CN104202596A - Image color-cast detection method and system applied to intelligent terminal - Google Patents

Abstract

The invention discloses an image color-cast detection method and system applied to an intelligent terminal. The image color-cast detection method includes: acquiring images; performing spatial switching; computing parameters of histogram and equivalent circle of the images under the ab two-dimensional color coordinates; respectively calculating NNO areas of a source images and converted image information and the equivalent circle parameters corresponding to the NNO areas; quantizing thresholds, comparing the parameters, judging image color-cast situations, performing color-cast image classification, or performing secondary detection on non-color-cast images; after repeated testing, dividing the images into color-cast images, natural color-cast images, true color-cast images, non-color-cast images and unable-to-be-detected images. The image color-cast detection method and system has good applicability and high color-cast detection accuracy and reliability; computing time and complexity are lowered, good real-time performance is achieved, and the image color-cast detection method and system is applicable to real-time detection of photographed images of the intelligent terminal.

Description

A kind of image colour cast detection method and system that is applied to intelligent terminal

Technical field

The invention belongs to digital image processing techniques field, relate in particular to a kind of image colour cast detection method and system that is applied to intelligent terminal.

Background technology

One of most important information that color comprises as image is directly to weigh the key character of equipment image quality.The key factor that affects color of image quality is the semaphore of storing in digital imaging apparatus internal image transducer, and its content not only depends on the surface color of collected object, also by the extraneous light conditions being subject at that time.Therefore when imaging device is if digital camera, scanner are in the time working, the impact that is subject to factors due to its inner sensitive component causes finally obtaining existence error to a certain degree between the color of color digital image and the realistic colour of real scene body surface, i.e. so-called colour cast.

In non-reference picture quality appraisement field, colour cast is an important measurement index.Current traditional algorithm is realized according to color constancy the detection of colour cast.Classical algorithm has max_RGB algorithm, Grey World algorithm, Retinex algorithm etc.There is the shortcoming that accuracy is lower, algorithm is complicated, time complexity is high in these algorithms! Be not suitable for intelligent terminal occasion higher to requirement of real-time and that computational resource is limited.

Summary of the invention

The object of the embodiment of the present invention is to provide a kind of image colour cast detection method and system that is applied to intelligent terminal, and being intended to solve does not have a kind of problem of more exactly image being carried out colour cast detection method at present.

The embodiment of the present invention is achieved in that a kind of image colour cast detection method that is applied to intelligent terminal, and this image colour cast detection method that is applied to intelligent terminal comprises:

The first step, in Lab space, the parameter of the histogram of computed image under ab two-dimensional color coordinate and circle of equal value;

Second step, solves respectively source images and the NNO region of image information after conversion and corresponding equivalence circle parameter; Quantization threshold, reduced parameter, judges image colour cast situation, carries out colour cast Images Classification, or non-colour cast image detects again;

The 3rd step, through repeated detection, is divided into colour cast image by image, essential colour cast image, and true colour cast image, without colour cast image, cannot detected image.

Further, need to obtain a secondary RGB image I mg_sur as image to be detected by the intelligent terminal of taking pictures before the parameter of the histogram under ab two-dimensional color coordinate and circle of equal value in first step computed image; Source images Img_sur is transformed into Lab chrominance space by rgb space, obtains changing rear image I mg_Lab and the view data on L, a, b component thereof.

Further, colour cast Images Classification comprises the following steps: calculate luminance component histogram; The number of times and the interval accounting that occur according to pixel judge colour cast type for the first time; Finally determine image colour cast type by NNO region and source images two-dimensional histogram circle of equal value parameter: essential colour cast, true colour cast.

Further, the concrete grammar of colour cast Images Classification comprises:

Step 1, through type (1), the histogram distribution feature of quantitative analysis Img_Lab image under ab two-dimensional color coordinate, and calculate circle E of equal value according to formula (2), (3) _qcenter of circle C, radius sigma, u, D, D _σparameter;

$\left\{\begin{array}{c}{u}_k=\underset{k}{\∫}\mathrm{kF}(a,b)\mathrm{dk},\\ {\mathrm{\σ}}_k^2=\underset{k}{\∫}{(u_k-k)}^{2}F(a,b)\mathrm{dk}\end{array}\right.,k=a,b---\left(1\right)$

$\left\{\begin{array}{c}C=(u_a,u_b)\\ \mathrm{\σ}=\sqrt{{{\mathrm{\σ}}_a}^2+{{\mathrm{\σ}}_b}^2}\end{array}\right.---\left(2\right)$

$\left\{\begin{array}{c}u=\sqrt{{u_a}^2+{u_b}^2}\\ D=u-\mathrm{\σ}\\ D_{\mathrm{\σ}}=D/\mathrm{\σ}\end{array}\right.---\left(3\right)$

In formula (3), u is the distance of the round center of circle C of this equivalence apart from neutral axis (a=0, b=0), and D is the distance of the outer lateral extent neutral axis of circle of equal value, D _σrepresent that this two-dimensional histogram circle of equal value departs from the degree of neutral axis: D _σbe worth greatlyr, show that this image histogram departs from neutral axis more serious;

Step 2, judges image colour cast situation for the first time: in the time meeting formula (4), think that the ab two dimensional surface histogram of image is assembled, and be temporarily colour cast image by graphic collection, otherwise, tentatively assert that image is non-colour cast image, execution step step 3;

(D>10and D _σ>0.6)or(D _σ>1.5) (4)

Step 3, solves the NNO region of image; Theoretical foundation: the no color differnece surface in image scene can be reflected the color of incident illumination in scene completely.As long as therefore extract the gray face in scene, then by the colour cast situation of these gray faces, just can estimate accurately the drift condition of the illumination of image; Method is as follows: if Img_NNO (i, j) pixel is NNO area pixel:

Wherein L, a, b are three component information of image at Lab chrominance space, and d is the colourity radius maximum of testing image Img_sur in Lab chrominance space; Meanwhile, for preventing the interference for NNO extracted region of noise spot in image, restriction d place pixel and each NNO area pixel point Img_NNO (i, j) are non-isolated pixel point.

