CN108921838A - Method and apparatus for detection image - Google Patents
Method and apparatus for detection image Download PDFInfo
- Publication number
- CN108921838A CN108921838A CN201810694004.2A CN201810694004A CN108921838A CN 108921838 A CN108921838 A CN 108921838A CN 201810694004 A CN201810694004 A CN 201810694004A CN 108921838 A CN108921838 A CN 108921838A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- detected
- rectangular region
- rectangular
- 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
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for detection image.One specific embodiment of this method includes:Obtain image to be detected;Color value based on the pixel that image to be detected includes determines object pixel from the pixel that image to be detected includes;At least two rectangular region images are extracted from image to be detected;For the rectangular region image at least two rectangular region images, determine the quantity for the object pixel that the rectangular region image includes, in response to determining that identified quantity is greater than preset first amount threshold, determine that the rectangular region image is target rectangle area image;It determines that the quantity of target rectangle area image, and the quantity in response to determining target rectangle area image are greater than preset second amount threshold, determines that image to be detected is target image.This embodiment improves the efficiency of image detection, enrich the means of image detection.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus for detection image.
Background technique
Currently, needing to audit it for a large amount of picture occurred on network, to pick out qualified figure
Piece.For example, to will appear unintelligible, person's handwriting discontinuous and other issues for certain black and white sketch images, it usually needs manually screened
Out.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for detection image.
In a first aspect, the embodiment of the present application provides a kind of method for detection image, this method includes:It obtains to be checked
Altimetric image;Color value based on the pixel that image to be detected includes determines target picture from the pixel that image to be detected includes
Element;At least two rectangular region images are extracted from image to be detected;For the rectangle region at least two rectangular region images
Area image determines the quantity for the object pixel that the rectangular region image includes, in response to determining that it is default that identified quantity is greater than
The first amount threshold, determine the rectangular region image be target rectangle area image;Determine the number of target rectangle area image
Amount, and the quantity in response to determining target rectangle area image are greater than preset second amount threshold, determine image to be detected
For target image.
In some embodiments, the color value for the pixel for including based on image to be detected, the picture for including from image to be detected
In element, object pixel is determined, including:The pixel in pixel for including for image to be detected, determines the color value of the pixel
Mean value, and determine the maximum color value of the pixel and the difference of minimum color value;Based on identified color value, mean value and difference
Value, from the pixel that image to be detected includes, determines object pixel.
In some embodiments, based on identified color value, mean value and difference, the pixel for including from image to be detected
In, determine object pixel, including:The pixel in pixel for including for image to be detected, color value, mean value based on the pixel
And difference, determine whether the pixel is gray pixels;In response to determining that the pixel is gray pixels, and the color value of the pixel
Mean value is greater than preset mean value threshold value, determines that the pixel is object pixel.
In some embodiments, at least two rectangular region images are extracted from image to be detected, including:Determine that rectangle is sliding
From image to be detected, it is sliding successively to extract rectangle according to the mobile rectangular slide window of preset sliding step for the size of dynamic window
The region of dynamic window covering, is determined as rectangular region image for extracted region, wherein sliding step is sliding for characterizing rectangle
The distance that dynamic window moves every time.
In some embodiments, for the rectangular region image at least two rectangular region images, the rectangle is determined
The quantity for the object pixel that area image includes, in response to determining that identified quantity is greater than preset first amount threshold, really
Before the fixed rectangular region image is target rectangle area image, this method further includes:For the pixel in image to be detected, really
Determine the quantity for the object pixel that in image to be detected, the pixel correspondence rectangular area includes, wherein the pixel is located at the picture
At the Corner of the correspondence rectangular area of element, the pixel at corresponding rectangular area, Corner angle steel joint is to be detected
Pixel at the origin of image.
In some embodiments, the quantity for the object pixel that the rectangular region image includes is determined, including:Based on the rectangle
Position of the pixel in image to be detected in area image and the correspondence rectangular area of the pixel in image to be detected include
Object pixel quantity, determine the quantity for the object pixel that the rectangular region image includes.
In some embodiments, image to be detected obtains as follows:From preset image collection, length is chosen
Greater than preset length threshold, and width is greater than the image of preset width threshold value as image to be detected.
Second aspect, the embodiment of the present application provide a kind of device for detection image, which includes:It obtains single
Member is configured to obtain image to be detected;First determination unit is configured to the color for the pixel for including based on image to be detected
Value, from the pixel that image to be detected includes, determines object pixel;Extraction unit is configured to extract from image to be detected
At least two rectangular region images;Second determination unit is configured to for the rectangle region at least two rectangular region images
Area image determines the quantity for the object pixel that the rectangular region image includes, in response to determining that it is default that identified quantity is greater than
The first amount threshold, determine the rectangular region image be target rectangle area image;Third determination unit, is configured to determine
The quantity of target rectangle area image, and the quantity in response to determining target rectangle area image are greater than preset second quantity
Threshold value determines that image to be detected is target image.
In some embodiments, the first determination unit includes:First determining module is configured to for image to be detected packet
The pixel in pixel included determines the mean value of the color value of the pixel, and determines the maximum color value and minimum face of the pixel
The difference of color value;Second determining module is configured to based on identified color value, mean value and difference, from image to be detected packet
In the pixel included, object pixel is determined.
In some embodiments, the second determining module is further configured to:In the pixel for including for image to be detected
Pixel, color value, mean value and difference based on the pixel determine whether the pixel is gray pixels;In response to determining the picture
Element is gray pixels, and the mean value of the color value of the pixel is greater than preset mean value threshold value, determines that the pixel is object pixel.
