CN102881001A - Device and method for converting color image into grey scale image - Google Patents
Device and method for converting color image into grey scale image Download PDFInfo
- Publication number
- CN102881001A CN102881001A CN2011101959055A CN201110195905A CN102881001A CN 102881001 A CN102881001 A CN 102881001A CN 2011101959055 A CN2011101959055 A CN 2011101959055A CN 201110195905 A CN201110195905 A CN 201110195905A CN 102881001 A CN102881001 A CN 102881001A
- Authority
- CN
- China
- Prior art keywords
- axis
- projection
- gray level
- image
- level image
- 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
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a device and method for converting a color image into a grey scale image. The method comprises the steps as follows: (a), an initial projection axis is chosen from an image space of the color image; (b), the color image is converted into the grey scale image by utilizing the projection axis; (c), a grey scale image evaluating indicator of the grey scale image is determined; (d), the projection axis is changed, and the Step (b) to the Step (d) are repeated till a set of the projection axes covers a preset range of the image space, so that the grey scale images and the grey scale image evaluating indicators corresponding to the grey scale images respectively are obtained; and (e) the optimum grey scale image evaluating indicator in the grey scale image evaluating indicators is determined, and the grey scale image corresponding to the optimum grey scale image evaluating indicator is determined to be the grey scale image that the color image is required to be converted to.
Description
Technical field
The present invention relates to the image recognition technology field, relate in particular to the technical field that coloured image is converted to gray level image.
Background technology
Common coloured image gray processing method is not considered the concrete condition of target image mostly.Useful Information is lost behind the gray processing of being everlasting in a lot of images.For character recognition and file and picture processing, the identifying information between prospect (literal) and the background need to obtain to keep in gray processing.Identifying information is few between prospect and background has harmful effect for character recognition precision and file and picture Disposal quality.Thus, the performance of common coloured image gray processing method in character recognition and file and picture processing is general.
Summary of the invention
The present invention proposes in view of the above-mentioned situation of prior art, in order to overcome or to alleviate the one or more of shortcomings that the defective because of prior art causes, provides at least a kind of useful selection.
To achieve these goals, according to an aspect of the present invention, provide a kind of method that coloured image is converted to gray level image, described method comprises following step: a, chooses initial axis of projection in the image space of described coloured image; B, utilize described axis of projection, described coloured image is converted to gray level image; C, determine the gray level image evaluation index of described gray level image; D, the described axis of projection of conversion; Repeating said steps b-d until the set of axis of projection has covered the preset range of described image space, thereby obtains a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes; E, determine the gray level image evaluation index of the best in a plurality of gray level image evaluation indexes, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
According to a further aspect in the invention, provide a kind of device that coloured image is converted to gray level image, described device comprises: initial axis of projection selected cell, and it chooses initial axis of projection in the image space of described coloured image; Converting unit, it utilizes described axis of projection, and described coloured image is converted to gray level image; Gray level image evaluation index determining unit is determined the gray level image evaluation index of described gray level image; The axis of projection converter unit, the described axis of projection of its conversion; The coverage control module, determine whether the set of axis of projection has covered the preset range of described image space, and when the set of determining axis of projection does not cover the preset range of described image space, make described converting unit, described gray level image evaluation index determining unit, the work of described axis of projection converter unit iterative cycles, until the set of described axis of projection has covered the preset range of described image space, thereby obtain a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes; Optimum gradation image determining unit, determine the gray level image evaluation index of the best in described a plurality of gray level image evaluation index, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
Should be noted that term " comprises/comprise/have " existence that refers to feature, important document, step or assembly when this paper uses, but do not get rid of the existence of one or more further feature, important document, step or assembly or additional.
Above general remark and all be schematically below in conjunction with the detailed description of accompanying drawing is not the restriction to protection scope of the present invention.
Description of drawings
From referring to the accompanying drawing detailed description of the present invention, will more clearly understand above and other purpose of the present invention, feature and advantage.In the accompanying drawings, same or similar label is indicated same or similar element.
Fig. 1 has schematically shown the process flow diagram according to the method for gray level image that coloured image is converted to of one embodiment of the present invention.
Fig. 2 has schematically shown the process flow diagram according to the method for gray level image that coloured image is converted to of another embodiment of the invention.
Fig. 3 has schematically shown the process flow diagram according to the method for definite initial axis of projection of another embodiment of the present invention.
Fig. 4 has schematically shown an embodiment who carries out the embodiment of local space search according to the employing double-throw axis of shadow of one embodiment of the present invention.
