CN110503115A - A kind of color identification method, device, equipment and computer readable storage medium - Google Patents
A kind of color identification method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110503115A CN110503115A CN201910816577.2A CN201910816577A CN110503115A CN 110503115 A CN110503115 A CN 110503115A CN 201910816577 A CN201910816577 A CN 201910816577A CN 110503115 A CN110503115 A CN 110503115A
- Authority
- CN
- China
- Prior art keywords
- color
- colored pixels
- images
- recognized
- color identification
- 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of color identification methods, including images to be recognized is transformed into color space；Extract the colored pixels feature of multiple preset kinds of each component image in color space；Color identification is carried out to images to be recognized according to the colored pixels feature after Cluster-Fusion.It can be seen that, colored pixels feature can be used to the pixel distribution in perceptual image, due to having used the colored pixels feature of multiple preset kinds of each component image in color space in the present invention, the colored pixels feature of the individual type utilized in compared with the prior art, the color in images to be recognized can preferably be perceived, to strengthen color identification method in the anti-interference ability of complex environment, the accuracy that color identifies under complex environment is improved.The invention also discloses a kind of color identification device, equipment and computer readable storage mediums, have the identical beneficial effect of color identification method as above.
Description
Technical field
The present invention relates to colors to identify field, and more particularly to a kind of color identification method, the invention further relates to a kind of face
Color identification device, equipment and computer readable storage medium.
Background technique
Color identification has important application, such as guidance and the control field of robot in many fields, in the prior art
Color identification method can obtain higher accuracy rate under simple environment, but complex environment (such as uneven illumination it is even with
And background is complicated) under the accuracy rate that identifies of color it is poor.
Therefore, how to provide a kind of scheme of solution above-mentioned technical problem is that those skilled in the art need to solve at present
Problem.
Summary of the invention
The object of the present invention is to provide a kind of color identification methods, can preferably perceive the color in images to be recognized,
To strengthening color identification method in the anti-interference ability of complex environment, improve color under complex environment identify it is accurate
Property；It is a further object of the present invention to provide a kind of color identification device, equipment and computer readable storage mediums, can be preferably
The color in images to be recognized is perceived, to strengthen color identification method in the anti-interference ability of complex environment, is improved multiple
The accuracy that color identifies under heterocycle border.
In order to solve the above technical problems, the present invention provides a kind of color identification methods, comprising:
Images to be recognized is transformed into color space；
Extract the colored pixels feature of multiple preset kinds of each component image in the color space；
Cluster-Fusion is carried out to the colored pixels feature of the multiple preset kind；
The color of the images to be recognized is determined according to the colored pixels feature after Cluster-Fusion.
It is preferably, described that images to be recognized is transformed into color space specifically:
Images to be recognized is transformed into the face of normalized rgb color mode, tone saturation degree lightness HSV and YCBCR
In the colour space.
Preferably, the colored pixels feature of the multiple preset kind includes: mean value, standard deviation and entropy.
Preferably, the colored pixels feature according to after Cluster-Fusion carries out color identification specifically:
Under a variety of illumination conditions, using the colored pixels feature after Cluster-Fusion to radial basis function support to
Amount machine RBF-SVM is trained, and is obtained color and is judged data；
Judge that data carry out color identification to the data to be identified according to the color.
Preferably, the colored pixels feature to the multiple preset kind carries out Cluster-Fusion, comprising:
Cluster-Fusion is carried out by colored pixels feature of the fuzzy C-mean algorithm FCM algorithm to the multiple preset kind.
Preferably, it is described images to be recognized is transformed into color space before, the color identification method further include:
Original image is converted through RGB triple channel image to the hsv color space；
It selects to carry out based on the original image of the smooth space filtering to the tone channel in the hsv color space
Process of convolution；
The filtered original image is split using Global thresholding；
Using the original image after edge detection algorithm traversal segmentation, object edge characteristic information is obtained；
By spatial pyramid method, object in the original image is determined according to the object edge characteristic information
The position of body；
Using the image of the target object as images to be recognized.