In some embodiments, extraction unit is further configured to:The size for determining rectangular slide window, according to default
The mobile rectangular slide window of sliding step the region of rectangular slide window covering is successively extracted, by institute from image to be detected
The region of extraction is determined as rectangular region image, wherein sliding step is for characterizing the distance that rectangular slide window moves every time.
In some embodiments, which further includes:4th determination unit is configured to for the picture in image to be detected
Element determines the quantity for the object pixel that in image to be detected, the pixel correspondence rectangular area includes, wherein the pixel position
At the Corner of the correspondence rectangular area of the pixel, the pixel at corresponding rectangular area, Corner angle steel joint is
Pixel at the origin of image to be detected.
In some embodiments, the second determination unit is further configured to:For at least two rectangular region images
Rectangular region image, based on position of the pixel in the rectangular region image in image to be detected and image to be detected
In pixel the correspondence rectangular area object pixel that includes quantity, determine the object pixel that the rectangular region image includes
Quantity determines that the rectangular region image is target square in response to determining that identified quantity is greater than preset first amount threshold
Shape area image.
In some embodiments, image to be detected obtains as follows:From preset image collection, length is chosen
Greater than preset length threshold, and width is greater than the image of preset width threshold value as image to be detected.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, which includes:One or more processing
Device;Storage device is stored thereon with one or more programs;When one or more programs are executed by one or more processors,
So that one or more processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method as described in implementation any in first aspect is realized when computer program is executed by processor.
Method and apparatus provided by the embodiments of the present application for detection image, by being extracted at least from image to be detected
Two rectangular region images count the quantity for the object pixel that rectangular region image includes to determine target rectangle area
Area image, then the quantity in target rectangle region is counted, so that it is determined that whether image to be detected is target image, improve
The efficiency of image detection enriches the means of image detection.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein;
Fig. 2 is the flow chart according to one embodiment of the method for detection image of the application;
Fig. 3 is the schematic diagram according to an application scenarios of the method for detection image of the application;
Fig. 4 is the flow chart according to another embodiment of the method for detection image of the application;
Fig. 5 is the illustrative diagram according to the correspondence rectangular area of the method for detection image of the application;
Fig. 6 is the object pixel for including according to the calculating rectangular region image of the method for detection image of the application
Illustrative diagram;
Fig. 7 is the structural schematic diagram according to one embodiment of the device for detection image of the application;
Fig. 8 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can the method for detection image using the embodiment of the present application or the device for detection image
Exemplary system architecture 100.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as image processing class is answered on terminal device 101,102,103
With, web browser applications, instant messaging tools, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be the various electronic equipments with display screen, including but not limited to smart phone, tablet computer, e-book reading
(Moving Picture Experts Group Audio Layer III, dynamic image expert compress mark for device, MP3 player
Quasi- audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression
Standard audio level 4) player, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is
When software, it may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or software module (such as with
To provide the software or software module of Distributed Services), single software or software module also may be implemented into.It does not do herein specific
It limits.
Server 105 can be to provide the server of various services, for example, to terminal device 101,102,103 upload to
The backstage image detection server that detection image is detected.Backstage image detection server can be to the mapping to be checked received
As (such as determining whether image to be detected is target image) detected, testing result is obtained.
It should be noted that the method provided by the embodiment of the present application for detection image can be held by server 105
Row, can also be executed, correspondingly, the device for detection image can be set in server by terminal device 101,102,103
In 105, also it can be set in terminal device 101,102,103.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing the software of Distributed Services or software module), also may be implemented
At single software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the process of one embodiment of the method for detection image according to the application is shown
200.This is used for the method for detection image, includes the following steps:
Step 201, image to be detected is obtained.
In the present embodiment, for the executing subject of the method for detection image, (such as server shown in FIG. 1 or terminal are set
It is standby) it can be by wired connection mode or radio connection from long-range or from local obtain image to be detected.Wherein, to be checked
Altimetric image can be the image in some image collection.As an example, the image in certain image collection is believed with corresponding label
Breath, and each label information is same or similar (such as label is " pencil drawing ", " sketch images ", " simple picture " etc.), the image set
Image in conjunction needs to be detected, then the image in the image collection is image to be detected.
In some optional implementations of the present embodiment, image to be detected can obtain as follows:From pre-
If image collection in, choose length be greater than preset length threshold, and width be greater than preset width threshold value image conduct
Image to be detected.As an example, preset image collection can be the collection that the label for the image for including is the image of " pencil drawing "
It closes, in order to improve the accuracy of image detection, in the image collection, length is greater than length threshold and width is greater than width threshold
The image of value is determined as image to be detected.It optionally, can also length and width to image to be detected in order to improve detection speed
The upper limit is respectively set in degree.In practice, the thumbnail of certain image can be determined as image to be detected.
Step 202, the color value for the pixel for including based on image to be detected, from the pixel that image to be detected includes, really
Set the goal pixel.
In the present embodiment, based on the image to be detected obtained in step 201, above-mentioned executing subject can be based on to be detected
The color value for the pixel that image includes determines object pixel from the pixel that image to be detected includes.Specifically, above-mentioned execution
Main body can determine object pixel according to various methods from the pixel that image to be detected includes.As an example, above-mentioned execution master
Body can be from the pixel that image to be detected includes, and the pixel for selecting color value to be in preset range is as object pixel.Example
Such as, color value may include R (red, Red) value, G (green, Green) value, B (blue, Blue) value, can be by R value, G value, B
Value is in preset range the pixel of (such as 0-100) as object pixel.
