CN106780413B - Image enhancement method and device - Google Patents
Image enhancement method and device Download PDFInfo
- Publication number
- CN106780413B CN106780413B CN201611085142.8A CN201611085142A CN106780413B CN 106780413 B CN106780413 B CN 106780413B CN 201611085142 A CN201611085142 A CN 201611085142A CN 106780413 B CN106780413 B CN 106780413B
- Authority
- CN
- China
- Prior art keywords
- histogram
- gray
- image
- gray level
- point
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000006835 compression Effects 0.000 claims description 32
- 238000007906 compression Methods 0.000 claims description 32
- 230000003044 adaptive effect Effects 0.000 claims description 31
- 238000010606 normalization Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 241001270131 Agaricus moelleri Species 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 210000004872 soft tissue Anatomy 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Studio Devices (AREA)
Abstract
The invention is suitable for medical image processing, and provides an image enhancement method, which comprises the following steps: receiving an interested area image, acquiring a mask area in the interested area, acquiring a gray histogram of each pixel in the mask area, calculating a reference point according to the gray histogram of the mask area, calculating and obtaining a self-adaptive enhancement curve according to the reference point, and stretching the interested area image according to the self-adaptive enhancement curve to obtain an enhanced image. The embodiment of the invention solves the problem that the prior art cannot enhance the image under different external conditions and different processing parameters, so that the processed image cannot achieve the optimal display effect.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to an image enhancement method and device.
Background
After a series of algorithms such as correction, enhancement, noise reduction, equalization and the like are carried out on an X-ray image, the brightness and the contrast of the image are not suitable for direct observation of human eyes, and the brightness and the contrast of the image need to be adjusted once again.
The conventional method for enhancing an X-ray image generally selects a fixed enhancement curve by clinical experience according to conditions such as determined dosage, body position, correction, enhancement and the like, and stretches the gray value of the image before display to achieve the purpose of adjusting brightness and contrast.
Although the conventional enhancement method is simple, when external conditions and post-processing parameters are greatly changed, a fixed enhancement curve is used for gray scale stretching, and the display effect is not ideal and even partial image information can be lost. Meanwhile, the conventional enhancement method cannot adjust the shape of the stretching position of the enhancement curve according to the information of the part of the image to be observed, and has poor adaptability.
Disclosure of Invention
The invention aims to provide an image enhancement method and an image enhancement device, and aims to solve the problems that the shape of the stretching position of an enhancement curve cannot be adjusted according to the information of a part needing to be observed of an image in the conventional image enhancement method, and the adaptability is poor.
The invention is realized in such a way that an image enhancement method comprises the following steps:
receiving an image of an area of interest, acquiring a mask area in the area of interest, and acquiring a gray level histogram of each pixel in the mask area;
calculating a reference point according to the gray level histogram of each pixel in the mask area;
calculating a self-adaptive enhancement curve according to the reference point;
and stretching the image of the region of interest according to the self-adaptive enhancement curve to obtain an enhanced image.
Further, the acquiring a mask region in the region of interest and acquiring a gray histogram of the mask region includes:
acquiring a mask region of the region-of-interest image by using a binarization processing, region growing or threshold segmentation mode;
and counting the gray value of each pixel point in the mask area, and generating a gray histogram of each pixel in the mask area according to the counted gray value.
Further, the generating a gray level histogram of the mask region according to the gray level value obtained by statistics includes:
generating a primary gray level histogram according to the gray level value obtained by statistics;
and merging and compressing the gray scales of the primary gray histogram to 256 gray levels to obtain the gray histogram of the mask region.