Fig. 5 has schematically shown the method for the embodiment that provides according to Fig. 4 of the present invention and the Contrast on effect of common coloured image gray processing method.
Fig. 6 has schematically shown the block diagram that coloured image is converted to the device of gray level image according to one embodiment of the present invention.
Fig. 7 has schematically shown the block diagram that coloured image is converted to the device of gray level image according to one embodiment of the present invention.
Fig. 8 shows the schematic block diagram that can be used for implementing according to the computing machine of the method and apparatus of the embodiment of the invention.
Embodiment
With reference to the accompanying drawings embodiments of the present invention are described in detail.
Fig. 1 has schematically shown the process flow diagram according to the method for gray level image that coloured image is converted to of one embodiment of the present invention.
As shown in Figure 1, at first at step S102, determine initial axis of projection.This initial axis of projection can be determined at random, perhaps preassigned axis of projection can be defined as initial axis of projection, and for example rgb space cube diagonal axis is set to initial axis of projection.Alternatively, for example can be with the foreground center (for example foreground cluster centre) of coloured image and the line between background colour center (for example background colour cluster centre) as initial axis of projection.In this case, need at first to determine foreground center and the background colour center of coloured image, then determine the line at this foreground center and background colour center.
Then, at step S104, according to initial axis of projection coloured image is converted to gray level image.For example each axis of projection can corresponding projective transformation, and with the be projected as example of rgb space to gray space, the projective transformation of gray processing is calculated according to the formula that is similar to G=a*R+b*G+c*B, and the rgb value of each pixel is converted into gray-scale value.A wherein, b, c are coefficient.It is well-known to those skilled in the art utilizing axis of projection that coloured image is converted to gray level image, thereby this paper will not describe in detail.
Then, at step S106, calculate the gray level image evaluation index of the next gray level image of conversion.In one embodiment, the described gray level image evaluation index inter-class variance that is gray level image.The computing method of the inter-class variance of gray level image have a variety of, for example can adopt following method to calculate inter-class variance:
M wherein
0And m
1Represent respectively the gray average of prospect and background pixel, and
Represent the gray average of all pixels.In the embodiment of alternative, can calculate foreground center and the background colour center of this gray level image, and calculate the distance between this prospect cluster centre and the background cluster centre.The method of cluster or the method for binaryzation be can utilize, the center of foreground and the center of background colour determined.For example when adopting the method for cluster, the cluster centre of foreground and the cluster centre of background colour are respectively the center of foreground and the center of background colour.
In another embodiment, can be with the gray variance of gray level image as the gray level image evaluation index.Calculate the quadratic sum of difference of the gray-scale value subtracted image average gray value gained of each pixel in the gray level image, then with this quadratic sum divided by total number of pixels, can obtain the gray variance of this gray level image.In another embodiment, can be with the gray standard deviation of gray level image as the gray level image evaluation index.Calculate first gray variance, to this gray variance extraction of square root, can obtain the gray standard deviation of this gray level image.
Above gray level image evaluation index only is exemplary, is not exclusiveness.Those skilled in the art can be according to the spirit of this paper, can indicate any index of the distance between the foreground and background colour in the gray space, as the gray level image evaluation index.This is because this paper intention in the gray processing process of coloured image, farthest pushes away foreground and the background colour of coloured image.
Then, at step S108, the conversion axis of projection namely changes this axis of projection.In one embodiment, for example choose parallel with original axis of projection and at a distance of the straight line of preset distance as new axis of projection, perhaps select the straight line of the angle that becomes to be scheduled to original axis of projection as new axis of projection.
Then, in step S110, according to the axis of projection after the conversion coloured image is converted to gray level image.This step and step S104 are basic identical, and just axis of projection is different.
Then, at step S112, calculate the gray level image evaluation index of resulting gray level image.
Then judge in step S114 whether the set (comprising in initial axis of projection and the primitive axis neighborhood other axis of projection that sampling (conversion) obtains) of used axis of projection has covered the predetermined spatial dimension of image space (for brevity, hereinafter be also referred to as judge whether axis of projection has covered the spatial dimension of being scheduled to of image space).In one embodiment, described predetermined space scope can be the whole image space of coloured image.In another embodiment, described predetermined space scope is the part in the whole image space of described coloured image.
If axis of projection does not also have predetermined spatial dimension (the step S114 in overlay image space, no), then process and return step S108, the conversion axis of projection, and according to the axis of projection after the conversion coloured image is converted to gray level image (S110), calculate the gray level image evaluation index of this gray level image, and proceed to step S114 at this and judge.