In some optional implementations of the present embodiment, above-mentioned executing subject can in accordance with the following steps, to be checked
In the pixel that altimetric image includes, object pixel is determined:
The pixel in pixel for including firstly, for image to be detected determines the mean value of the color value of the pixel, and really
The difference of the maximum color value of the fixed pixel and minimum color value.As an example, the color value of pixel may include R value, G value, B
Value, above-mentioned executing subject can determine the R value, G value, B value of each pixel that image to be detected includes, calculate each pixel
R value, G value, the mean value of B value, and determine the maximum difference between the R value, G value, B value three of each pixel.For example, certain pixel
R value, G value, B value be respectively 137,120,128, then the maximum color value of the pixel is 137, and minimum color value is 120, then should
The maximum color value of pixel and the difference of minimum color value are 137-120=17, and the mean value of the color value of the pixel is (137+
120+128)/3。
Then, target is determined from the pixel that image to be detected includes based on identified color value, mean value and difference
Pixel.As an example, for each pixel that detection image includes, above-mentioned executing subject can determine whether the pixel meets
One preset condition and the second preset condition, wherein the first preset condition can be:The maximum color value of the pixel and minimum color
The difference of value is in preset first difference range;Second preset condition can be:Each color value of the pixel respectively with
The difference of the mean value of the color value of the pixel is in preset second difference range.If the pixel meets the first preset condition
Or second preset condition, then it can determine that the pixel is nearly scoriaceous pixel, otherwise, which is approximate colored pixel.
In practice, in above-mentioned second preset condition, corresponding second difference range of each color value be may be the same or different.
For example, it is assumed that image to be detected is the photo of pencil drawing, when usually taking pictures to pencil drawing, captured obtained photo can be general
It is yellow or general red, therefore, corresponding second difference range of R value can be set greater than to the corresponding second difference model of other color values
It encloses, so as to improve the accuracy of image detection.
Based on above-mentioned first preset condition and the second preset condition, above-mentioned executing subject can determine whether the pixel is mesh
Mark pixel.Such as the pixel meets the first preset condition and the second preset condition simultaneously, then the pixel is object pixel (grey picture
Element);Alternatively, the pixel is unsatisfactory for the first preset condition and the second preset condition simultaneously, then the pixel is object pixel (color images
Element).By the embodiment, the flexibility and accuracy that object pixel is extracted from image to be detected can be improved.
It is above-mentioned to hold based on identified color value, mean value and difference in some optional implementations of the present embodiment
Row main body can determine object pixel in accordance with the following steps from the pixel that image to be detected includes:
The pixel in pixel for including for image to be detected, above-mentioned executing subject can be primarily based on the color of the pixel
Value, mean value and difference, determine whether the pixel is gray pixels.The citing for continuing above embodiment, if the pixel is simultaneously
Meet the first preset condition and the second preset condition, it is determined that the pixel is gray pixels.Then, above-mentioned executing subject can be rung
It should be in determining that the pixel is gray pixels, and the mean value of the color value of the pixel is greater than preset mean value threshold value, determines the pixel
For object pixel.In general, color value includes R value, G value, B value, and R value, G value, the mean value of B value are bigger, then closer to white.For
Detect that mean value can be greater than the picture of preset mean value threshold value by partially white pixel, above-mentioned executing subject from image to be detected
Element is determined as object pixel (i.e. inclined white pixel).It by present embodiment, may be implemented from image to be detected, more accurately, fastly
Object pixel is determined fastly, to help to improve the efficiency and accuracy of image detection.
Step 203, at least two rectangular region images are extracted from image to be detected.
In the present embodiment, above-mentioned executing subject can extract at least two rectangular region images from image to be detected.
Specifically, above-mentioned executing subject can extract rectangular region image according to various methods from image to be detected.For example, above-mentioned hold
Row main body can be according to the preset each coordinate range of technical staff, by the corresponding figure of each coordinate range from image to be detected
As extracting as rectangular region image.
Step 204, for the rectangular region image at least two rectangular region images, the rectangular region image packet is determined
The quantity of the object pixel included determines the rectangle region in response to determining that identified quantity is greater than preset first amount threshold
Area image is target rectangle area image.
In the present embodiment, for the rectangular region image at least two rectangular region images that are extracted in step 203,
Above-mentioned executing subject can determine the quantity for the object pixel that the rectangular region image includes first.Then, in response to determining institute
Determining quantity is greater than preset first amount threshold, determines that the rectangular region image is target rectangle area image.As showing
Example, it is assumed that object pixel is the partially white gray pixels of color, then the integral color of target rectangle area image is partially greyish white.It needs
Illustrate, the first amount threshold can be the specific quantitative value of technical staff's setting, be also possible to above-mentioned executing subject root
The numerical value being calculated according to the percentage that technical staff is arranged.In general, above-mentioned executing subject can determine often according to various methods
The quantity for the object pixel that a rectangular region image includes.For example, above-mentioned executing subject can successively count each rectangular area
The quantity for the object pixel that image includes.
Step 205, the quantity of target rectangle area image, and the number in response to determining target rectangle area image are determined
Amount is greater than preset second amount threshold, determines that image to be detected is target image.
In the present embodiment, the target rectangle area image determined based on step 204, above-mentioned executing subject can first really
Set the goal the quantity of rectangular region image.It is counted then in response to the quantity for determining target rectangle area image greater than preset second
Threshold value is measured, determines that image to be detected is target image.