Further, the gray histogram of the mask region includes 256 gray levels of 0 level to 255 levels, and the reference point includes a center point and a compression point, the calculating the reference point according to the gray histogram of the mask region includes:
normalizing the gray level histogram of the mask area, and setting the numerical values of 0 level and 255 level of the gray level histogram after normalization processing as 0 to obtain a normalized histogram;
fitting an envelope line of the normalized histogram according to a preset multiple term;
calculating the mean value of the normalized histogram, and segmenting the envelope curve of the fitted normalized histogram by using the mean value of the normalized histogram to obtain a plurality of peaks;
searching a maximum peak from a plurality of peaks, and taking the top point of the maximum peak as a central point;
and acquiring coordinates of the vertexes of the left and right peaks of the maximum peak, calculating the distance from the vertexes of the left and right peaks to the central point, and taking the vertex of the peak farthest away as a compression point.
Further, if the coordinates of the center point are represented by (xm, ym) and the coordinates of the compression point are represented by (xc, yc), then the calculating an adaptive enhancement curve according to the reference point comprises:
representing the adaptive enhancement curve by y, then y ═ a × b × atan c × x-xm + ym; - - - - (1)
Substituting xm ═ ym ═ 0 into the formula of the adaptive enhancement curve, denoted b with c, then:
substituting the formula (2) into the formula (1) for simplification to obtain:
setting the adaptive enhancement curve over a compression point (xc, yc), where yc is expressed by a compression factor xc and cCoeff, yc ≦ xc ≦ cCoeff when xc ≦ xm, and yc ≦ yd- (xd-xc) × cCoeff when xc > xm, where xd ≦ yd ≦ 255;
substituting the coordinates of (xd, yd) and (xc, yc) into equation (3) yields:
calculating a formula (4) to obtain values of three coefficients a, b and c, and substituting the values of a, b and c obtained by solving into the formula (1) to obtain the self-adaptive enhancement curve;
and mapping the gray level input and output range of the self-adaptive enhancement curve to the gray level range of the primary gray level histogram through interpolation operation.
The present invention also provides an image enhancement apparatus, comprising:
the histogram generating unit is used for receiving an image of an interested area, acquiring a mask area in the interested area and acquiring a gray level histogram of each pixel in the mask area;
a reference point calculating unit, configured to calculate a reference point according to a gray level histogram of each pixel in the mask region;
an enhancement curve obtaining unit, configured to calculate an adaptive enhancement curve according to the reference point;
and the image stretching unit is used for stretching the image of the region of interest according to the self-adaptive enhancement curve to obtain an enhanced image.
Further, the histogram generating unit includes:
a mask region acquisition module, configured to acquire a mask region of the region-of-interest image by using binarization processing, region growing, or threshold segmentation;
and the histogram generation module is used for counting the gray value of each pixel point in the mask area and generating a gray histogram of each pixel in the mask area according to the counted gray value.
Further, the histogram generation module includes:
the histogram generation submodule is used for generating a primary gray level histogram according to the gray level value obtained by statistics;
and the histogram processing submodule is used for merging and compressing the gray scales of the primary gray histogram to 256 gray levels to obtain the gray histogram of the mask region.
Further, the reference point calculation unit includes:
the normalization processing module is used for performing normalization processing on the gray level histogram of the mask area and setting the numerical values of 0 level and 255 level of the gray level histogram after the normalization processing to be 0 to obtain a normalization histogram;
the central point top removing module is used for fitting the envelope curve of the normalized histogram according to preset multiple items, calculating the mean value of the normalized histogram, segmenting the fitted envelope curve of the normalized histogram by using the mean value of the normalized histogram to obtain a plurality of peaks, searching the largest peak from the peaks, and taking the peak of the largest peak as the central point;
and the compression point determining module is used for acquiring the coordinates of the vertexes of the left and right peaks of the maximum peak, calculating the distance from the vertexes of the left and right peaks to the central point, and taking the vertex of the peak farthest away as the compression point.