Further, it is the supplementary and correction to last result that non-colour cast image detects again, and step is: the two-dimensional histogram circle of equal value that generates respectively source images and NNO area image, quantization threshold, reduced parameter, output detections result: essential colour cast, true colour cast, without colour cast.

Further, the concrete grammar that non-colour cast image detects again comprises:

Step 1, solves the corresponding circle D of equal value of its two-dimensional histogram to result images _σthe parameter of NNO, the parameters of contrast source images circle of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, carries out secondary judgement from the variation tendency of both parameters to non-focused image or non-colour cast image;

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crimage two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively, quantized image is in the two-dimensional histogram that extracts front and back, NNO region round situation of change of equal value effectively, the isoparametric amplitude of variation of two-dimensional histogram circle of equal value σ, u of normal non-colour cast image source image and NNO area image is larger, the equivalence circle parameter that is the NNO area image of normal non-colour cast image changes greatly than the equivalence circle parameter of source images, and this characteristic conforms is normally without the color characteristic of colour cast image; Meanwhile, colour cast image is less in σ, the u parameter value variation amplitude of extracting front and back, NNO region, and the NNO area image of colour cast image has the color characteristic of colour cast equally; So realizing the method for non-colour cast Images Classification by the variation of analysis σ, u parameter value is that effectively setup parameter threshold value is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively;

Step 2, the image that is judged to be for the first time colour cast image is classified:

By the histogram distribution information of utilizing image at the L of Lab chrominance space component, image is classified first; In the time that picture material is obvious essential colour cast, the histogram distribution of the L component of Lab chrominance space presents zonal gathering and distributes; And picture material is while being true colour cast, the histogram distribution of the L component of Lab chrominance space is rendered as more uniform discrete distribution; In the following way the L component of image is processed:

When certain pixel occurrence number in L histogram of component lower than the highest pixel occurrence number of occurrence number 1% time, by the pixel count zero setting of this pixel; L histogram of component after treatment of judgement, the minimum pixel that pixel occurrence number is non-vanishing and maximum pixel across interval whether be less than 80% at the proportion of the whole pixel range of L component;

In the time that non-zero number of times region that pixel is crossed over is less than or equal to whole pixel range 80%, judge that this image colour cast type is essential colour cast; In the time being greater than 80, the judgement of products for further;

To having essential colour cast feature, and picture material is not very single essential colour cast image and true colour cast image, further judges according to the variation of the relative source images of the parameters circle of equal value parameter of the two-dimensional histogram in NNO region circle of equal value; Color constancy; If the distortion of image generation colour cast, NNO region also can embody colour cast feature; If colour cast distortion does not occur image, NNO region should show the feature of normal picture, uses equally formula (6) to classify to colour cast image, and arranging according to different scenes of threshold value adjusted:

Wherein σ _crand u _crcolour cast image two-dimensional histogram radius of a circle σ of equal value and the amplitude index of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively.

Further, this image colour cast detection method that is applied to intelligent terminal specifically comprises the following steps:

Step 1, obtains a secondary RGB image I mg_sur as image to be detected by intelligent terminal capable of taking pictures;

Step 2, is transformed into Lab chrominance space by source images Img_sur by rgb space, obtains changing rear image I mg_Lab and the view data on L, a, b component;

Step 3, through type (1), the histogram distribution feature of quantitative analysis Img_Lab image under ab two-dimensional color coordinate, and calculate circle E of equal value according to formula (2), (3) _qcenter of circle C, radius sigma, u, D, D _σparameter;

$\left\{\begin{array}{c}{u}_k=\underset{k}{\&Integral;}\mathrm{kF}(a,b)\mathrm{dk},\\ {\mathrm{\&sigma;}}_k^2=\underset{k}{\&Integral;}{(u_k-k)}^{2}F(a,b)\mathrm{dk}\end{array}\right.,k=a,b---\left(1\right)$

$\left\{\begin{array}{c}C=(u_a,u_b)\\ \mathrm{\&sigma;}=\sqrt{{{\mathrm{\&sigma;}}_a}^2+{{\mathrm{\&sigma;}}_b}^2}\end{array}\right.---\left(2\right)$

$\left\{\begin{array}{c}u=\sqrt{{u_a}^2+{u_b}^2}\\ D=u-\mathrm{\&sigma;}\\ D_{\mathrm{\&sigma;}}=D/\mathrm{\&sigma;}\end{array}\right.---\left(3\right)$

In formula (3), u is the distance of the round center of circle C of this equivalence apart from neutral axis (a=0, b=0), and D is the distance of the outer lateral extent neutral axis of circle of equal value, D _σrepresent that this two-dimensional histogram circle of equal value departs from the degree of neutral axis: D _σbe worth greatlyr, show that this image histogram departs from neutral axis more serious;

Step 4, judges image colour cast situation for the first time: in the time meeting formula (4), think that the ab two dimensional surface histogram of image is assembled, and be temporarily colour cast image by graphic collection, execution step seven; Otherwise, tentatively assert that image is non-colour cast image, execution step five;

(D>10and D _σ>0.6)or(D _σ>1.5) (4)

Step 5, solve NNO (nearneutralobjects) region of image, theoretical foundation: the no color differnece surface in image scene can be reflected the color of incident illumination in scene completely, by the colour cast situation of these gray faces, estimate accurately the drift condition of the illumination of image, method is as follows: if Img_NNO (i, j) pixel is NNO area pixel:

Wherein L, a, b are three component information of image at Lab chrominance space, d is the colourity radius maximum of testing image Img_sur in Lab chrominance space, simultaneously, for preventing the interference for NNO extracted region of noise spot in image, restriction d place pixel and each NNO area pixel point Img_NNO (i, j) are non-isolated pixel point;