If axis of projection has covered the predetermined spatial dimension (step S114 is) of image space, then process proceeding to step S116.In step S116, in step S106 and the determined numerous gray level image evaluation indexes of step S112, determine best gray level image evaluation index.For example when this gray level image evaluation index was inter-class variance, best gray level image evaluation index was maximum inter-class variance.When this gray level image evaluation index be between foreground center and the background colour center apart from the time, best gray level image evaluation index is maximum prospect cluster centre and the distance between the background cluster centre.When this gray level image evaluation index gray variance that is gray level image or gray standard deviation, best gray level image evaluation index is maximum gray variance or gray standard deviation.In step S116, the gray level image that also will have this best gray level image evaluation index is defined as final gray level image.
Fig. 2 has schematically shown the process flow diagram according to the method for gray level image that coloured image is converted to of another embodiment of the invention.
The process flow diagram of Fig. 2 is compared with the process flow diagram of Fig. 1, can know, in embodiment shown in Figure 2, increased step S201.Step S201 with the RGB color space conversion of coloured image to the spherical coordinates space (ρ, θ,
).Initial point is the cubical center of rgb space.Then in step S102, in the spherical coordinates space, determine initial axis of projection, in step S108, carry out the axis of projection conversion in the spherical coordinates space.Other step and Fig. 1's is basic identical, thereby this paper repeats no more.
With the RGB color space coordinate system of coloured image be transformed into spherical coordinate system (ρ, θ,
), in the spherical coordinates space, carry out the axis of projection conversion, the uniform conversion of axis of projection can be realized, thereby performance can be improved.
Fig. 3 has schematically shown the process flow diagram according to the method for definite initial axis of projection of another embodiment of the present invention.
As shown in Figure 3, at first at step S302, determine initial the first axis of projection.For example can by described coloured image is carried out color cluster, determine foreground cluster centre and background colour cluster centre.Then with the line between described foreground cluster centre and the background colour cluster centre as initial the first axis of projection.Then at step S304, determine that the axis of projection different from initial the first axis of projection is as initial the second axis of projection.For example with the diagonal line of described rgb space as initial the second axis of projection.
In this embodiment of determining two axis of projections, can carry out step S104 to the processing of S114 for the first initial axis of projection and the second initial axis of projection respectively.In step S114, when judging for the first axis of projection, judge whether the set of used all the first axis of projections has covered the first preset range of color space, when judging for the second axis of projection, judge whether the set of used all the second axis of projections has covered the second preset range of color space, and described the first preset range and the second preset range have consisted of the preset range among the step S114.
The two initial axis of projections of utilization are searched for, and gray processing exchanging shaft search volume are restricted to the adjacent domains of two initial axis of projections, can improve the search speed of the optimum axis of projection of searching for the greyscale transformation of carrying out coloured image.
Further, the present inventor has been found that, by with the line between described foreground center and the background colour center as initial the first axis of projection, and with the diagonal line of described rgb space as initial the second axis of projection, both can obtain to be in close proximity to the optimal result of total space search, can significantly save search time again, improve search speed, the improvement amplitude reaches decades of times.
The invention is not restricted to the situation of two axis of projections, and three or more axis of projections can be arranged.These axis of projections can rule of thumb be determined.And in preferred embodiment, these axis of projections are not parallel to each other.
Fig. 4 has schematically shown an embodiment who carries out the embodiment of local space search according to the employing double-throw axis of shadow of one embodiment of the present invention.In this embodiment, at first the coloured image rgb space is transformed into the spherical coordinates space (ρ, θ,
), initial point is the cubical center of rgb space.Then determine two initial axis of projections.These two initial axis of projections are respectively RGB cube diagonal axis and the two class cluster lines of centres:
A
0The initial parameter that represents the first axis of projection.θ
0Be the folded angle of the first axis of projection and z axle forward,
For from positive z axle from the x axle by the angle that counterclockwise forwards the projection of the first axis of projection at coordinate plane xoy to and turn over.
A
1The initial parameter that represents the first axis of projection.θ
1Be the folded angle of the first axis of projection and z axle forward,
For from positive z axle from the x axle by the angle that counterclockwise forwards the projection of the first axis of projection at coordinate plane xoy to and turn over.