Further, if the coordinates of the central point are represented by (xm, ym) and the coordinates of the compression point are represented by (xc, yc), the enhancement curve obtaining unit is specifically configured to:
representing the adaptive enhancement curve by y, then y ═ a × b × atan c × x-xm + ym; - - - - (5)
Substituting xm ═ ym ═ 0 into the formula of the adaptive enhancement curve, denoted b with c, then:
substituting formula (6) into formula (5) for simplification, we get:
setting the adaptive enhancement curve over a compression point (xc, yc), where yc is expressed by a compression factor xc and cCoeff, yc ≦ xc ≦ cCoeff when xc ≦ xm, and yc ≦ yd- (xd-xc) × cCoeff when xc > xm, where xd ≦ yd ≦ 255;
substituting the coordinates of (xd, yd) and (xc, yc) into equation (7) yields:
calculating a formula (8) to obtain values of three coefficients a, b and c, and substituting the values of a, b and c obtained by solving into a formula (5) to obtain the self-adaptive enhancement curve;
and mapping the gray level input and output range of the self-adaptive enhancement curve to the gray level range of the primary gray level histogram through interpolation operation.
Compared with the prior art, the invention has the beneficial effects that: according to the embodiment of the invention, the mask area of the image of the region of interest is obtained according to the preset mask, the gray histogram of the mask area is obtained, the form of the gray histogram is automatically analyzed according to the obtained gray histogram, the self-adaptive enhancement curve for adjusting the brightness and the contrast is generated, and the image to be processed is stretched by utilizing the self-adaptive enhancement curve to obtain the enhanced image. The embodiment of the invention solves the problem that the prior art cannot enhance the image under different external conditions and different processing parameters, so that the processed image cannot achieve the optimal display effect.
Drawings
Fig. 1 is a flowchart of an image enhancement method according to an embodiment of the present invention;
FIG. 2a is an image of a region of interest before stretching provided by an embodiment of the present invention;
FIG. 2b is an enhanced image obtained by stretching an image of a region of interest using an adaptive enhancement curve according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an image enhancement apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The technical scheme adopted by the embodiment of the invention is that the form of the histogram is automatically analyzed according to the histogram of an image mask region (a soft tissue and bone part effective tissue region of a beam splitter shielding region and an air region is removed), and an optimal S curve for adjusting brightness and contrast is automatically generated.
Based on the above principle, the present invention provides an image enhancement method as shown in fig. 1, including:
s101, receiving an image of an area of interest, acquiring a mask area in the area of interest, and acquiring a gray level histogram of each pixel in the mask area;
s102, calculating a reference point according to the gray level histogram of each pixel in the mask area;
s103, calculating an adaptive enhancement curve according to the reference point;
and S104, stretching the image of the region of interest according to the self-adaptive enhancement curve to obtain an enhanced image.
Specifically, step S101 includes:
and S1011, acquiring a mask region of the region-of-interest image by using a binarization processing method, a region growing method or a threshold value segmentation method.
And S1012, counting the gray value of each pixel point in the mask area, and generating a gray histogram of each pixel in the mask area according to the counted gray value. In step S1012, when a primary gray histogram is generated according to the counted gray values, the gray levels of the primary gray histogram are merged and compressed to 256 gray levels, so as to obtain a gray histogram of the mask region.
Specifically, in step S101, the area information map of the beam splitter may be transmitted from an external device, and after the area information map of the beam splitter is segmented, an image of a region of interest is obtained, and a mask area is obtained by a simple binarization process, an area growing process or a threshold segmentation process on a preset mask of the image of the region of interest, wherein an image processing basic algorithm is applied, which is not described in detail herein, and a gray level value of each pixel in the mask area is counted according to information of the mask area to generate a primary gray level histogram. Since the gray level of the X-ray image may be 65536(16 bitmap) or 16384(14 bitmap) in practical applications, for the convenience of subsequent calculation, the gray levels of the primary gray histogram need to be combined and compressed to 256 gray levels, and finally the gray histogram of the mask region is obtained. The step S101 is mainly used to exclude the invalid region of the region of interest and obtain the valid region, such as the soft tissue and bone valid tissue region of the beam splitter blocking region and the air region.