In order to solve the above technical problems, the present invention also provides a kind of color identification devices, comprising:
Conversion module, for images to be recognized to be transformed into color space；
Extraction module, the colored pixels for extracting multiple preset kinds of each component image in the color space are special
Sign；
Fusion Module carries out Cluster-Fusion for the colored pixels feature to the multiple preset kind；
Identification module, for determining the color of the images to be recognized according to the colored pixels feature after Cluster-Fusion.
Preferably, the colored pixels feature of the multiple preset kind includes: mean value, standard deviation and entropy.
In order to solve the above technical problems, the present invention also provides a kind of color-identifying apparatus, comprising:
Memory, for storing computer program；
Processor, when for executing the computer program the step of realization any one as above color identification method.
In order to solve the above technical problems, the computer can the present invention also provides a kind of computer readable storage medium
It reads to be stored with computer program on storage medium, the as above any one face is realized when the computer program is executed by processor
The step of color recognition methods.
The present invention provides a kind of color identification methods, including images to be recognized is transformed into color space；Extract face
The colored pixels feature of multiple preset kinds of each component image in the colour space；It is special according to the colored pixels after Cluster-Fusion
Sign carries out color identification to images to be recognized.
As it can be seen that colored pixels feature can be used to the pixel distribution in perceptual image, due to having used face in the present invention
The colored pixels feature of multiple preset kinds of each component image in the colour space, compared with the prior art in utilize it is individual
The colored pixels feature of one type can preferably perceive the color in images to be recognized, to strengthen color identification side
Method improves the accuracy that color identifies under complex environment in the anti-interference ability of complex environment.
The present invention also provides a kind of color identification device, equipment and computer readable storage mediums, have color as above
The identical beneficial effect of recognition methods.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to institute in the prior art and embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of flow diagram of color identification method provided by the invention；
Fig. 2 is a kind of structural schematic diagram of color identification device provided by the invention；
Fig. 3 is a kind of structural schematic diagram of color-identifying apparatus provided by the invention.
Specific embodiment
Core of the invention is to provide a kind of color identification method, can preferably perceive the color in images to be recognized,
To strengthening color identification method in the anti-interference ability of complex environment, improve color under complex environment identify it is accurate
Property；Another core of the invention is to provide a kind of color identification device, equipment and computer readable storage medium, can be preferably
The color in images to be recognized is perceived, to strengthen color identification method in the anti-interference ability of complex environment, is improved multiple
The accuracy that color identifies under heterocycle border.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to FIG. 1, Fig. 1 is a kind of flow diagram of color identification method provided by the invention, comprising:
Step S1: images to be recognized is transformed into color space；
Specifically, since processor can not Direct Recognition images to be recognized this entirety, it is therefore desirable to by images to be recognized
The component image that can be identified is converted to, after images to be recognized is transformed into color space, can be convenient subsequent step pair
The component image to be identified being transformed into color space is handled, to carry out color identification.
Step S2: the colored pixels feature of multiple preset kinds of each component image in color space is extracted；
Specifically, having multiple component images in each color space, the colored pixels feature in each component image can
To characterize the distribution of the pixel in images to be recognized, the colored pixels feature extracted can be used for identifying the color in image.
Specifically, can be navigated to first in each component image color characteristic ROI (region of interest,
Area-of-interest), colored pixels feature is then extracted again.
Wherein, it is contemplated that carried out in the prior art only with the colored pixels feature of the independent type extracted
Color identification, and in the embodiment of the present invention, the color of multiple preset kinds of each component image in color space can be extracted
There are three component image in pixel characteristic, such as each color space, three default classes fixed in each component image are extracted
Colored pixels feature of type etc. carries out color identification convenient for subsequent step, and the embodiment of the present invention is it is not limited here.
Specifically, colored pixels feature, there are many kinds of class, different colored pixels features combines the work identified for color
With effect difference, the colored pixels feature of multiple preset kinds has been selected in the embodiment of the present invention, has been compared and an individual class
The colored pixels feature of type, can preferably characterize color, so that under complex environment, such as illumination deficiency or background
Preferably the color in images to be recognized can be identified under noisy equal environment.