Then obtain gray level image according to initial axis of projection (the first axis of projection and the second axis of projection), and calculate the inter-class variance between the gray level image.The conversion axis of projection, and repeat above-mentioned step, thus obtain a plurality of gray level images and the inter-class variance corresponding with described a plurality of volume gray level images.The hunting zone is limited in the proximity space of two initial axis of projections:
Suppose to use blanketly
Conversion axis of projection in the expression spherical coordinate.
For based on axis of projection
The gray level image that obtains.
The expression gray level image
On inter-class variance.Then the optimization aim function is:
At last, determine last gray level image according to optimum inter-class variance.
As can be seen from Figure 4 with prospect and background to the axis of projection projection, overlapping minimum or be separated by farthest between two line segments that optimum axis of projection forms, can obtain separability best between prospect and background to optimum axial projection.
Fig. 5 has schematically shown the method for the embodiment that provides according to Fig. 4 of the present invention and the Contrast on effect of common coloured image gray processing method.
Fig. 5 A shows the former figure of coloured image.Fig. 5 B shows the result who adopts after conventional method is carried out gray processing.Fig. 5 C shows the result who adopts after the present invention's method shown in Figure 4 is carried out gray processing.Contrast Fig. 5 B and Fig. 5 C, visible more clear according to the resulting gray level image of method of the present invention.
Fig. 6 has schematically shown the block diagram that coloured image is converted to the device of gray level image according to one embodiment of the present invention.
As shown in Figure 6, according to one embodiment of the present invention, the device that coloured image is converted to gray level image comprises initial axis of projection selected cell 601, converting unit 602, gray level image evaluation index determining unit 603, axis of projection converter unit 604, coverage control module 605 and optimum gradation image determining unit 606.
Initial axis of projection selected cell 601 is chosen initial axis of projection in the image space of described coloured image.Converting unit 602 is utilized described axis of projection, and described coloured image is converted to gray level image.Gray level image evaluation index determining unit 603 is determined the gray level image evaluation index of described gray level image.The described axis of projection of axis of projection converter unit 604 conversion.Coverage control module 605 determines whether the set of used axis of projection has covered the preset range of described image space, and when the set of determining used axis of projection does not cover the preset range of described image space, make described converting unit, gray level image evaluation index determining unit and the cycling of axis of projection converter unit, until the set of described used axis of projection covers till the preset range of described image space, thereby obtain a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes.Optimum gradation image determining unit is determined the gray level image evaluation index of the best in described a plurality of gray level image evaluation index, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
Described gray level image evaluation index can be one or more of in the following index: the inter-class variance of gray level image; The foreground center of gray level image and the distance between the background colour center; The gray variance of gray level image; And the gray standard deviation of gray level image.The calculating of these indexs can be described referring to preamble.
Fig. 7 has schematically shown the block diagram that coloured image is converted to the device of gray level image according to one embodiment of the present invention.As shown in Figure 7, according to another embodiment of the invention, the device that coloured image is converted to gray level image also comprises coordinate transformation unit 701, and coordinate transformation unit 701 is converted to the spherical coordinates space with the coordinate space of described coloured image from rgb space.
In this case, axis of projection converter unit 604 by two angles in the spherical coordinates space of the described axis of projection of conversion (be θ and
), come the described axis of projection of conversion.As previously mentioned, the RGB color space coordinate system with coloured image is transformed into spherical coordinate system
In the spherical coordinates space, carry out the axis of projection conversion, can realize the uniform conversion of axis of projection, thereby can improve performance.
In one embodiment, described axis of projection converter unit with two angles in the spherical coordinates space of described axis of projection (be θ and
) progressively even conversion 360 is spent respectively, thereby cover whole spherical coordinates space.Cover whole image spaces and can improve the precision of processing.
In another kind of aforesaid way, described axis of projection converter unit with two angles in the spherical coordinates space of described axis of projection (be θ and
) the even predetermined angle (such as 205 degree, 245 degree, 275 degree etc.) of conversion progressively respectively, thereby only cover the preset range in the spherical coordinates space of coloured image.
In another embodiment, initial axis of projection selected cell 601 is chosen mutually different two or more initial axis of projections, converting unit 602, gray level image evaluation index determining unit 603, axis of projection converter unit 604 carry out work for initial axis of projection selected cell 601 determined primitive axis respectively, and described coverage control module arranges respectively the predetermined coverage separately of described two or more axis of projections.
Utilize this embodiment, can and process between the load and obtain better compromise in conversion accuracy and slewing rate.