Specifically, the gray histogram of the mask region is classified into 256 gray levels from the 0 th level to the 255 th level, and step S102 includes:
and S1021, performing normalization processing on the gray level histogram of the mask region, and setting the numerical values of 0 level and 255 level of the gray level histogram after the normalization processing to be 0 to obtain a normalized histogram. In this step, the gray histogram of the mask region obtained in step S101 is normalized, and the values of two gray levels on the two sides of the histogram obtained after the normalization process are set to 0, that is, the values of 0 th level and 255 th level are set to 0, so as to obtain the normalized histogram.
And S1022, fitting the envelope curve of the normalized histogram according to a preset multiple term. In this step, the envelope of the normalized histogram obtained in step S1021 is fitted with a polynomial, and the order is 10.
And S1023, calculating the mean value of the normalized histogram, and segmenting the envelope curve of the normalized histogram after fitting by using the mean value of the normalized histogram to obtain a plurality of peaks. In this step, the envelope is binarized and divided by the mean of the normalized histogram, so that a plurality of peaks can be divided.
S1024, searching the largest peak from the peaks, and taking the top point of the largest peak as a central point. In this step, the largest peak is found among the plurality of peaks divided in step S1023, and the abscissa, i.e., the x-coordinate, corresponding to the vertex of the largest peak is obtained, with the vertex of the largest peak as the center point xm.
And S1025, acquiring the coordinates of the vertexes of the left and right peaks of the maximum peak, calculating the distance from the vertexes of the left and right peaks to the central point, and taking the vertex of the peak farthest away as a compression point. In this step, the abscissa of the peak on both the left and right sides of the maximum peak is found, and the distances from the abscissa of the peak on both the left and right sides to the abscissa of the center point xm are calculated, respectively, with the vertex of the peak most distant from the center point as the compression point xc.
Specifically, the coordinates of the center point are represented by (xm, ym) and the coordinates of the compression point are represented by (xc, yc), then step S103 includes:
representing the adaptive enhancement curve by y, then y ═ a × b × atan c × x-xm + ym; - - - - (1)
Substituting xm ═ ym ═ 0 into the formula of the adaptive enhancement curve, denoted b with c, then:
substituting the formula (2) into the formula (1) for simplification to obtain:
setting the adaptive enhancement curve over a compression point (xc, yc), where yc is expressed by a compression factor xc and cCoeff, yc ≦ xc ≦ cCoeff when xc ≦ xm, and yc ≦ yd- (xd-xc) × cCoeff when xc > xm, where xd ≦ yd ≦ 255;
substituting the coordinates of (xd, yd) and (xc, yc) into equation (3) yields:
calculating a formula (4) to obtain values of three coefficients a, b and c, and substituting the values of a, b and c obtained by solving into the formula (1) to obtain the self-adaptive enhancement curve;
and mapping the gray level input and output range of the self-adaptive enhancement curve to the gray level range of the primary gray level histogram through interpolation operation.
More specifically, the adaptive enhancement curve formula is defined as:
y＝a*b*atan c*x-xm+ym
where xm ═ ym. Because the adaptive enhancement curve passes through the (0, 0) point and the (xd, xd) point, where xd ═ yd ═ 255.
Substituting therefore the (0, 0) point coordinates, b can be represented by c:
let the adaptive enhancement curve exceed the compression point (xc, yc), where yc can be expressed by the compression factors xc and cCoeff, in this case there are two cases:
when xc < ═ xm, yc ═ xc cCoeff, wherein the value of cCoeff ranges from 0.3 to 0.4; otherwise yc ═ yd- (xd-xc) × cCoeff.
By substituting the coordinates of (xd, xd) and (xc, yc) into the equations, the following equations can be set forth:
three coefficients a, b and c can be obtained by solving the equation set. And generating a corresponding self-adaptive enhancement curve by using the three solved coefficients, and mapping the gray level input and output range of the self-adaptive enhancement curve to the original gray level range by using interpolation operation.