In practice, target image can be the image of poor quality.Surveying image to be detected is usually pencil drawing or black and white element
The image for the types such as drawing, in order to detect the quality of image to be detected, it is thus necessary to determine that the partially white region of color in image to be detected
Number, if partially white region is excessive, illustrate that the lines in image to be detected are unintelligible, discontinuous, image to be detected
Poor quality.As an example it is supposed that the first amount threshold is the 88% of the quantity for the pixel that rectangular region image includes, the second number
The 70% of the sum that threshold value is rectangular region image is measured, then if the quantity for the target rectangle area image that image to be detected includes
Greater than above-mentioned second amount threshold, then image to be detected is target image.Optionally, above-mentioned electronic equipment can determine it is to be checked
Altimetric image be target image after, output characterization image to be detected be target image information (such as " image be poor quality scheme
Picture ").
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for detection image of the present embodiment
Figure.In the application scenarios of Fig. 3, terminal device 301 uploads a width hand-drawing image 303 first, and server 302 obtains the Freehandhand-drawing
Image is as image to be detected.Then, the color value for each pixel that server includes based on image to be detected, from mapping to be checked
In the pixel that picture includes, determine that color is grey and partially white pixel is object pixel.Then, server is pre- according to technical staff
The image coordinate first set extracts multiple rectangular region images 304 with overlapping region from image to be detected, wherein
The size of each rectangular region image is w1*h1, wherein w1 is the length of rectangular region image, and h1 is rectangular region image
Width.Subsequently, server determines the quantity for the object pixel that each rectangular region image includes, the object pixel that will include
The rectangular region image that quantity is greater than preset first amount threshold 305 (such as w1*h1*88%) is determined as target rectangle region
Image 306.Finally, server 302 determines that the quantity of target rectangle area image is greater than preset second amount threshold, 307 (N*
70%, wherein N is the sum of rectangular region image), determine that image to be detected is target image (i.e. Poor Image), and output
Characterize the information 308 that image to be detected is target image.
The method provided by the above embodiment of the application, by extracting at least two rectangular area figures from image to be detected
Picture counts the quantity for the object pixel that rectangular region image includes to determine target rectangle area image, then to mesh
The quantity of mark rectangular area is counted, so that it is determined that whether image to be detected is target image, improves the effect of image detection
Rate enriches the means of image detection.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for detection image.The use
In the process 400 of the method for detection image, include the following steps:
Step 401, image to be detected is obtained.
In the present embodiment, step 401 and the step 201 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 402, the color value for the pixel for including based on image to be detected, from the pixel that image to be detected includes, really
Set the goal pixel.
In the present embodiment, step 402 and the step 202 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 403, the size for determining rectangular slide window moves rectangular slide window according to preset sliding step, from
In image to be detected, the region of rectangular slide window covering is successively extracted, extracted region is determined as rectangular region image.
In this embodiment, for the executing subject of the method for detection image, (such as server shown in FIG. 1 or terminal are set
It is standby) size that can determine rectangular slide window, according to the mobile rectangular slide window of preset sliding step, from image to be detected
In, the region of rectangular slide window covering is successively extracted, extracted region is determined as rectangular region image.Wherein, it slides
Step-length is for characterizing the distance that rectangular slide window moves every time.As an example it is supposed that the size of rectangular slide window is w1*
H1, the size of image to be detected are w2*h2, sliding step 1, by the pixel in image to be detected upper left corner be determined as origin (1,
1), then start the distance for successively sliding 1 pixel to the right from the rectangular area the coordinate of image to be detected (1,1)~(w1, h1),
If sliding into the rightmost side of image to be detected, sliding window is moved down to the distance of a pixel, most from image to be detected
Left side starts to continue to slide, and the rectangular region image of w1*h1 is extracted in sliding every time.In this way, the rectangular region image that can be extracted
Quantity be (w2-w1+1) * (h2-h1+1).By using the method for sliding window, can when extracting rectangular region image,
Without considering the size of image to be detected, the rectangular region image extracted is set sufficiently to cover image to be detected, so as to improve
Extract the flexibility of rectangular region image.
Step 404, for the pixel in image to be detected, in image to be detected, the pixel correspondence rectangle region is determined
The quantity for the object pixel that domain includes.
In the present embodiment, for each pixel in image to be detected, above-mentioned executing subject can determine mapping to be checked
The quantity for the object pixel that as in, the pixel correspondence rectangular area includes.Wherein, which is located at the correspondence square of the pixel
At the Corner in shape region, the pixel at corresponding rectangular area, Corner angle steel joint is the origin of image to be detected
Pixel at coordinate.As an example, the Corner of corresponding rectangular area is bottom right angle point, then the angle steel joint of Corner is left
Upper angle point.As shown in fig. 5, it is assumed that the size of image to be detected 501 is 10*6, the coordinate of the pixel at the origin of image to be detected
For (1,1), the coordinate of certain pixel 502 is (4,5), then the correspondence rectangular area of the pixel such as in Fig. 5 503.
Step 405, for the rectangular region image at least two rectangular region images, based in the rectangular region image
Position of the pixel in image to be detected and the pixel in image to be detected the correspondence rectangular area object pixel that includes
Quantity, determine the quantity for the object pixel that the rectangular region image includes, be greater than in response to quantity determined by determining default
The first amount threshold, determine the rectangular region image be target rectangle area image.
In the present embodiment, for each rectangular region image at least two rectangular region images, above-mentioned electronics is set
It is standby to be primarily based on position of the pixel in the rectangular region image in image to be detected and the picture in image to be detected
The quantity for the object pixel that the correspondence rectangular area of element includes, determines the quantity for the object pixel that the rectangular region image includes.