Step 6, solves the corresponding circle D of equal value of its two-dimensional histogram to the result images of step 5 _σthe parameter of NNO, the parameters of contrast source images circle of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, carries out secondary judgement from the variation tendency of both parameters to non-focused image or non-colour cast image;

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crimage two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively, quantized image is in the two-dimensional histogram that extracts front and back, NNO region round situation of change of equal value effectively, there is good parameter role of delegate, the two-dimensional histogram circle of equal value σ of normal non-colour cast image source image and NNO area image, the isoparametric amplitude of variation of u is larger, the equivalence circle parameter that is the NNO area image of normal non-colour cast image changes greatly than the equivalence circle parameter of source images, this characteristic conforms is normally without the color characteristic of colour cast image, simultaneously, colour cast image is less in σ, the u parameter value variation amplitude of extracting front and back, NNO region, it is the color characteristic that the NNO area image of colour cast image has colour cast equally, so, realizing the method for non-colour cast Images Classification by the variation of analysis σ, u parameter value is that effectively setup parameter threshold value is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively;

Step 7, the image that is judged to be for the first time colour cast image is classified:

By the histogram distribution information of utilizing image at the L of Lab chrominance space component, image is classified first, in the time that picture material is obvious essential colour cast, the histogram distribution of the L component of Lab chrominance space presents zonal gathering and distributes; And picture material is while being true colour cast, the histogram distribution of the L component of Lab chrominance space is rendered as more uniform discrete distribution, in the following way the L component of image is processed:

When certain pixel occurrence number in L histogram of component lower than the highest pixel occurrence number of occurrence number 1% time, by the pixel count zero setting of this pixel;

L histogram of component after treatment of judgement, the minimum pixel that pixel occurrence number is non-vanishing and maximum pixel across interval whether be less than 80% at the proportion of the whole pixel range of L component:

In the time that non-zero number of times region that pixel is crossed over is less than or equal to whole pixel range 80%, judge that this image colour cast type is essential colour cast;

In the time being greater than 80, the judgement of products for further;

To thering is essential colour cast feature, and picture material is not very single essential colour cast image and true colour cast image, further judge according to the variation of the relative source images of the parameters circle of equal value parameter of the two-dimensional histogram in their NNO region circle of equal value, color constancy, if the distortion of image generation colour cast, NNO region also can embody colour cast feature; If colour cast distortion does not occur image, NNO region should show the feature of normal picture, uses equally formula (6) to classify to colour cast image, and wherein, arranging according to different scenes of threshold value adjusted:

Wherein σ _crand u _crcolour cast image two-dimensional histogram radius of a circle σ of equal value and the amplitude index of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively;

Step 8, is embedded into the program of the method in mobile terminal capable of taking pictures, and the picture that equipment is obtained detects in real time, to obtain the evaluation in performance aspect color to this hardware.

Another object of the embodiment of the present invention is to provide a kind of image colour cast detection system that is applied to intelligent terminal, it is characterized in that, this image colour cast detection system that is applied to intelligent terminal comprises:

By RGB image acquisition; Space conversion; The parameter of the histogram of computed image under ab two-dimensional color coordinate and circle of equal value; Solve respectively source images and NNO (the near neutral objects) region of image information after conversion and corresponding equivalence circle parameter thereof; Quantization threshold, reduced parameter, judges image colour cast situation, carries out colour cast Images Classification, or " non-colour cast image " detects again; Through repeated detection, image is divided into colour cast image, essential colour cast image, true colour cast image, without colour cast image, cannot detected image.

The present invention can not be subject to the limitation of scene or priori, and compared to existing technologies, has improved the precision detecting, and has general applicability simultaneously, has improved accuracy rate and reliability that colour cast detects; And the present invention has used conversion and the histogram of color space, NNO region, some knowledge of circle of equal value neatly, simplify operand, there is good real-time performance, be suitable for the take pictures real-time detection of image of intelligent terminal, also can be used for evaluating the performance of intelligent terminal image-taking system.

Because the image library set for colour cast research specially is not all set up in current most of graph image storehouse, therefore, cannot comprehensively analyze the performance comparison situation of this paper algorithm and other algorithms.In order to verify the accuracy of improving algorithm effect herein, I have collected a large amount of colour casts, normal picture (192 width experimental image altogether from network, the image that wherein 20 width essence colour cast images, the true colour cast image of 30 width, 109 width normal pictures and 33 width cannot judge), and this image collection is carried out respectively former Lab chrominance space colour cast detection algorithm and improved rear algorithm, and the experiment detection statistics result of two algorithms is contrasted, Detection accuracy and the False Rate of main contrast two algorithms, testing result contrast situation is as shown in the table:

As seen from the above table, improve algorithm with respect to former algorithm all increasing in classification with without the detection accuracy of the context of detection again of colour cast image at colour cast image.Meanwhile, due to improve algorithm need to be by other evaluation and classification algorithm, make algorithm in whole flow process, be sealing, establish one's own system, can be used in fast detecting and the evaluation map application scenario as colouring information.

Brief description of the drawings

Fig. 1 is the image colour cast detection method flow chart that is applied to intelligent terminal that the embodiment of the present invention provides;

Fig. 2 is the flow chart of the image colour cast detection method embodiment that is applied to intelligent terminal that provides of the embodiment of the present invention;

Fig. 3 is the colour cast Images Classification module schematic flow sheet that the embodiment of the present invention provides;

Fig. 4 is the non-colour cast image detection module schematic flow sheet again that the embodiment of the present invention provides;

Fig. 5 is the embedding Android equipment interface schematic diagram that the embodiment of the present invention provides;

Fig. 6 is the embedding Android device data operational flowchart that the embodiment of the present invention provides.

Embodiment

In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.

Below in conjunction with drawings and the specific embodiments, application principle of the present invention is further described.