In step S104, the region-of-interest image is stretched by using the adaptive enhancement curve, that is, the image in fig. 2a is stretched by using the adaptive enhancement curve generated in step S103, and the image in fig. 2a is stretched to obtain the enhanced image shown in fig. 2 b. By comparing fig. 2a and fig. 2b, it can be clearly seen that after the region of interest image is stretched, the brightness and contrast to be processed are improved, and an excellent display effect is obtained.
The invention also shows an image enhancement apparatus as shown in fig. 3, comprising:
a histogram generating unit 301 for receiving the region-of-interest image, acquiring a mask region within the region-of-interest, and acquiring a gray level histogram of each pixel within the mask region,
a reference point calculating unit 302, configured to calculate a reference point according to the gray level histogram of each pixel in the mask region;
an enhancement curve obtaining unit 303, configured to calculate an adaptive enhancement curve according to the reference point;
an image stretching unit 304, configured to stretch the image of the region of interest according to the adaptive enhancement curve, so as to obtain an enhanced image.
Further, the histogram generation unit 301 includes:
a mask region acquisition module, configured to acquire a mask region of the region-of-interest image by using binarization processing, region growing, or threshold segmentation;
and the histogram generation module is used for counting all gray values in the pixel points of the mask region and generating a gray histogram of the mask region according to the counted gray values.
Further, the histogram generation module includes:
the histogram generation submodule is used for generating a primary gray level histogram according to the gray level value obtained by statistics;
and the histogram processing submodule is used for merging and compressing the gray scales of the primary gray histogram to 256 gray levels to obtain the gray histogram of the mask region.
Further, the reference point calculation unit 302 includes:
the normalization processing module is used for performing normalization processing on the gray level histogram of the mask area and setting the numerical values of 0 level and 255 level of the gray level histogram after the normalization processing to be 0 to obtain a normalization histogram;
the central point top removing module is used for fitting the envelope curve of the normalized histogram according to preset multiple items, calculating the mean value of the normalized histogram, segmenting the fitted envelope curve of the normalized histogram by using the mean value of the normalized histogram to obtain a plurality of peaks, searching the largest peak from the peaks, and taking the peak of the largest peak as the central point;
and the compression point determining module is used for acquiring the coordinates of the vertexes of the left and right peaks of the maximum peak, calculating the distance from the vertexes of the left and right peaks to the central point, and taking the vertex of the peak farthest away as the compression point.
Further, if the coordinates of the central point are represented by (xm, ym) and the coordinates of the compression point are represented by (xc, yc), the enhancement curve obtaining unit 303 is specifically configured to:
representing the adaptive enhancement curve by y, then y ═ a × b × atan c × x-xm + ym; - - - - (5)
Substituting xm ═ ym ═ 0 into the formula of the adaptive enhancement curve, denoted b with c, then:
substituting formula (6) into formula (5) for simplification, we get:
setting the adaptive enhancement curve over a compression point (xc, yc), where yc is expressed by a compression factor xc and cCoeff, yc ≦ xc ≦ cCoeff when xc ≦ xm, and yc ≦ yd- (xd-xc) × cCoeff when xc > xm, where xd ≦ yd ≦ 255;
substituting the coordinates of (xd, yd) and (xc, yc) into equation (7) yields:
calculating a formula (8) to obtain values of three coefficients a, b and c, and substituting the values of a, b and c obtained by solving into a formula (5) to obtain the self-adaptive enhancement curve;