Step S3: Cluster-Fusion is carried out to the colored pixels feature of multiple preset kinds；
Step S4: the color of images to be recognized is determined according to the colored pixels feature after Cluster-Fusion.
Specifically, Cluster-Fusion can merge multiple colored pixels features, after according to Cluster-Fusion
Colored pixels feature carries out color identification, wherein the colored pixels feature after Cluster-Fusion can be the form of multi-dimensional matrix.
The present invention provides a kind of color identification methods, including images to be recognized is transformed into color space；Extract face
The colored pixels feature of multiple preset kinds of each component image in the colour space；It is special according to the colored pixels after Cluster-Fusion
Sign carries out color identification to images to be recognized.
As it can be seen that colored pixels feature can be used to the pixel distribution in perceptual image, due to having used face in the present invention
The colored pixels feature of multiple preset kinds of each component image in the colour space, compared with the prior art in utilize it is individual
The colored pixels feature of one type can preferably perceive the color in images to be recognized, to strengthen color identification side
Method improves the accuracy that color identifies under complex environment in the anti-interference ability of complex environment.
On the basis of the above embodiments:
Embodiment as one preferred, images to be recognized is transformed into color space specifically:
Images to be recognized is transformed into the face of normalized rgb color mode, tone saturation degree lightness HSV and YCBCR
In the colour space.
Specifically, color space may include normalized rgb color mode, HSV ((Hue Saturation Value,
Tone saturation degree lightness) and YCBCR, various color space color can be improved due to covering different types of angle
The accuracy of identification.
Wherein, naturally it is also possible to only select any two kinds in above-mentioned three kinds of color spaces, the embodiment of the present invention is herein not
It limits.
Wherein, original image can do normalized in rgb color mode first, it is possible to reduce uniformity illumination pair
The influence of image.
Embodiment as one preferred, the colored pixels feature of multiple preset kinds include: mean value, standard deviation and entropy
Value.
Specifically, the research work of personnel after study, determines mean value, standard deviation and entropy for the pixel of image
Distributed point have preferably characterize effect, therefore the preset kind in the embodiment of the present invention be mean value, standard deviation and entropy, can
To improve the accuracy of color identification.
Certainly, other than the preset kind provided in the embodiment of the present invention, preset kind can also be other multiple types,
The embodiment of the present invention is it is not limited here.
It is specific to carry out color identification according to the colored pixels feature after Cluster-Fusion for embodiment as one preferred
Are as follows:
Under a variety of illumination conditions, using the colored pixels feature after Cluster-Fusion to radial basis function support vector machines
RBF-SVM is trained, and is obtained color and is judged data；
Judge that data carry out color identification to data to be identified according to color.
Specifically, using after Cluster-Fusion colored pixels feature carry out color identification specific steps can with it is existing
It is identical in technology, using the colored pixels feature after Cluster-Fusion to RBF (Radial basis under a variety of illumination conditions
Function, radial basis function) SVM (Support Vector Machine, support vector machines) is trained, and it can be further
Improve the color recognition capability under complex illumination environment, wherein the data that training obtains later can carry out color identification.
Specifically, each image may switch to the hsv color based on human vision after color identification mission starts
Identification operation is carried out in space.
Wherein it is possible to which the colored pixels feature after Cluster-Fusion is mapped it from lower dimensional space by nonlinear function
To higher dimensional space, to can effectively be carried out curve fitting and data classification in study.
Embodiment as one preferred carries out Cluster-Fusion to the colored pixels feature of multiple preset kinds, comprising:
Cluster-Fusion is carried out by colored pixels feature of the fuzzy C-mean algorithm FCM algorithm to multiple preset kinds.
Specifically, FCM (Fuzzy CognitiveMap, Fuzzy C-Means Cluster Algorithm) has speed fast and stability
The advantages that strong.
Certainly, other than FCM, Cluster-Fusion can also be carried out using other kinds of algorithm, the embodiment of the present invention is herein
Without limitation.