In general, the quantity for the object pixel that the rectangular region image includes can be calculated according to following formula:
N=s [xx] [yy]-s [x-1] [yy]-s [xx] [y-1]+s [x-1] [y-1],
Wherein, n is the quantity for the object pixel that rectangular region image includes, and s is the correspondence rectangle of the pixel under certain coordinate
The quantity for the object pixel that region includes, xx, yy are respectively the abscissa of the pixel at the lower right corner of rectangular region image and indulge
Coordinate, x, y are respectively the abscissa and ordinate of the pixel of the left upper of rectangular region image.As shown in fig. 6, mapping to be checked
The size of picture 601 is 10*6, and the size of rectangular region image 602 is 3*3, and the coordinate of pixel A is (xx, yy), the coordinate of pixel B
For (x-1, yy), the coordinate of pixel C is (xx, y-1), and the coordinate of pixel D is (x-1, y-1).S [xx] [yy] is pair of pixel A
The quantity for the object pixel for answering rectangular area to include, s [x-1] [yy] are the object pixel that the correspondence rectangular area of pixel B includes
Quantity, the quantity for the correspondence rectangular area object pixel that includes that s [xx] [y-1] is pixel C, s [x-1] [y-1] is pixel D
The correspondence rectangular area object pixel that includes quantity.
Then, for above-mentioned executing subject in response to determining that identified quantity is greater than preset first amount threshold, determining should
Rectangular region image is target rectangle area image.
By this step, can be repeated to avoid when counting the quantity for the object pixel that each rectangular region image includes
Count the quantity for the object pixel that the laps of two rectangular region images includes.The calculation amount of the embodiment mainly by
The size of detection image influences, influenced by the size of sliding window and the quantity of rectangular region image it is smaller, so as to reduce
The time complexity of calculating helps to improve the efficiency of image detection.
Step 406, the quantity of target rectangle area image, and the number in response to determining target rectangle area image are determined
Amount is greater than preset second amount threshold, determines that image to be detected is target image.
In the present embodiment, step 406 and the step 205 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Figure 4, it is seen that the method for detection image compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 highlight the step of extracting rectangular region image using sliding window, and united using corresponding rectangular region image
The step of counting the quantity of object pixel, when so as to avoid the quantity statistics for carrying out object pixel to each rectangular region image,
Repetition judges whether pixel is object pixel and repeats to count the target picture that the overlapping region of multiple rectangular region images includes
The quantity of element, helps to improve the flexibility of the efficiency and image detection of image detection.
With further reference to Fig. 7, as the realization to method shown in above-mentioned each figure, this application provides one kind for detecting figure
One embodiment of the device of picture, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in fig. 7, the device 700 for detection image of the present embodiment includes:Acquiring unit 701 is configured to obtain
Take image to be detected;First determination unit 702, is configured to the color value for the pixel for including based on image to be detected, to be checked
In the pixel that altimetric image includes, object pixel is determined;Extraction unit 703 is configured to extract at least two from image to be detected
A rectangular region image;Second determination unit 704 is configured to for the rectangular area figure at least two rectangular region images
Picture determines the quantity for the object pixel that the rectangular region image includes, and is greater than preset the in response to quantity determined by determining
One amount threshold determines that the rectangular region image is target rectangle area image;Third determination unit 705, is configured to determine
The quantity of target rectangle area image, and the quantity in response to determining target rectangle area image are greater than preset second quantity
Threshold value determines that image to be detected is target image.
In the present embodiment, acquiring unit 701 can by wired connection mode or radio connection from long-range or
Image to be detected is obtained from local.Wherein, image to be detected can be the image in some image collection.As an example, certain figure
Image set close in image have corresponding label information, and each label information it is same or similar (such as label be " pencil drawing ",
" sketch images ", " simple picture " etc.), the image in the image collection needs to be detected, then the image in the image collection is to be checked
Altimetric image.
In the present embodiment, the image to be detected obtained based on acquiring unit 701, above-mentioned first determination unit 702 can be with
Color value based on the pixel that image to be detected includes determines object pixel from the pixel that image to be detected includes.Specifically
Ground, above-mentioned first determination unit 702 can determine object pixel according to various methods from the pixel that image to be detected includes.
As an example, above-mentioned first determination unit 702 can select color value to be in default model from the pixel that image to be detected includes
Pixel in enclosing is as object pixel.For example, color value may include R (red, Red) value, G (green, Green) value, B (indigo plant
Color, Blue) value, R value, G value, B value can be in preset range the pixel of (such as 0-100) as object pixel.
In the present embodiment, extraction unit 703 can extract at least two rectangular region images from image to be detected.Tool
Body, said extracted unit 703 can extract rectangular region image according to various methods from image to be detected.For example, above-mentioned
Extraction unit 703 can be according to the preset each coordinate range of technical staff, by each coordinate range pair from image to be detected
The image zooming-out answered, which comes out, is used as rectangular region image.
In the present embodiment, the rectangular area figure at least two rectangular region images extracted for extraction unit 703
Picture, above-mentioned second determination unit 704 can determine the quantity for the object pixel that the rectangular region image includes first.Then, it rings
Preset first amount threshold should be greater than in determining identified quantity, determine that the rectangular region image is target rectangle administrative division map
Picture.It should be noted that the first amount threshold can be the specific quantitative value of technical staff's setting, it is also possible to above-mentioned apparatus
700 numerical value being calculated according to the percentage of technical staff's setting.In general, above-mentioned second determination unit 704 can be according to each
Kind method determines the quantity for the object pixel that each rectangular region image includes.For example, above-mentioned second determination unit 704 can be according to
The quantity for the object pixel that the secondary each rectangular region image of statistics includes.As an example it is supposed that object pixel is that color is partially white
Gray pixels, then the integral color of target rectangle area image is partially greyish white.