In one embodiment, the foreground center of the described coloured image of initial axis of projection selected cell 601 selections and the line between the background colour center are as initial the first axis of projection, and with the diagonal line of the rgb space of described coloured image as initial the second axis of projection, converting unit 602, gray level image evaluation index determining unit 603, axis of projection converter unit 604 carry out work for initial axis of projection selected cell 601 determined primitive axis respectively.Particularly, described axis of projection converter unit is described the first axis of projection of conversion and described the second axis of projection respectively, described converting unit is respectively for described the first axis of projection and the second axis of projection with through described the first axis of projection and second axis of projection of conversion, carry out described coloured image to the conversion of gray level image, described coverage control module arranges respectively the predetermined coverage of described the first axis of projection and described the second axis of projection.
Should be noted that in this article, to the description of device and to the description of method can cross-reference, mutual understanding.The feature that occurs in one embodiment can be applied to another embodiment in same or similar mode, and the feature or the feature in this another embodiment that replace in this another embodiment are used.
According to the embodiment of the present invention, in the process with the coloured image gray processing, foreground and the background colour of coloured image are farthest pushed away, thereby can realize that gray level image goes forward to have best separability between background, thus keep more behind the gray processing before the background identifying information.This helps to improve the effect such as character recognition and file and picture processing.
In addition, according to the embodiment of the present invention, utilize the method for two initial axis of projections or many initial axis of projection search to improve coloured image gray processing exchanging shaft search speed.By the two initial axis of projection adjacent domain that the restriction of gray processing exchanging shaft search volume is selected in the method, both can obtain to be in close proximity to the optimal result of total space search, can significantly save search time again, improve search speed, the improvement amplitude reaches decades of times.
The above apparatus and method of the present invention can be realized by hardware, also can be realized in conjunction with software by hardware, firmware.For example abovely the present invention relates to such logical block readable program, when this program during by logical block performed (the directly rear execution such as execution or explanation, compiling), can make this logical block realize device or component parts mentioned above, or make this logical block realize the whole bag of tricks or step mentioned above.The processor that uses in logical block such as field programmable logic parts, ASIC (application specific integrated circuit), DSP (digital signal processor), microprocessor, the computing machine etc.The invention still further relates to be used to the storage medium of storing above program, such as hard disk, disk, CD, DVD, flash, magneto-optic disk, storage card, memory stick etc.
Fig. 8 shows the schematic block diagram that can be used for implementing according to the computing machine of the method and apparatus of the embodiment of the invention.
In Fig. 8, CPU (central processing unit) (CPU) 801 carries out various processing according to the program of storage in the ROM (read-only memory) (ROM) 802 or from the program that storage area 808 is loaded into random access memory (RAM) 803.In RAM 803, also store as required data required when CPU 801 carries out various processing etc.CPU 801, ROM 802 and RAM 803 are connected to each other via bus 804.Input/output interface 805 also is connected to bus 804.
Following parts are connected to input/output interface 805: importation 806 (comprising keyboard, mouse etc.), output 807 (comprise display, such as cathode-ray tube (CRT) (CRT), liquid crystal display (LCD) etc., with loudspeaker etc.), storage area 808 (comprising hard disk etc.), communications portion 809 (comprising that network interface unit is such as LAN card, modulator-demodular unit etc.).Communications portion 809 is processed such as the Internet executive communication via network.As required, driver 810 also can be connected to input/output interface 805.Detachable media 811 can be installed on the driver 810 as required such as disk, CD, magneto-optic disk, semiconductor memory etc., so that the computer program of therefrom reading is installed in the storage area 808 as required.
In the situation that realize above-mentioned series of processes by software, such as detachable media 811 program that consists of software is installed such as the Internet or storage medium from network.
It will be understood by those of skill in the art that this storage medium is not limited to shown in Figure 8 wherein has program stored therein, distributes separately to provide the detachable media 811 of program to the user with equipment.The example of detachable media 811 comprises disk (comprising floppy disk (registered trademark)), CD (comprising compact disc read-only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk (comprising mini-disk (MD) (registered trademark)) and semiconductor memory.Perhaps, storage medium can be hard disk that comprises in ROM 802, the storage area 808 etc., computer program stored wherein, and be distributed to the user with the equipment that comprises them.
In a word, embodiments of the present invention provide the technical scheme in the following remarks at least.