Embodiment as one preferred, before images to be recognized is transformed into color space, the color identification method
Further include:
Original image is converted through RGB triple channel image to hsv color space；
It selects to carry out at convolution based on original image of the smooth space filtering to the tone channel in hsv color space
Reason；
Filtered original image is split using Global thresholding；
Using the original image after edge detection algorithm traversal segmentation, object edge characteristic information is obtained；
By spatial pyramid method, the position of target object in original image is determined according to object edge characteristic information
It sets；
Using the image of target object as images to be recognized.
Specifically, images to be recognized is likely to one in only original image before identifying to images to be recognized
Fraction, it is also necessary to determine images to be recognized from original image in advance, turn in the embodiment of the present invention by images to be recognized
Before changing in color space, images to be recognized can be determined, provide the method that images to be recognized is determined in automation.
Wherein, (the selection mark of threshold value can be first split for filtered original image in the embodiment of the present invention
Will definitely be based on ideal bimodal hypothesis), on the basis of the original image after then dividing again using Canny edge detection algorithm into
Row traversal, conveniently obtains the edge feature information of object, it can be understood as the profile of object finally recycles spatial pyramid side
Method can determine the position of target object in original image according to object edge characteristic information, thus just define to
Identify image.
Specifically, by edge feature information input into spatial pyramid structure, shape template is created with this；It is creating
Shape template in, define the pyramid grade of template, every layer of pyramid includes a certain number of aspect of model, feature quantity
It is reduced with the reduction of pyramid grade, it is special that pyramid higher ranked model can be gradually matched during template matching
Sign.The matching of shape template is traversed in the picture using the method based on invariant moment features, and is existed according to pyramid grade
Gradually matched in image, during traversal can with the rotation of Definition Model, scaling etc. attributes, finally find in the picture
The position of object simultaneously returns with a matrix type.
Specifically, edge detection algorithm is carried out to the original image after over-segmentation in the embodiment of the present invention, it can be thinner
The edge feature information in ground traversal image is caused, to be easier to be accurately obtained images to be recognized.
In order to solve the above technical problems, the present invention also provides a kind of color identification devices, comprising:
Conversion module 1, for images to be recognized to be transformed into color space；
Extraction module 2, for extracting the colored pixels feature of multiple preset kinds of each component image in color space；
Fusion Module 3 carries out Cluster-Fusion for the colored pixels feature to multiple preset kinds；
Identification module 4, for determining the color of images to be recognized according to the colored pixels feature after Cluster-Fusion.
Embodiment as one preferred, the colored pixels feature of multiple preset kinds include: mean value, standard deviation and entropy
Value.
The reality of color identification method above-mentioned is please referred to for the introduction of color identification device provided in an embodiment of the present invention
Example is applied, details are not described herein for the embodiment of the present invention.
In order to solve the above technical problems, the present invention also provides a kind of color-identifying apparatus, comprising:
Memory 5, for storing computer program；
Processor 6, when for executing computer program realize as above any one of color identification method the step of.
The reality of color identification method above-mentioned is please referred to for the introduction of color-identifying apparatus provided in an embodiment of the present invention
Example is applied, details are not described herein for the embodiment of the present invention.
In order to solve the above technical problems, the present invention also provides a kind of computer readable storage medium, it is computer-readable to deposit
It is stored with computer program on storage media, color identification method any one of as above is realized when computer program is executed by processor
Step.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.It should also be noted that, in the present specification, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of color identification method characterized by comprising
Images to be recognized is transformed into color space；
Extract the colored pixels feature of multiple preset kinds of each component image in the color space；
Cluster-Fusion is carried out to the colored pixels feature of the multiple preset kind；
The color of the images to be recognized is determined according to the colored pixels feature after Cluster-Fusion.
2. color identification method according to claim 1, which is characterized in that described that images to be recognized is transformed into color sky
Between in, comprising:
It is empty that images to be recognized is transformed into normalized rgb color mode, the color of tone saturation degree lightness HSV and YCBCR
Between in.
3. color identification method according to claim 2, which is characterized in that the colored pixels of the multiple preset kind are special
Sign includes: mean value, standard deviation and entropy.