As shown in Figure 1, the image colour cast detection method that is applied to intelligent terminal of the embodiment of the present invention comprises the following steps:

S101:RGB image acquisition: obtain by terminal imaging device;

S102: space conversion: RGB image is transformed into Lab space;

S103: the parameter of the histogram of computed image under ab two-dimensional color coordinate and circle of equal value;

S104: solve respectively source images and NNO (the near neutral objects) region of image information after conversion and corresponding equivalence circle parameter thereof;

S105: quantization threshold, reduced parameter, judges image colour cast situation, carries out colour cast Images Classification, or " non-colour cast image " detects again;

S106: through repeated detection, image is divided into colour cast image, essential colour cast image, true colour cast image, without colour cast image, cannot detected image.

Concrete steps of the present invention are:

Step 1, obtains a secondary RGB image I mg_sur as image to be detected by intelligent terminal capable of taking pictures;

Step 2, is transformed into Lab chrominance space by source images Img_sur by rgb space, obtains changing rear image I mg_Lab and the view data on L, a, b component thereof;

Step 3, through type (1), the histogram distribution feature of quantitative analysis Img_Lab image under ab two-dimensional color coordinate, and calculate circle E of equal value according to formula (2), (3) _qcenter of circle C, radius sigma, u, D, D _σetc. parameter;

$\left\{\begin{array}{c}{u}_k=\underset{k}{\&Integral;}\mathrm{kF}(a,b)\mathrm{dk},\\ {\mathrm{\&sigma;}}_k^2=\underset{k}{\&Integral;}{(u_k-k)}^{2}F(a,b)\mathrm{dk}\end{array}\right.,k=a,b---\left(1\right)$

$\left\{\begin{array}{c}C=(u_a,u_b)\\ \mathrm{\&sigma;}=\sqrt{{{\mathrm{\&sigma;}}_a}^2+{{\mathrm{\&sigma;}}_b}^2}\end{array}\right.---\left(2\right)$

$\left\{\begin{array}{c}u=\sqrt{{u_a}^2+{u_b}^2}\\ D=u-\mathrm{\&sigma;}\\ D_{\mathrm{\&sigma;}}=D/\mathrm{\&sigma;}\end{array}\right.---\left(3\right)$

In formula (3), u is the distance of the round center of circle C of this equivalence apart from neutral axis (a=0, b=0), and D is the distance of the outer lateral extent neutral axis of circle of equal value, D _σrepresent that this two-dimensional histogram circle of equal value departs from the degree of neutral axis: D _σbe worth greatlyr, show that this image histogram departs from neutral axis more serious;

Step 4, judges image colour cast situation for the first time: in the time meeting formula (4), think that the ab two dimensional surface histogram of image is assembled, and temporarily by graphic collection be " colour cast image ", execution step seven; Otherwise, tentatively assert that image is " non-colour cast image ", execution step five;

(D>10and D _σ>0.6)or(D _σ>1.5) (4)

Step 5, solve NNO (the near neutral objects) region of image, theoretical foundation: the no color differnece surface (gray face under standard white light in image scene, be the neutral gray area of coloured image) can reflect the color of incident illumination in scene completely, as long as therefore extract the gray face in scene, then by the colour cast situation of these gray faces, just can estimate accurately the drift condition of the illumination of image, method is as follows: if Img_NNO is (i, j) pixel is NNO area pixel:

Wherein L, a, b are three component information of image at Lab chrominance space, d is the colourity radius maximum of testing image Img_sur in Lab chrominance space, simultaneously, for preventing the interference for NNO extracted region of noise spot in image, restriction d place pixel and each NNO area pixel point Img_NNO (i, j) are non-isolated pixel point;

Step 6, solves the corresponding circle D of equal value of its two-dimensional histogram to the result images of step 5 _σthe parameter of NNO, the parameters of contrast source images circle of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, carries out secondary judgement from the variation tendency of both parameters to non-focused image (non-colour cast image);

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crimage two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively, quantized image is in the two-dimensional histogram that extracts front and back, NNO region round situation of change of equal value effectively, there is good parameter role of delegate, the two-dimensional histogram circle of equal value σ of normal non-colour cast image source image and NNO area image, the isoparametric amplitude of variation of u is larger, the equivalence circle parameter that is the NNO area image of normal non-colour cast image changes greatly than the equivalence circle parameter of source images, this characteristic conforms is normally without the color characteristic of colour cast image, simultaneously, colour cast image is less in σ, the u parameter value variation amplitude of extracting front and back, NNO region, it is the color characteristic that the NNO area image of colour cast image has colour cast equally, so, it is effective realizing the method for non-colour cast Images Classification by the variation of analysis σ, u parameter value, based on the analysis and synthesis of abundant experimental results, setup parameter threshold value is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively; Other situations are regarded as the image type that algorithm cannot be processed;

Step 7, the image that is judged to be for the first time " colour cast image " is classified:

1, by the histogram distribution information of utilizing image at the L of Lab chrominance space component, image is classified first, in the time that picture material is obvious essential colour cast, the histogram distribution of the L component of its Lab chrominance space presents zonal gathering and distributes; And picture material is while being true colour cast, the histogram distribution of the L component of its Lab chrominance space is rendered as more uniform discrete distribution, through a large amount of experiments, in the following way the L component of image is processed:

1.1, when certain pixel occurrence number in L histogram of component lower than the highest pixel occurrence number of occurrence number 1% time, by the pixel count zero setting of this pixel;

1.2, judge the L histogram of component after 1.1 step process, the minimum pixel that pixel occurrence number is non-vanishing and maximum pixel across interval whether be less than 80% at the proportion of the whole pixel range of L component:

1.2.1, in the time that non-zero number of times region that pixel is crossed over is less than or equal to whole pixel range 80%, judge that this image colour cast type is essential colour cast;

1.2.2, in the time being greater than 80, the judgement of products for further;