In the present embodiment, the target rectangle area image determined based on the second determination unit 704, above-mentioned third determine single
Member 705 can determine the quantity of target rectangle area image first.Then in response to the quantity for determining target rectangle area image
Greater than preset second amount threshold, determine that image to be detected is target image.
In some optional implementations of the present embodiment, the first determination unit 702 may include:First determining module
(not shown), the pixel being configured in the pixel for including for image to be detected determine the equal of the color value of the pixel
Value, and determine the maximum color value of the pixel and the difference of minimum color value;Second determining module (not shown), is matched
It is set to based on identified color value, mean value and difference, from the pixel that image to be detected includes, determines object pixel.
In some optional implementations of the present embodiment, the second determining module can be further configured to:For
The pixel in pixel that image to be detected includes, color value, mean value and difference based on the pixel determine whether the pixel is ash
Color pixel;In response to determining that the pixel is gray pixels, and the mean value of the color value of the pixel is greater than preset mean value threshold value, really
The fixed pixel is object pixel.
In some optional implementations of the present embodiment, extraction unit 703 can be further configured to:Determine square
The size of shape sliding window successively extracts square from image to be detected according to the mobile rectangular slide window of preset sliding step
The region of shape sliding window covering, is determined as rectangular region image for extracted region, wherein sliding step is for characterizing square
The distance that shape sliding window moves every time.
In some optional implementations of the present embodiment, which can also include:4th determination unit is (in figure not
Show), it is configured to determine in image to be detected, the pixel correspondence rectangular area for the pixel in image to be detected
Including object pixel quantity, wherein the pixel is located at the Corner of correspondence rectangular area of the pixel, corresponding rectangle
Pixel at region, Corner angle steel joint is the pixel at the origin of image to be detected.
In some optional implementations of the present embodiment, the second determination unit can be further configured to:For
Rectangular region image at least two rectangular region images, based on the pixel in the rectangular region image in image to be detected
Position and the pixel in image to be detected the correspondence rectangular area object pixel that includes quantity, determine the rectangle region
The quantity for the object pixel that area image includes is determined in response to determining that identified quantity is greater than preset first amount threshold
The rectangular region image is target rectangle area image.
In some optional implementations of the present embodiment, image to be detected can obtain as follows:From pre-
If image collection in, choose length be greater than preset length threshold, and width be greater than preset width threshold value image conduct
Image to be detected.
The device provided by the above embodiment of the application, by extracting at least two rectangular area figures from image to be detected
Picture counts the quantity for the object pixel that rectangular region image includes to determine target rectangle area image, then to mesh
The quantity of mark rectangular area is counted, so that it is determined that whether image to be detected is target image, improves the effect of image detection
Rate enriches the means of image detection.
Below with reference to Fig. 8, it is (such as shown in FIG. 1 that it illustrates the electronic equipments for being suitable for being used to realize the embodiment of the present application
Server or terminal device) computer system 800 structural schematic diagram.Electronic equipment shown in Fig. 8 is only an example,
Should not function to the embodiment of the present application and use scope bring any restrictions.
As shown in figure 8, computer system 800 includes central processing unit (CPU) 801, it can be read-only according to being stored in
Program in memory (ROM) 802 or be loaded into the program in random access storage device (RAM) 803 from storage section 808 and
Execute various movements appropriate and processing.In RAM 803, also it is stored with system 800 and operates required various programs and data.
CPU 801, ROM 802 and RAM 803 are connected with each other by bus 804.Input/output (I/O) interface 805 is also connected to always
Line 804.
I/O interface 805 is connected to lower component:Importation 806 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 807 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage section 808 including hard disk etc.;
And the communications portion 809 of the network interface card including LAN card, modem etc..Communications portion 809 via such as because
The network of spy's net executes communication process.Driver 810 is also connected to I/O interface 805 as needed.Detachable media 811, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 810, in order to read from thereon
Computer program be mounted into storage section 808 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 809, and/or from detachable media
811 are mounted.When the computer program is executed by central processing unit (CPU) 801, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer-readable medium either the two any combination.Computer-readable medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable medium can include but is not limited to:Electrical connection, portable meter with one or more conducting wires
Calculation machine disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable medium, which can be, any includes or storage program has
Shape medium, the program can be commanded execution system, device or device use or in connection.And in the application
In, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, wherein
Carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to electric
Magnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable Jie
Any computer-readable medium other than matter, the computer-readable medium can be sent, propagated or transmitted for being held by instruction
Row system, device or device use or program in connection.The program code for including on computer-readable medium
It can transmit with any suitable medium, including but not limited to:Wirelessly, electric wire, optical cable, RF etc. or above-mentioned any conjunction
Suitable combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as:A kind of processor packet
Include acquiring unit, the first determination unit, extraction unit, the second determination unit and third determination unit.Wherein, the name of these units
Claim not constituting the restriction to the unit itself under certain conditions, for example, acquiring unit is also described as " obtaining to be checked
The unit of altimetric image ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment;It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are held by the electronic equipment
When row, so that the electronic equipment:Obtain image to be detected;Color value based on the pixel that image to be detected includes, to be detected
In the pixel that image includes, object pixel is determined;At least two rectangular region images are extracted from image to be detected;For at least
Rectangular region image in two rectangular region images determines the quantity for the object pixel that the rectangular region image includes, response
The quantity determined by determining is greater than preset first amount threshold, determines that the rectangular region image is target rectangle administrative division map
Picture;Determine the quantity of target rectangle area image, and the quantity in response to determining target rectangle area image greater than preset
Second amount threshold determines that image to be detected is target image.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (16)
1. a kind of method for detection image, including:
Obtain image to be detected;
Color value based on the pixel that described image to be detected includes determines mesh from the pixel that described image to be detected includes
Mark pixel;
At least two rectangular region images are extracted from described image to be detected;
For the rectangular region image at least two rectangular region image, the target that the rectangular region image includes is determined
The quantity of pixel determines that the rectangular region image is in response to determining that identified quantity is greater than preset first amount threshold
Target rectangle area image;
Determine the quantity of target rectangle area image, and the quantity in response to determining target rectangle area image greater than preset
Second amount threshold determines that described image to be detected is target image.