and mapping the gray level input and output range of the self-adaptive enhancement curve to the gray level range of the primary gray level histogram through interpolation operation.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. An image enhancement method, comprising:
receiving an image of an area of interest, acquiring a mask area in the area of interest, and acquiring a gray level histogram of each pixel in the mask area;
calculating a reference point on the envelope curve according to the envelope curve of the gray level histogram of each pixel in the mask area;
calculating a self-adaptive enhancement curve according to the coordinates of the reference point;
stretching the image of the region of interest according to the self-adaptive enhancement curve to obtain an enhanced image;
wherein the gray level histogram of the mask region includes 256 gray levels of 0 level to 255 levels, and the reference point includes a center point and a compression point, and the calculating the reference point located on the envelope according to the envelope of the gray level histogram of each pixel in the mask region includes:
normalizing the gray level histogram of the mask area, and setting the numerical values of 0 level and 255 level of the gray level histogram after normalization processing as 0 to obtain a normalized histogram;
fitting an envelope line of the normalized histogram according to a preset multiple term;
calculating the mean value of the normalized histogram, and segmenting the envelope curve of the fitted normalized histogram by using the mean value of the normalized histogram to obtain a plurality of peaks;
searching a maximum peak from a plurality of peaks, and taking the top point of the maximum peak as a central point;
acquiring coordinates of peaks at the left side and the right side of the maximum peak, calculating the distance from the peak at the left side and the peak at the right side to the central point, and taking the peak at the farthest distance as a compression point;
wherein (xm, ym) represents the coordinates of the center point and (xc, yc) represents the coordinates of the compression point, the calculating an adaptive boost curve from the coordinates of the reference point comprises:
expressing the adaptive boost curve by y, then y ═ a (b · atan (c × (x-xm)) + ym); - - - - (1)
Substituting xm ═ ym ═ 0 into the formula of the adaptive enhancement curve, denoted b with c, then:
substituting the formula (2) into the formula (1) for simplification to obtain:
setting the adaptive enhancement curve over a compression point (xc, yc), where yc is expressed by a compression factor xc and cCoeff, yc ≦ xc ≦ cCoeff when xc ≦ xm, and yc ≦ yd- (xd-xc) × cCoeff when xc > xm, where xd ≦ yd ≦ 255;
substituting the coordinates of (xd, yd) and (xc, yc) into equation (3) yields:
calculating a formula (4) to obtain values of three coefficients a, b and c, and substituting the values of a, b and c obtained by solving into the formula (1) to obtain the self-adaptive enhancement curve;
and mapping the gray level input and output range of the self-adaptive enhancement curve to the gray level range of the primary gray level histogram through interpolation operation.
2. The image enhancement method of claim 1, wherein said obtaining a mask region within the region of interest and obtaining a gray-level histogram of the mask region comprises:
acquiring a mask region of the region-of-interest image by using a binarization processing, region growing or threshold segmentation mode;
and counting the gray value of each pixel point in the mask area, and generating a gray histogram of each pixel in the mask area according to the counted gray value.
3. The image enhancement method of claim 2, wherein the generating a gray level histogram of the mask region from the statistically derived gray level values comprises:
generating the primary gray level histogram according to the gray level value obtained by statistics;
and merging and compressing the gray scales of the primary gray histogram to 256 gray levels to obtain the gray histogram of the mask region.