2, those are had to essential colour cast feature, and picture material is not very single essential colour cast image and true colour cast image, further judge according to the variation of the relative source images of the parameters circle of equal value parameter of the two-dimensional histogram in their NNO region circle of equal value, the principle of this step is: color constancy, if the distortion of image generation colour cast, its NNO region also can embody colour cast feature; If colour cast distortion does not occur image, its NNO region should show the feature of normal picture, through localized experimental verification, uses equally formula (6) to classify to colour cast image, and wherein, arranging of threshold value can be adjusted according to different scenes:

Wherein σ _crand u _crcolour cast image two-dimensional histogram radius of a circle σ of equal value and the amplitude index of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively; ;

Step 8, is embedded into the program of the method in mobile terminal capable of taking pictures, and the picture that equipment is obtained detects in real time, to obtain the evaluation in performance aspect color to this hardware;

Specific embodiments of the invention:

As shown in Figure 2, the embodiment of the present invention by colour cast Images Classification module (Fig. 3), non-colour cast image module detects (Fig. 4) two parts composition again, the algorithm idea of these two modules is embedded into Android equipment (intelligent Android system mobile phone), design user interface as shown in Figure 5, on the main interface of mobile phone A pp, places three control: ImageView, for showing the image that camera obtains, it is exactly source images to be evaluated; TextView, provides the evaluation result of image, and whether the image obtaining by this mobile phone exists colour cast, and is the colour cast of which kind of type; Button, arranges monitoring event onClick, when after trigger event, the camera-enabled that calling mobile phone is built-in, is defaulted as and calls post-positioned pick-up head (if having front-facing camera), after getting image and detect, and result feedback is shown to TextView, the operating process of whole data flow as shown in Figure 6, is divided into five module: Button, equipment camera, obtain image, colour cast algorithm, evaluation result, is elaborated the operating process according to data flow below:

Button: in Android exploitation, Button is one of control the most frequently used in various UI, user can trigger sequence of events by touching it, one does not have the Button of click event without any meaning, on stream, conventionally to give unique ID of Button or key, named herein is button, can be for it arranges association attributes in XML file, for example wide, high, mainly in the onCreat of Activity, obtain button example by findViewById, then the monitor onClickListener to a click event of button binding, by button click invocation facility camera, ,

Equipment camera: Google provides the API that calls built-in camera, only need to obtain corresponding authority, just can, by the camera on built-in camera API Calls mobile phone, realize and take pictures and obtain image;

Obtain image: obtain image by calling camera, need to have man-machine interactively to realize image taking here;

Colour cast algorithm: the implementation language of algorithm is based on the embedded system of smart machine, and in Android platform, realize this algorithm by Java language, process is as follows:

Step 1, is transformed into Lab chrominance space by source images Img_sur by rgb space, obtain conversion after image I mg_Lab and the view data on L, a, b component;

Step 2, through type (1), obtains the histogram distribution feature of Img_Lab image under ab two-dimensional color coordinate, and calculates circle E of equal value according to formula (2), (3) _qcenter of circle C, radius sigma, u, D, D _σetc. parameter;

$\left\{\begin{array}{c}{u}_k=\underset{k}{\&Integral;}\mathrm{kF}(a,b)\mathrm{dk},\\ {\mathrm{\&sigma;}}_k^2=\underset{k}{\&Integral;}{(u_k-k)}^{2}F(a,b)\mathrm{dk}\end{array}\right.,k=a,b---\left(1\right)$

$\left\{\begin{array}{c}C=(u_a,u_b)\\ \mathrm{\&sigma;}=\sqrt{{{\mathrm{\&sigma;}}_a}^2+{{\mathrm{\&sigma;}}_b}^2}\end{array}\right.---\left(2\right)$

$\left\{\begin{array}{c}u=\sqrt{{u_a}^2+{u_b}^2}\\ D=u-\mathrm{\&sigma;}\\ D_{\mathrm{\&sigma;}}=D/\mathrm{\&sigma;}\end{array}\right.---\left(3\right)$

In formula (3), u is the distance of the round center of circle C of this equivalence apart from neutral axis (a=0, b=0), and D is the distance of the outer lateral extent neutral axis of circle of equal value, D _σrepresent that this two-dimensional histogram circle of equal value departs from the degree of neutral axis;

Step 3, judges image colour cast situation for the first time: in the time meeting formula (4), think that the ab two dimensional surface histogram of image is assembled, and temporarily by graphic collection be " colour cast image ", execution step seven; Otherwise, tentatively assert that image is " non-colour cast image ", execution step five;

(D>10and D _σ>0.6)or(D _σ>1.5) (4)

Step 4, solves the NNO region of image, if Img_NNO (i, j) pixel is NNO area pixel:

Wherein L, a, b are three component information of image at Lab chrominance space, d is the colourity radius maximum of testing image Img_sur in Lab chrominance space, simultaneously, for preventing the interference for NNO extracted region of noise spot in image, restriction d place pixel and each NNO area pixel point Img_NNO (i, j) are non-isolated pixel point;

Step 5, solves the corresponding circle D of equal value of its two-dimensional histogram to result images _σthe parameter of NNO, and contrast source images round parameters of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, from the variation tendency of both parameters, non-focused image (non-colour cast image) is carried out to secondary judgement;

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crrepresented respectively image two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point, setup parameter threshold value is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively; Other situations are regarded as the image type that algorithm cannot be processed;

Step 6, the image that is judged to be for the first time " colour cast image " is classified:

1, utilize the histogram distribution information of image at the L of Lab chrominance space component, image classified first, in the following way the L component of image is processed:

1.1, when certain pixel occurrence number in L histogram of component lower than the highest pixel occurrence number of occurrence number 1% time, by the pixel count zero setting of this pixel;

1.2, judge the L histogram of component after i step process, the minimum pixel that pixel occurrence number is non-vanishing and maximum pixel across interval whether be less than 80% at the proportion of the whole pixel range of L component:

1.2.1, in the time that non-zero number of times region that pixel is crossed over is less than or equal to whole pixel range 80%, judge that this image colour cast type is essential colour cast; ;

1.2.1, in the time being greater than 80, the judgement of products for further;

2, those are had to essential colour cast feature, and picture material is not very single essential colour cast image and true colour cast image, further judge according to the variation of the relative source images of the parameters circle of equal value parameter of the two-dimensional histogram in NNO region circle of equal value.Because detecting at present ununified image library, colour cast can supply experiment, all sample images equal network retrieval of originating, through localized experimental verification, uses formula (6) to classify to colour cast image equally, wherein, arranging of threshold value can be adjusted according to different scenes:

Wherein σ _crand u _crcolour cast image two-dimensional histogram radius of a circle σ of equal value and the amplitude index of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively;

Evaluation result: the result feedback of colour cast algorithm is shown to TextView.