2. according to the method described in claim 1, wherein, the color value of the pixel for including based on described image to be detected,
From the pixel that described image to be detected includes, object pixel is determined, including:
The pixel in pixel for including for described image to be detected determines the mean value of the color value of the pixel, and determining should
The difference of the maximum color value of pixel and minimum color value;
Object pixel is determined from the pixel that described image to be detected includes based on identified color value, mean value and difference.
It is described based on identified color value, mean value and difference 3. according to the method described in claim 2, wherein, from it is described to
In the pixel that detection image includes, object pixel is determined, including:
The pixel in pixel for including for described image to be detected, color value, mean value and difference based on the pixel, determining should
Whether pixel is gray pixels;In response to determining that the pixel is gray pixels, and the mean value of the color value of the pixel is greater than default
Mean value threshold value, determine the pixel be object pixel.
4. described to extract at least two rectangular areas from described image to be detected according to the method described in claim 1, wherein
Image, including:
The size for determining rectangular slide window, according to the mobile rectangular slide window of preset sliding step, from described to be checked
In altimetric image, the region of the rectangular slide window covering is successively extracted, extracted region is determined as rectangular region image,
Wherein, the sliding step is for characterizing the distance that rectangular slide window moves every time.
5. according to the method described in claim 1, wherein, in the rectangle at least two rectangular region image
Area image determines the quantity for the object pixel that the rectangular region image includes, in response to determining that it is pre- that identified quantity is greater than
If the first amount threshold, determine the rectangular region image be target rectangle area image before, the method also includes:
For the pixel in described image to be detected, determine that in described image to be detected, the pixel correspondence rectangular area is wrapped
The quantity of the object pixel included, wherein the pixel is located at the Corner of correspondence rectangular area of the pixel, corresponding rectangle region
Pixel at domain, Corner angle steel joint is the pixel at the origin of described image to be detected.
6. according to the method described in claim 5, wherein, the number for the object pixel that the determination rectangular region image includes
Amount, including:
Based on the pixel in the rectangular region image in described image to be detected position and described image to be detected in
The quantity for the object pixel that the correspondence rectangular area of pixel includes, determines the number for the object pixel that the rectangular region image includes
Amount.
7. method described in one of -6 according to claim 1, wherein described image to be detected obtains as follows:
From preset image collection, chooses length and be greater than preset length threshold, and width is greater than preset width threshold value
Image is as image to be detected.
8. a kind of device for detection image, including:
Acquiring unit is configured to obtain image to be detected;
First determination unit is configured to the color value for the pixel for including based on described image to be detected, from the mapping to be checked
In the pixel that picture includes, object pixel is determined;
Extraction unit is configured to extract at least two rectangular region images from described image to be detected;
Second determination unit is configured to for the rectangular region image at least two rectangular region image, and determining should
The quantity for the object pixel that rectangular region image includes, in response to determining that identified quantity is greater than preset first quantity threshold
Value determines that the rectangular region image is target rectangle area image;
Third determination unit is configured to determine the quantity of target rectangle area image, and in response to determining target rectangle area
The quantity of area image is greater than preset second amount threshold, determines that described image to be detected is target image.
9. device according to claim 8, wherein first determination unit includes:
First determining module, the pixel being configured in the pixel for including for described image to be detected determine the face of the pixel
The mean value of color value, and determine the maximum color value of the pixel and the difference of minimum color value;
Second determining module, is configured to based on identified color value, mean value and difference, includes from described image to be detected
In pixel, object pixel is determined.
10. device according to claim 9, wherein second determining module is further configured to:
The pixel in pixel for including for described image to be detected, color value, mean value and difference based on the pixel, determining should
Whether pixel is gray pixels;In response to determining that the pixel is gray pixels, and the mean value of the color value of the pixel is greater than default
Mean value threshold value, determine the pixel be object pixel.
11. device according to claim 8, wherein the extraction unit is further configured to:
The size for determining rectangular slide window, according to the mobile rectangular slide window of preset sliding step, from described to be checked
In altimetric image, the region of the rectangular slide window covering is successively extracted, extracted region is determined as rectangular region image,
Wherein, the sliding step is for characterizing the distance that rectangular slide window moves every time.
12. device according to claim 8, wherein described device further includes:
4th determination unit, is configured to for the pixel in described image to be detected, determine it is in described image to be detected, should
The quantity for the object pixel that the correspondence rectangular area of pixel includes, wherein the pixel is located at the correspondence rectangular area of the pixel
At Corner, the pixel at corresponding rectangular area, Corner angle steel joint is the origin of described image to be detected
The pixel at place.
13. device according to claim 12, wherein second determination unit is further configured to:
For the rectangular region image at least two rectangular region image, existed based on the pixel in the rectangular region image
The object pixel that position in described image to be detected and the correspondence rectangular area of the pixel in described image to be detected include
Quantity, determine the quantity for the object pixel that the rectangular region image includes, be greater than in response to quantity determined by determining default
The first amount threshold, determine the rectangular region image be target rectangle area image.
14. the device according to one of claim 8-13, wherein described image to be detected obtains as follows:
From preset image collection, chooses length and be greater than preset length threshold, and width is greater than preset width threshold value
Image is as image to be detected.