Remarks 1, a kind of method that coloured image is converted to gray level image, described method comprises following step:
A, in the image space of described coloured image, choose initial axis of projection;
B, utilize described axis of projection, described coloured image is converted to gray level image;
C, determine the gray level image evaluation index of described gray level image;
D, the described axis of projection of conversion; Repeating said steps b-d until the set of axis of projection has covered the preset range of described image space, thereby obtains a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes;
E, determine the gray level image evaluation index of the best in a plurality of gray level image evaluation indexes, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
Remarks 2, according to remarks 1 described method, wherein, described gray level image evaluation index is one or more of in the following index:
The inter-class variance of gray level image;
The foreground center of gray level image and the distance between the background colour center;
The gray variance of gray level image; And
The gray standard deviation of gray level image.
Remarks 3, according to remarks 1 described method, wherein, described method also comprises the step that the coordinate space of described coloured image is converted to the spherical coordinates space from rgb space.
Remarks 4, according to remarks 3 described methods, wherein, in described steps d, two angles in the spherical coordinates space of the described axis of projection of conversion, thereby the described axis of projection of conversion.
Remarks 5, according to remarks 4 described methods, wherein, with two angles in the spherical coordinates space of described axis of projection even conversion 360 degree progressively respectively, thereby cover whole spherical coordinates space.
Remarks 6, according to remarks 1 described method, wherein, in described step a, choose mutually different two or more initial axis of projections,
Described step b carries out for described two or more axis of projections respectively to steps d, and the predetermined coverage separately of described two or more axis of projections is set respectively.
Remarks 7, according to remarks 1 or remarks 3 described methods, wherein, in described step a, select the foreground center of described coloured image and the line between the background colour center as initial the first axis of projection, and with the diagonal line of the rgb space of described coloured image as initial the second axis of projection, described step b-d carries out for described the first axis of projection and described the second axis of projection respectively, and the predetermined coverage separately of described two or more axis of projections is set respectively.
Remarks 8, a kind of device that coloured image is converted to gray level image, described device comprises:
Initial axis of projection selected cell, it chooses initial axis of projection in the image space of described coloured image;
Converting unit, it utilizes described axis of projection, and described coloured image is converted to gray level image;
Gray level image evaluation index determining unit is determined the gray level image evaluation index of described gray level image;
The axis of projection converter unit, the described axis of projection of its conversion;
The coverage control module, determine whether the set of axis of projection has covered the preset range of described image space, and when the set of determining axis of projection does not cover the preset range of described image space, make described converting unit, described gray level image evaluation index determining unit, the work of described axis of projection converter unit iterative cycles, until the set of described axis of projection has covered the preset range of described image space, thereby obtain a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes;
Optimum gradation image determining unit, determine the gray level image evaluation index of the best in described a plurality of gray level image evaluation index, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
Remarks 9, according to remarks 8 described devices, wherein, described gray level image evaluation index is one or more of in the following index:
The inter-class variance of gray level image;
The foreground center of gray level image and the distance between the background colour center;
The gray variance of gray level image; And
The gray standard deviation of gray level image.
Remarks 10, according to remarks 8 described devices, wherein, described device also comprises:
Coordinate transformation unit is converted to the spherical coordinates space with the coordinate space of described coloured image from rgb space.
Remarks 11, according to remarks 10 described devices, wherein, described axis of projection converter unit comes the described axis of projection of conversion by two angles in the spherical coordinates space of the described axis of projection of conversion.
Remarks 12, according to remarks 11 described devices, wherein, described axis of projection converter unit is two angles in the spherical coordinates space of described axis of projection even conversion 360 degree progressively respectively, thereby covers whole spherical coordinates space.
Remarks 13, according to remarks 8 described devices, wherein, described initial axis of projection selected cell is chosen mutually different two or more initial axis of projections,
Described axis of projection converter unit is described two or more axis of projections of conversion respectively, the described converting unit of described axis of projection is respectively for described two or more axis of projections with through described two or more axis of projections of conversion, carry out described coloured image to the conversion of gray level image, described coverage control module arranges respectively the predetermined coverage separately of described two or more axis of projections.
Remarks 14, according to remarks 8 or remarks 10 described devices, wherein, described initial axis of projection selected cell selects the foreground center of described coloured image and the line between the background colour center as initial the first axis of projection, and with the diagonal line of the rgb space of described coloured image as initial the second axis of projection, described axis of projection converter unit is described the first axis of projection of conversion and described the second axis of projection respectively, described converting unit is respectively for described the first axis of projection and the second axis of projection with through described the first axis of projection and second axis of projection of conversion, carry out described coloured image to the conversion of gray level image, described coverage control module arranges respectively the predetermined coverage of described the first axis of projection and described the second axis of projection.