The real-time that the present invention is good repeatedly judges in the time of colour cast image detection, makes testing result more reliable, accurate; More accurate aspect colour cast Images Classification.By a large amount of experiments, as far as possible objectively in quantization algorithm about threshold value selection problem--image belongs to the threshold value of colour cast or non-colour cast, colour cast image belongs to the threshold value of true colour cast or essential colour cast; Context of detection again at non-colour cast image is more accurate.The method has further been analyzed the parameter front and back situation of change of the corresponding circle of equal value of two-dimensional histogram, and colour cast image is divided into true colour cast and essential colour cast by the situation that has proposed first to distribute according to the L component information of image, can more effectively supplement the truth of effective evaluation image colour cast to primary testing result; When the accuracy of algorithm is improved, retain dexterously the features such as the real-time of former algorithm, and accurately to colour cast Images Classification, can evaluate better the performance of imaging product, choose reasonable consumptive material.

Due to its lightweight, easily realize, real-time is good, accuracy high can be embedded into multiple mobile terminal capable of taking pictures, not only comprise the terminal of Android system, also comprise the operating systems such as iOS, windows, can directly reflect the performance of obtaining image of intelligent terminal capable of taking pictures by the detection and classification of colour cast; Not only can be for can directly obtaining the end product of digital picture, but also can be for evaluating color static imaging (laser printing, xerography) product, adopt certain measure, by papery image digitazation, thereby the quality of the good and bad degree, particularly compatible consumptive material obtained for light source information in perception color static imaging objectively (laser printing, xerography) product imaging scene.For color printer, the electrophotographic image forming performance of the formula of carbon dust or printer, all may produce comparatively serious impact to the color of image.Range of application is very extensive.

The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.

Claims (8)

1. an image colour cast detection method that is applied to intelligent terminal, is characterized in that, this image colour cast detection method that is applied to intelligent terminal comprises:

The first step, in Lab space, the parameter of the histogram of computed image under ab two-dimensional color coordinate and circle of equal value;

Second step, solves respectively source images and the NNO region of image information after conversion and corresponding equivalence circle parameter; Quantization threshold, reduced parameter, judges image colour cast situation, carries out colour cast Images Classification, or non-colour cast image detects result images is solved to the corresponding of equal value circle of two-dimensional histogram D _σthe parameter of NNO, the parameters of contrast source images circle of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, carries out secondary judgement from the variation tendency of both parameters to non-focused image or non-colour cast image;

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crimage two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively, quantized image is in the two-dimensional histogram that extracts front and back, NNO region round situation of change of equal value effectively, the isoparametric amplitude of variation of two-dimensional histogram circle of equal value σ, u of normal non-colour cast image source image and NNO area image is larger, the equivalence circle parameter that is the NNO area image of normal non-colour cast image changes greatly than the equivalence circle parameter of source images, and this characteristic conforms is normally without the color characteristic of colour cast image; Meanwhile, colour cast image is less in σ, the u parameter value variation amplitude of extracting front and back, NNO region, and the NNO area image of colour cast image has the color characteristic of colour cast equally; So realizing the method for non-colour cast Images Classification by the variation of analysis σ, u parameter value is that effectively parameter threshold is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively;

The 3rd step, through being not more than 3 detections, is divided into colour cast image by image, essential colour cast image, and true colour cast image, without colour cast image, cannot detected image.

2. be applied to as described in claim 1 the image colour cast detection method of intelligent terminal, it is characterized in that, before the parameter of the histogram in first step computed image under ab two-dimensional color coordinate and circle of equal value, need to obtain a secondary RGB image I mg_sur as image to be detected by the intelligent terminal of taking pictures; Source images Img_sur is transformed into Lab chrominance space by rgb space, obtains changing rear image I mg_Lab and image brightness and chroma data on L, a, b component; It is as follows that wherein rgb space is transformed into Lab chrominance space formula:

$\left\{\begin{array}{c}L=(13933*R+46871*G+4732*B)/2^16\\ a=377*(14503*R-22218*G+7714*B)/2^24+128\\ b=160*(12773*R+39695*G-52468*B)/2^24+128\end{array}\right..$

3. the image colour cast detection method that is applied to as described in claim 1 intelligent terminal, is characterized in that, colour cast Images Classification comprises the following steps: calculate luminance component histogram; The number of times and the interval accounting that occur according to pixel judge colour cast type for the first time; Finally determine image colour cast type by NNO region and source images two-dimensional histogram circle of equal value parameter: essential colour cast, true colour cast.