15. a kind of electronic equipment, including:
One or more processors;
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Method as described in any in claim 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810694004.2A CN108921838A (en) | 2018-06-29 | 2018-06-29 | Method and apparatus for detection image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810694004.2A CN108921838A (en) | 2018-06-29 | 2018-06-29 | Method and apparatus for detection image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108921838A true CN108921838A (en) | 2018-11-30 |
Family
ID=64423636
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810694004.2A Pending CN108921838A (en) | 2018-06-29 | 2018-06-29 | Method and apparatus for detection image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108921838A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112700407A (en) * | 2020-12-14 | 2021-04-23 | 贝壳技术有限公司 | Method and device for determining image definition and storage medium |
CN112862686A (en) * | 2021-02-19 | 2021-05-28 | 成都国科微电子有限公司 | Demosaicing method, device, equipment and medium based on bright and dark lines |
CN113744177A (en) * | 2020-05-28 | 2021-12-03 | 中科寒武纪科技股份有限公司 | Method and device for detecting angular point of image and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8290296B2 (en) * | 2009-07-31 | 2012-10-16 | Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. | System and method for detecting blemishes in an image captured by an electronic device |
CN103218778A (en) * | 2013-03-22 | 2013-07-24 | 华为技术有限公司 | Image and video processing method and device |
CN103556561A (en) * | 2013-10-24 | 2014-02-05 | 中联重科股份有限公司 | Method and system for detecting pavement segregation and engineering machine |
CN105096350A (en) * | 2014-05-21 | 2015-11-25 | 腾讯科技(深圳)有限公司 | Image detection method and device |
CN106898082A (en) * | 2017-03-15 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
CN107103628A (en) * | 2017-03-22 | 2017-08-29 | 北京安博通科技股份有限公司 | Image detecting method and device |
-
2018
- 2018-06-29 CN CN201810694004.2A patent/CN108921838A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8290296B2 (en) * | 2009-07-31 | 2012-10-16 | Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. | System and method for detecting blemishes in an image captured by an electronic device |
CN103218778A (en) * | 2013-03-22 | 2013-07-24 | 华为技术有限公司 | Image and video processing method and device |
CN103556561A (en) * | 2013-10-24 | 2014-02-05 | 中联重科股份有限公司 | Method and system for detecting pavement segregation and engineering machine |
CN105096350A (en) * | 2014-05-21 | 2015-11-25 | 腾讯科技(深圳)有限公司 | Image detection method and device |
CN106898082A (en) * | 2017-03-15 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
CN107103628A (en) * | 2017-03-22 | 2017-08-29 | 北京安博通科技股份有限公司 | Image detecting method and device |
Non-Patent Citations (4)
Title |
---|
BINBIN_SUN: "RGB图像中给定区域是否为灰度图的判定", 《CSDN:HTTPS://BLOG.CSDN.NET/BINBIN_SUN/ARTICLE/DETAILS/80765425》 * |
WEIXIN_30909575: "判断位图是否是黑白图片", 《CSDN:HTTPS://BLOG.CSDN.NET/WEIXIN_30909575/ARTICLE/DETAILS/95422789》 * |
丁烈梅著: "《路面施工技术》", 31 August 2017, 北京理工大学出版社 * |
李煜东著: "《算法竞赛进阶指南》", 31 January 2018, 河南电子音像出版社 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113744177A (en) * | 2020-05-28 | 2021-12-03 | 中科寒武纪科技股份有限公司 | Method and device for detecting angular point of image and storage medium |
CN112700407A (en) * | 2020-12-14 | 2021-04-23 | 贝壳技术有限公司 | Method and device for determining image definition and storage medium |
CN112862686A (en) * | 2021-02-19 | 2021-05-28 | 成都国科微电子有限公司 | Demosaicing method, device, equipment and medium based on bright and dark lines |
CN112862686B (en) * | 2021-02-19 | 2023-10-27 | 杭州国科微电子有限公司 | Demosaicing method, device, equipment and medium based on bright and dark lines |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110399848A (en) | Video cover generation method, device and electronic equipment | |
CN107491771A (en) | Method for detecting human face and device | |
CN109446990A (en) | Method and apparatus for generating information | |
CN108090916A (en) | For tracking the method and apparatus of the targeted graphical in video | |
CN109308469A (en) | Method and apparatus for generating information | |
CN110619314A (en) | Safety helmet detection method and device and electronic equipment | |
CN109389589A (en) | Method and apparatus for statistical number of person | |
CN109033464A (en) | Method and apparatus for handling information | |
CN110213614A (en) | The method and apparatus of key frame are extracted from video file | |
CN108921838A (en) | Method and apparatus for detection image | |
CN109255337A (en) | Face critical point detection method and apparatus | |
CN109389096A (en) | Detection method and device | |
CN109389072A (en) | Data processing method and device | |
CN110059623A (en) | Method and apparatus for generating information | |
CN109784304A (en) | Method and apparatus for marking dental imaging | |
CN110502665A (en) | Method for processing video frequency and device | |
CN109285181A (en) | The method and apparatus of image for identification | |
CN109255767A (en) | Image processing method and device | |
CN107704388A (en) | For the method and apparatus for the startup time for determining application | |
CN110516678A (en) | Image processing method and device | |
CN110059624A (en) | Method and apparatus for detecting living body | |
CN109754464A (en) | Method and apparatus for generating information | |
CN108882025A (en) | Video frame treating method and apparatus | |
CN110516099A (en) | Image processing method and device | |
CN109271557A (en) | Method and apparatus for output information |
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 |