4. color identification method according to claim 3, which is characterized in that the face according to after Cluster-Fusion
Color pixel feature carries out color identification specifically:
Under a variety of illumination conditions, using the colored pixels feature after Cluster-Fusion to radial basis function support vector machines
RBF-SVM is trained, and is obtained color and is judged data；
Judge that data carry out color identification to the data to be identified according to the color.
5. color identification method according to claim 1, which is characterized in that the color to the multiple preset kind
Pixel characteristic carries out Cluster-Fusion, comprising:
Cluster-Fusion is carried out by colored pixels feature of the fuzzy C-mean algorithm FCM algorithm to the multiple preset kind.
6. color identification method according to any one of claims 1 to 5, which is characterized in that described to turn images to be recognized
Before changing in color space, the color identification method further include:
Original image is converted through RGB triple channel image to the hsv color space；
It selects to carry out convolution based on the original image of the smooth space filtering to the tone channel in the hsv color space
Processing；
The filtered original image is split using Global thresholding；
Using the original image after edge detection algorithm traversal segmentation, object edge characteristic information is obtained；
By spatial pyramid method, target object in the original image is determined according to the object edge characteristic information
Position；
Using the image of the target object as images to be recognized.
7. a kind of color identification device characterized by comprising
Conversion module, for images to be recognized to be transformed into color space；
Extraction module, for extracting the colored pixels feature of multiple preset kinds of each component image in the color space；
Fusion Module carries out Cluster-Fusion for the colored pixels feature to the multiple preset kind；
Identification module, for determining the color of the images to be recognized according to the colored pixels feature after Cluster-Fusion.
8. color identification method according to claim 7, which is characterized in that the colored pixels of the multiple preset kind are special
Sign includes: mean value, standard deviation and entropy.
9. a kind of color-identifying apparatus characterized by comprising
Memory, for storing computer program；
Processor, realizing the color identification method as described in any one of claim 1 to 6 when for executing the computer program
Step.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the step of the color identification method as described in any one of claim 1 to 6 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910816577.2A CN110503115A (en) | 2019-08-30 | 2019-08-30 | A kind of color identification method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910816577.2A CN110503115A (en) | 2019-08-30 | 2019-08-30 | A kind of color identification method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110503115A true CN110503115A (en) | 2019-11-26 |
Family
ID=68590771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910816577.2A Pending CN110503115A (en) | 2019-08-30 | 2019-08-30 | A kind of color identification method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110503115A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145172A (en) * | 2019-12-31 | 2020-05-12 | 广东溢达纺织有限公司 | Method, device and system for determining distribution cycle data and computer equipment |
| CN111898616A (en) * | 2020-06-28 | 2020-11-06 | 北京配天技术有限公司 | Color recognition method, device and storage device |
| CN112241714A (en) * | 2020-10-22 | 2021-01-19 | 北京字跳网络技术有限公司 | Method and device for identifying designated area in image, readable medium and electronic equipment |
| WO2021212977A1 (en) * | 2020-04-24 | 2021-10-28 | 京东方科技集团股份有限公司 | Image color filtering method and apparatus, electronic device, and storage medium |
| WO2024103892A1 (en) * | 2022-11-17 | 2024-05-23 | 博奥生物集团有限公司 | Color recognition method and apparatus for cupping mark image |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034872A (en) * | 2012-12-26 | 2013-04-10 | 四川农业大学 | Farmland pest recognition method based on colors and fuzzy clustering algorithm |
| CN103996041A (en) * | 2014-05-15 | 2014-08-20 | 武汉睿智视讯科技有限公司 | Vehicle color identification method and system based on matching |