4. the image colour cast detection method that is applied to as described in claim 3 intelligent terminal, is characterized in that, the concrete grammar of colour cast Images Classification comprises:

Step 1, through type (1), analyzes the histogram distribution feature of Img_Lab image under ab two-dimensional color coordinate, and calculates circle E of equal value according to formula (2), (3) _qcenter of circle C, radius sigma, u, D, D _σparameter;

$\left\{\begin{array}{c}{u}_k=\underset{k}{\&Integral;}\mathrm{kF}(a,b)\mathrm{dk},\\ {\mathrm{\&sigma;}}_k^2=\underset{k}{\&Integral;}{(u_k-k)}^{2}F(a,b)\mathrm{dk}\end{array}\right.,k=a,b---\left(1\right)$

$\left\{\begin{array}{c}C=(u_a,u_b)\\ \mathrm{\&sigma;}=\sqrt{{{\mathrm{\&sigma;}}_a}^2+{{\mathrm{\&sigma;}}_b}^2}\end{array}\right.---\left(2\right)$

$\left\{\begin{array}{c}u=\sqrt{{u_a}^2+{u_b}^2}\\ D=u-\mathrm{\&sigma;}\\ D_{\mathrm{\&sigma;}}=D/\mathrm{\&sigma;}\end{array}\right.---\left(3\right)$

In formula (3), u is the distance of the round center of circle C of this equivalence apart from neutral axis (a=0, b=0), and D is the distance of the outer lateral extent neutral axis of circle of equal value, D _σrepresent that this two-dimensional histogram circle of equal value departs from the degree of neutral axis: D _σbe worth greatlyr, show that this image histogram departs from neutral axis more serious;

Step 2, judges image colour cast situation for the first time: in the time meeting formula (4), think that the ab two dimensional surface histogram of image is assembled, and be temporarily colour cast image by graphic collection, otherwise, tentatively assert that image is non-colour cast image, execution step step 3;

(D>10and D _σ>0.6)or(D _σ>1.5) (4)

Step 3, solves the NNO region of image; Theoretical foundation: the no color differnece surface in image scene can be reflected the color of incident illumination in scene completely; Extract the gray face in scene, by the colour cast situation of gray face, draw the drift condition of the illumination of image; Method is as follows: if Img_NNO (i, j) pixel is NNO area pixel:

Wherein L, a, b are three component information of image at Lab chrominance space, and d is the colourity radius maximum of testing image Img_sur in Lab chrominance space; Restriction d place pixel and each NNO area pixel point Img_NNO (i, j) are non-isolated pixel point.

5. be applied to as described in claim 1 the image colour cast detection method of intelligent terminal, it is characterized in that, it is supplementing and proofreading and correct last result that non-colour cast image detects again, step is: the two-dimensional histogram circle of equal value that generates respectively source images and NNO area image, quantization threshold, reduced parameter, output detections result: essential colour cast, true colour cast, without colour cast.

6. the image colour cast detection method that is applied to as described in claim 5 intelligent terminal, is characterized in that, the concrete grammar that non-colour cast image detects again comprises:

Step 1, solves the corresponding circle D of equal value of two-dimensional histogram to result images _σthe parameter of NNO, the parameters of contrast source images circle of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, carries out secondary judgement from the variation tendency of both parameters to non-focused image or non-colour cast image;

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crimage two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively, quantized image is in the two-dimensional histogram that extracts front and back, NNO region round situation of change of equal value effectively, the isoparametric amplitude of variation of two-dimensional histogram circle of equal value σ, u of normal non-colour cast image source image and NNO area image is larger, the equivalence circle parameter that is the NNO area image of normal non-colour cast image changes greatly than the equivalence circle parameter of source images, and this characteristic conforms is normally without the color characteristic of colour cast image; Meanwhile, colour cast image is less in σ, the u parameter value variation amplitude of extracting front and back, NNO region, and the NNO area image of colour cast image has the color characteristic of colour cast equally; So realizing the method for non-colour cast Images Classification by the variation of analysis σ, u parameter value is that effectively setup parameter threshold value is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively;

Step 2, the image that is judged to be for the first time colour cast image is classified:

By the histogram distribution information of utilizing image at the L of Lab chrominance space component, image is classified first; In the time that picture material is obvious essential colour cast, the histogram distribution of the L component of Lab chrominance space presents zonal gathering and distributes; And picture material is while being true colour cast, the histogram distribution of the L component of Lab chrominance space is rendered as more uniform discrete distribution; In the following way the L component of image is processed:

When certain pixel occurrence number in L histogram of component lower than the highest pixel occurrence number of occurrence number 1% time, by the pixel count zero setting of this pixel; L histogram of component after treatment of judgement, the minimum pixel that pixel occurrence number is non-vanishing and maximum pixel across interval whether be less than 80% at the proportion of the whole pixel range of L component;

In the time that non-zero number of times region that pixel is crossed over is less than or equal to whole pixel range 80%, judge that this image colour cast type is essential colour cast; In the time being greater than 80, the judgement of products for further;

To having essential colour cast feature, and picture material is not very single essential colour cast image and true colour cast image, further judges according to the variation of the relative source images of the parameters circle of equal value parameter of the two-dimensional histogram in NNO region circle of equal value; Color constancy; If the distortion of image generation colour cast, NNO region also can embody colour cast feature; If colour cast distortion does not occur image, NNO region should show the feature of normal picture, uses equally formula (6) to classify to colour cast image, and arranging according to different scenes of threshold value adjusted:

Wherein σ _crand u _crcolour cast image two-dimensional histogram radius of a circle σ of equal value and the amplitude index of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively.

7. the image colour cast detection method that is applied to as described in claim 1 intelligent terminal, is characterized in that, this image colour cast detection method that is applied to intelligent terminal specifically comprises the following steps:

Step 1, takes a secondary coloured image Img_sur by possessing the intelligent terminal of camera function, and RGB image is image to be detected;

Step 2, is transformed into Lab chrominance space by source images Img_sur by rgb space, obtains changing rear image I mg_Lab and the view data on L, a, b component;

Step 3, through type (1), the histogram distribution feature of quantitative analysis Img_Lab image under ab two-dimensional color coordinate, and calculate circle E of equal value according to formula (2), (3) _qcenter of circle C, radius sigma, u, D, D _σparameter;

$\left\{\begin{array}{c}{u}_k=\underset{k}{\&Integral;}\mathrm{kF}(a,b)\mathrm{dk},\\ {\mathrm{\&sigma;}}_k^2=\underset{k}{\&Integral;}{(u_k-k)}^{2}F(a,b)\mathrm{dk}\end{array}\right.,k=a,b---\left(1\right)$