Remarks 15, a kind of logical block readable program, described readable program when being carried out by described logical block, or through explain and/or compiling after when carrying out, can make described logical block realize remarks 1 to 7 described method or as the described device of remarks 8-14.
Remarks 16, the readable tangible storage medium of a kind of logical block, it stores remarks 15 described logical block readable programs.
Invention has been described for the concrete embodiment of above combination, but it will be apparent to those skilled in the art that these descriptions all are exemplary, is not limiting the scope of the invention.Those skilled in the art can make various variants and modifications to the present invention according to spirit of the present invention and principle, and these variants and modifications also within the scope of the invention.
Claims (10)
1. method that coloured image is converted to gray level image, described method comprises following step:
A, in the image space of described coloured image, choose initial axis of projection;
B, utilize described axis of projection, described coloured image is converted to gray level image;
C, determine the gray level image evaluation index of described gray level image;
D, the described axis of projection of conversion; Repeating said steps b-d until the set of used axis of projection has covered the predetermined space scope of described image space, thereby obtains a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes;
E, determine the gray level image evaluation index of the best in a plurality of gray level image evaluation indexes, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
2. method according to claim 1, wherein, described gray level image evaluation index is one or more of in the following index:
The inter-class variance of gray level image;
The foreground center of gray level image and the distance between the background colour center;
The gray variance of gray level image; And
The gray standard deviation of gray level image.
3. method according to claim 1, wherein, described method also comprises the step that the coordinate space of described coloured image is converted to the spherical coordinates space from rgb space.
4. method according to claim 3, wherein, in described steps d, two angles in the spherical coordinates space of the described axis of projection of conversion, thereby the described axis of projection of conversion.
5. method according to claim 4 wherein, with two angles in the spherical coordinates space of described axis of projection even conversion 360 degree progressively respectively, thereby covers whole spherical coordinates space.
6. method according to claim 1 wherein, in described step a, is chosen mutually different two or more initial axis of projections,
Described step b carries out for described two or more axis of projections respectively to steps d, respectively for described two or more axis of projections, the predetermined space scope of described image space is set.
7. method according to claim 1, wherein, in described step a, select the foreground center of described coloured image and the line between the background colour center as initial the first axis of projection, and with the diagonal line of the rgb space of described coloured image as initial the second axis of projection, described step b-d carries out for described the first axis of projection and described the second axis of projection respectively, and the predetermined coverage separately of described two or more axis of projections is set respectively.
8. device that coloured image is converted to gray level image, described device comprises:
Initial axis of projection selected cell, it chooses initial axis of projection in the image space of described coloured image;
Converting unit, it utilizes described axis of projection, and described coloured image is converted to gray level image;
Gray level image evaluation index determining unit is determined the gray level image evaluation index of described gray level image;
The axis of projection converter unit, the described axis of projection of its conversion;
The coverage control module, determine whether the set of used axis of projection has covered the preset range of described image space, and when the set of determining used axis of projection does not cover the preset range of described image space, make described converting unit, described gray level image evaluation index determining unit, described axis of projection converter unit iterative cycles work, until the set of described used axis of projection has covered the preset range of described image space, thereby obtain a plurality of gray level images and corresponding with described a plurality of gray level images respectively a plurality of gray level image evaluation indexes;
Optimum gradation image determining unit, determine the gray level image evaluation index of the best in described a plurality of gray level image evaluation index, and the gray level image corresponding with the gray level image evaluation index of described the best is defined as the gray level image that described coloured image should be converted to.
9. device according to claim 8, wherein, described device also comprises:
Coordinate transformation unit is converted to the spherical coordinates space with the coordinate space of described coloured image from rgb space.