| CN104778707A (en) * | 2015-04-22 | 2015-07-15 | 福州大学 | Electrolytic capacitor detecting method for improving general Hough transform |
-
2019
- 2019-08-30 CN CN201910816577.2A patent/CN110503115A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034872A (en) * | 2012-12-26 | 2013-04-10 | 四川农业大学 | Farmland pest recognition method based on colors and fuzzy clustering algorithm |
| CN103996041A (en) * | 2014-05-15 | 2014-08-20 | 武汉睿智视讯科技有限公司 | Vehicle color identification method and system based on matching |
| CN104778707A (en) * | 2015-04-22 | 2015-07-15 | 福州大学 | Electrolytic capacitor detecting method for improving general Hough transform |
Non-Patent Citations (1)
| Title |
|---|
| 许庆勇等: "《基于深度学习理论的纹身图像识别与检测研究》", 31 December 2018 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145172A (en) * | 2019-12-31 | 2020-05-12 | 广东溢达纺织有限公司 | Method, device and system for determining distribution cycle data and computer equipment |
| CN111145172B (en) * | 2019-12-31 | 2023-04-18 | 广东溢达纺织有限公司 | Method, device and system for determining distribution cycle data and computer equipment |
| WO2021212977A1 (en) * | 2020-04-24 | 2021-10-28 | 京东方科技集团股份有限公司 | Image color filtering method and apparatus, electronic device, and storage medium |
| US11830107B2 (en) | 2020-04-24 | 2023-11-28 | Boe Technology Group Co., Ltd. | Method and apparatus for filtering image colors, electronic device and storage medium |
| CN111898616A (en) * | 2020-06-28 | 2020-11-06 | 北京配天技术有限公司 | Color recognition method, device and storage device |
| CN112241714A (en) * | 2020-10-22 | 2021-01-19 | 北京字跳网络技术有限公司 | Method and device for identifying designated area in image, readable medium and electronic equipment |
| CN112241714B (en) * | 2020-10-22 | 2024-04-26 | 北京字跳网络技术有限公司 | Method and device for identifying designated area in image, readable medium and electronic equipment |
| WO2024103892A1 (en) * | 2022-11-17 | 2024-05-23 | 博奥生物集团有限公司 | Color recognition method and apparatus for cupping mark image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110503115A (en) | A kind of color identification method, device, equipment and computer readable storage medium | |
| US11410277B2 (en) | Method and device for blurring image background, storage medium and electronic apparatus | |
| US8411986B2 (en) | Systems and methods for segmenation by removal of monochromatic background with limitied intensity variations | |
| Mishra et al. | Active segmentation with fixation | |
| Scharstein | Matching images by comparing their gradient fields | |
| US8411932B2 (en) | Example-based two-dimensional to three-dimensional image conversion method, computer readable medium therefor, and system | |
| Gomes et al. | Efficient 3D object recognition using foveated point clouds | |
| US9401027B2 (en) | Method and apparatus for scene segmentation from focal stack images | |
| CN108510491A (en) | Blur the filter method of skeleton critical point detection result under background | |
| CA3032983A1 (en) | Systems and methods for keypoint detection | |
| CN112883881B (en) | Unordered sorting method and unordered sorting device for strip-shaped agricultural products | |
| CN109934838A (en) | A kind of picture semantic segmentation mask method and device based on super-pixel | |
| CN109829463A (en) | A kind of nail recognition methods, device, nail beauty machine and storage medium | |
| CN109919149A (en) | Object mask method and relevant device based on object detection model | |
| CN110188640B (en) | Face recognition method, face recognition device, server and computer readable medium | |
| CN108805838A (en) | A kind of image processing method, mobile terminal and computer readable storage medium | |
| CN109117837A (en) | Area-of-interest determines method and apparatus | |
| CN111161219B (en) | Robust monocular vision SLAM method suitable for shadow environment | |
| CN109785367B (en) | Method and device for filtering foreign points in three-dimensional model tracking | |
| US20170274285A1 (en) | Method and apparatus for automating the creation of a puzzle pix playable on a computational device from a photograph or drawing | |
| Khan et al. | Segmentation of single and overlapping leaves by extracting appropriate contours | |
| CN114596213A (en) | Image processing method and device | |
| CN116569207A (en) | Method and electronic device for managing artifacts of images | |
| Greco et al. | Saliency based aesthetic cut of digital images | |
| Liu et al. | Detection of geometric shape for traffic lane and mark |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191126 |