$\left\{\begin{array}{c}C=(u_a,u_b)\\ \mathrm{\&sigma;}=\sqrt{{{\mathrm{\&sigma;}}_a}^2+{{\mathrm{\&sigma;}}_b}^2}\end{array}\right.---\left(2\right)$

$\left\{\begin{array}{c}u=\sqrt{{u_a}^2+{u_b}^2}\\ D=u-\mathrm{\&sigma;}\\ D_{\mathrm{\&sigma;}}=D/\mathrm{\&sigma;}\end{array}\right.---\left(3\right)$

In formula (3), u is the distance of the round center of circle C of this equivalence apart from neutral axis (a=0, b=0), and D is the distance of the outer lateral extent neutral axis of circle of equal value, D _σrepresent that this two-dimensional histogram circle of equal value departs from the degree of neutral axis: D _σbe worth greatlyr, show that this image histogram departs from neutral axis more serious;

Step 4, judges image colour cast situation for the first time: in the time meeting formula (4), think that the ab two dimensional surface histogram of image is assembled, and be temporarily colour cast image by graphic collection, execution step seven; Otherwise, tentatively assert that image is non-colour cast image, execution step five;

(D>10and D _σ>0.6)or(D _σ>1.5) (4)

Step 5, solve the NNO region of image, theoretical foundation: the no color differnece surface in image scene can be reflected the color of incident illumination in scene completely, by the colour cast situation of gray face, draw the drift condition of the illumination of image, method is as follows: if Img_NNO (i, j) pixel is NNO area pixel:

Wherein L, a, b are three component information of image at Lab chrominance space, d is the colourity radius maximum of testing image Img_sur in Lab chrominance space, restriction d place pixel and each NNO area pixel point Img_NNO (i, j) are non-isolated pixel point;

Step 6, solves the corresponding circle D of equal value of its two-dimensional histogram to the result images of step 5 _σthe parameter of NNO, the parameters of contrast source images circle of equal value, using formula (6) as the quantitative basis of weighing image parameter variation, carries out secondary judgement from the variation tendency of both parameters to non-focused image or non-colour cast image;

σ _cr＝(σ-σ _NNO)/σ；u _cr＝(u-u _NNO)/u (6)

Wherein, σ _crand u _crimage two-dimensional histogram radius of a circle σ of equal value and the amplitude of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively, quantized image is in the two-dimensional histogram that extracts front and back, NNO region round situation of change of equal value effectively, there is good parameter role of delegate, the two-dimensional histogram circle of equal value σ of normal non-colour cast image source image and NNO area image, the isoparametric amplitude of variation of u is larger, the equivalence circle parameter that is the NNO area image of normal non-colour cast image changes greatly than the equivalence circle parameter of source images, this characteristic conforms is normally without the color characteristic of colour cast image, simultaneously, colour cast image is less in σ, the u parameter value variation amplitude of extracting front and back, NNO region, it is the color characteristic that the NNO area image of colour cast image has colour cast equally, so, realizing the method for non-colour cast Images Classification by the variation of analysis σ, u parameter value is that effectively setup parameter threshold value is as follows:

As image NNO region circle of equal value parameter D _σwhen NNO<-0.5, or, when the amplitude that σ, u parameter change before and after extracting NNO region exceedes respectively 70% and 60%, judge that image is normal non-colour cast image; As image NNO region circle of equal value parameter D _σwhen NNO>0.5, or the amplitude that σ, u parameter change before and after extracting NNO region lower than 40% and 30% time, judges that image is colour cast image respectively;

Step 7, the image that is judged to be for the first time colour cast image is classified:

By the histogram distribution information of utilizing image at the L of Lab chrominance space component, image is classified first, in the time that picture material is obvious essential colour cast, the histogram distribution of the L component of Lab chrominance space presents zonal gathering and distributes; And picture material is while being true colour cast, the histogram distribution of the L component of Lab chrominance space is rendered as more uniform discrete distribution, in the following way the L component of image is processed:

When certain pixel occurrence number in L histogram of component lower than the highest pixel occurrence number of occurrence number 1% time, by the pixel count zero setting of this pixel;

L histogram of component after treatment of judgement, the minimum pixel that pixel occurrence number is non-vanishing and maximum pixel across interval whether be less than 80% at the proportion of the whole pixel range of L component:

In the time that non-zero number of times region that pixel is crossed over is less than or equal to whole pixel range 80%, judge that this image colour cast type is essential colour cast;

In the time being greater than 80, the judgement of products for further;

To thering is essential colour cast feature, and picture material is not very single essential colour cast image and true colour cast image, further judge according to the variation of the relative source images of the parameters circle of equal value parameter of the two-dimensional histogram in their NNO region circle of equal value, color constancy, if the distortion of image generation colour cast, NNO region also can embody colour cast feature; If colour cast distortion does not occur image, NNO region should show the feature of normal picture, uses equally formula (6) to classify to colour cast image, and wherein, arranging according to different scenes of threshold value adjusted:

Wherein σ _crand u _crcolour cast image two-dimensional histogram radius of a circle σ of equal value and the amplitude index of distance of center circle from distance u relative Self-variation before and after extraction NNO region of initial point are represented respectively; ;

Step 8, is embedded into the program of the method in mobile terminal capable of taking pictures, and the picture that equipment is obtained detects in real time, and this program can be fed back testing result, i.e. the evaluation in performance aspect color to this hardware.

8. an image colour cast detection system that is applied to intelligent terminal, is characterized in that, this image colour cast detection system that is applied to intelligent terminal comprises: colour cast Images Classification module, non-colour cast image module, intelligent Android system mobile phone;

On the main interface of intelligent Android system mobile phone A pp, place three control: ImageView, for the image that shows that camera obtains, be exactly source images to be evaluated; TextView, provides the evaluation result of image, and whether the image obtaining by this mobile phone exists colour cast, and is the colour cast of which kind of type; Button, arranges monitoring event onClick, and when after trigger event, the camera-enabled that calling mobile phone is built-in, after getting image and detect, and shows result feedback to TextView.