015A (en) | Image-recognizing method, device, equipment and storage medium | |
| CN106951869B (en) | A kind of living body verification method and equipment | |
| US8515164B2 (en) | Non-product image identification | |
| CN110287862B (en) | Anti-candid detection method based on deep learning | |
| CN107516102B (en) | Method, device and system for classifying image data and establishing classification model | |
| CN107506738A (en) | Feature extracting method, image-recognizing method, device and electronic equipment | |
| CN108961183A (en) | Image processing method, terminal device and computer readable storage medium | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| JP2010211498A (en) | Image processing program and image processing system | |
| CN112819017B (en) | High-precision color cast image identification method based on histogram | |
| WO2017034419A1 (en) | A process, system and apparatus for machine colour characterisation of digital media | |
| CN106815598B (en) | 360-degree panoramic picture identification method and device | |
| CN112989098A (en) | Automatic retrieval method and device for image infringement entity and electronic equipment | |
| CN111986155A (en) | Universal scene character recognition method and device | |
| CN112883762A (en) | Living body detection method, device, system and storage medium | |
| CN106402717B (en) | A kind of AR control method for playing back and intelligent desk lamp | |
| CN115546141A (en) | Small sample Mini LED defect detection method and system based on multi-dimensional measurement | |
| CN115240245A (en) | Face living body detection method, face living body detection device and electronic equipment | |
| CN111935480B (en) | Detection method for image acquisition device and related device | |
| US10146042B2 (en) | Image processing apparatus, storage medium, and image processing method | |
| CN103971111B (en) | Image processing method and terminal device | |
| Gibson et al. | A perceptual based contrast enhancement metric using AdaBoost |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190702 |
|
| RJ01 | Rejection of invention patent application after publication |