10. device according to claim 8, wherein, described initial axis of projection selected cell selects the foreground center of described coloured image and the line between the background colour center as initial the first axis of projection, and with the diagonal line of the rgb space of described coloured image as initial the second axis of projection, described axis of projection converter unit is described the first axis of projection of conversion and described the second axis of projection respectively, described converting unit is respectively for described the first axis of projection and the second axis of projection with through described the first axis of projection and second axis of projection of conversion, carry out described coloured image to the conversion of gray level image, described coverage control module arranges respectively the preset range of described image space for described the first axis of projection and described the second axis of projection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101959055A CN102881001A (en) | 2011-07-13 | 2011-07-13 | Device and method for converting color image into grey scale image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101959055A CN102881001A (en) | 2011-07-13 | 2011-07-13 | Device and method for converting color image into grey scale image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102881001A true CN102881001A (en) | 2013-01-16 |
Family
ID=47482314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011101959055A Pending CN102881001A (en) | 2011-07-13 | 2011-07-13 | Device and method for converting color image into grey scale image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102881001A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992404A (en) * | 2015-08-07 | 2015-10-21 | 深圳市康冠商用科技有限公司 | Method and system for converting color picture image to gray scale image |
| CN106326895A (en) * | 2015-06-16 | 2017-01-11 | 富士通株式会社 | Image processing device and image processing method |
| CN106447603A (en) * | 2016-09-28 | 2017-02-22 | 西安交通大学 | Color image graying method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520845A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Layering method of color document images and device thereof |
| WO2010029932A1 (en) * | 2008-09-09 | 2010-03-18 | 株式会社メガトレード | Visual examination apparatus |
| CN101692313A (en) * | 2009-07-03 | 2010-04-07 | 华东师范大学 | Portable vehicle recognition device base on embedded platform |
| CN101908142A (en) * | 2010-08-04 | 2010-12-08 | 丁天 | Feature analysis-based video flame detecting method |
-
2011
- 2011-07-13 CN CN2011101959055A patent/CN102881001A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520845A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Layering method of color document images and device thereof |
| WO2010029932A1 (en) * | 2008-09-09 | 2010-03-18 | 株式会社メガトレード | Visual examination apparatus |
| CN101692313A (en) * | 2009-07-03 | 2010-04-07 | 华东师范大学 | Portable vehicle recognition device base on embedded platform |
| CN101908142A (en) * | 2010-08-04 | 2010-12-08 | 丁天 | Feature analysis-based video flame detecting method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106326895A (en) * | 2015-06-16 | 2017-01-11 | 富士通株式会社 | Image processing device and image processing method |
| CN106326895B (en) * | 2015-06-16 | 2020-07-07 | 富士通株式会社 | Image processing apparatus, image processing method, and program |
| CN104992404A (en) * | 2015-08-07 | 2015-10-21 | 深圳市康冠商用科技有限公司 | Method and system for converting color picture image to gray scale image |
| CN106447603A (en) * | 2016-09-28 | 2017-02-22 | 西安交通大学 | Color image graying method |
| CN106447603B (en) * | 2016-09-28 | 2019-04-12 | 西安交通大学 | A kind of color image gray processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101131768B (en) | Tile based precision rasterization in a graphics pipeline | |
| CN107067536B (en) | A kind of image boundary determines method, apparatus, equipment and storage medium | |
| EP3048555B1 (en) | Image processing device, image processing method, and image processing program | |
| CN101661622A (en) | Image processing apparatus, image processing method and program | |
| JP2009508239A (en) | Vectorization of color gradient | |
| CN101727580A (en) | Image processing apparatus, electronic medium, and image processing method | |
| US20090180690A1 (en) | Image searching apparatus and image searching method | |
| CN108052869B (en) | Lane line recognition method, lane line recognition device and computer-readable storage medium | |
| CN102968785A (en) | High-speed parallel image matching method based on multi-core digital signal processor (DSP) | |
| CN112825199B (en) | Collision detection method, device, equipment and storage medium | |
| CN108734161A (en) | Recognition methods, device, equipment and the storage medium in crown word number region | |
| CN102881001A (en) | Device and method for converting color image into grey scale image | |
| CN108268504A (en) | A kind of method and apparatus for the region of search for dividing point of interest | |
| CN105373538B (en) | A kind of display level of polygon object determines method and device | |
| JP4854746B2 (en) | Buffer management in vector graphics hardware | |
| CN105677843B (en) | A kind of automatic acquisition ancestor four to attribute method | |
| CN111127590B (en) | Second-order Bezier curve drawing method and device | |
| CN101496392B (en) | Method for selecting an image for insertion into a document | |
| CN113628286B (en) | Video color gamut detection method, device, computing equipment and computer storage medium | |
| CN108388825B (en) | Fast response code searching method and device | |
| US10796435B2 (en) | Image processing method and image processing apparatus | |
| CN111524446B (en) | Data processing method and device, electronic equipment and readable storage medium | |
| CN113051406A (en) | Character attribute prediction method, device, server and readable storage medium | |
| CN112783971A (en) | Transaction recording method, transaction query method, electronic device and storage medium | |
| CN113971694A (en) | Point cloud data processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130116 |