4. An image enhancement apparatus, comprising:
the histogram generating unit is used for receiving an image of an interested area, acquiring a mask area in the interested area and acquiring a gray level histogram of each pixel in the mask area;
a reference point calculating unit, configured to calculate a reference point located on an envelope of the gray level histogram of each pixel in the mask region according to the envelope;
the enhancement curve acquisition unit is used for calculating an adaptive enhancement curve according to the coordinates of the reference point;
the image stretching unit is used for stretching the image of the region of interest according to the self-adaptive enhancement curve to obtain an enhanced image;
wherein the reference point calculating unit includes:
the normalization processing module is used for performing normalization processing on the gray level histogram of the mask area and setting the numerical values of 0 level and 255 level of the gray level histogram after the normalization processing to be 0 to obtain a normalization histogram;
the central point top removing module is used for fitting the envelope curve of the normalized histogram according to preset multiple items, calculating the mean value of the normalized histogram, segmenting the fitted envelope curve of the normalized histogram by using the mean value of the normalized histogram to obtain a plurality of peaks, searching the largest peak from the peaks, and taking the peak of the largest peak as the central point;
the compression point determining module is used for acquiring the coordinates of the top points of the left and right peaks of the maximum peak, calculating the distance from the top points of the left and right peaks to the central point, and taking the top point of the peak with the farthest distance as a compression point;
wherein (xm, ym) represents the coordinates of the center point, and (xc, yc) represents the coordinates of the compression point, the enhancement curve obtaining unit is specifically configured to:
expressing the adaptive boost curve by y, then y ═ a (b · atan (c × (x-xm)) + ym); - - - - (5)
Substituting xm ═ ym ═ 0 into the formula of the adaptive enhancement curve, denoted b with c, then:
substituting formula (6) into formula (5) for simplification, we get:
setting the adaptive enhancement curve over a compression point (xc, yc), where yc is expressed by a compression factor xc and cCoeff, yc ≦ xc ≦ cCoeff when xc ≦ xm, and yc ≦ yd- (xd-xc) × cCoeff when xc > xm, where xd ≦ yd ≦ 255;
substituting the coordinates of (xd, yd) and (xc, yc) into equation (7) yields:
calculating a formula (8) to obtain values of three coefficients a, b and c, and substituting the values of a, b and c obtained by solving into a formula (5) to obtain the self-adaptive enhancement curve;
and mapping the gray level input and output range of the self-adaptive enhancement curve to the gray level range of the primary gray level histogram through interpolation operation.
5. The image enhancement apparatus according to claim 4, wherein the histogram generation unit includes:
a mask region acquisition module, configured to acquire a mask region of the region-of-interest image by using binarization processing, region growing, or threshold segmentation;
and the histogram generation module is used for counting the gray value of each pixel point in the mask area and generating a gray histogram of each pixel in the mask area according to the counted gray value.
6. The image enhancement apparatus of claim 5, wherein the histogram generation module comprises:
the histogram generation submodule is used for generating the primary gray level histogram according to the gray level value obtained by statistics;
and the histogram processing submodule is used for merging and compressing the gray scales of the primary gray histogram to 256 gray levels to obtain the gray histogram of the mask region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611085142.8A CN106780413B (en) | 2016-11-30 | 2016-11-30 | Image enhancement method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611085142.8A CN106780413B (en) | 2016-11-30 | 2016-11-30 | Image enhancement method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106780413A CN106780413A (en) | 2017-05-31 |
| CN106780413B true CN106780413B (en) | 2020-06-02 |
Family
ID=58914881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611085142.8A Active CN106780413B (en) | 2016-11-30 | 2016-11-30 | Image enhancement method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106780413B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301627B (en) * | 2017-06-26 | 2020-07-17 | 深圳市安健科技股份有限公司 | Artifact removing and enhancing method and device for dynamic image unsharp mask |
| CN108830817A (en) * | 2018-06-11 | 2018-11-16 | 华南理工大学 | A kind of histogram-equalized image Enhancement Method based on gray correction |
| CN111489318B (en) * | 2020-03-20 | 2023-10-27 | 上海联影智能医疗科技有限公司 | Medical image enhancement method and computer-readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463807A (en) * | 2014-12-24 | 2015-03-25 | 深圳市安健科技有限公司 | Method and system for self-adaptive enhancement of contrast ratio of X-ray image |
| CN104599270A (en) * | 2015-01-18 | 2015-05-06 | 北京工业大学 | Breast neoplasms ultrasonic image segmentation method based on improved level set algorithm |
| CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
| CN105488768A (en) * | 2015-11-27 | 2016-04-13 | 天津工业大学 | Contrast enhancement method for eye fundus image |
-
2016
- 2016-11-30 CN CN201611085142.8A patent/CN106780413B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463807A (en) * | 2014-12-24 | 2015-03-25 | 深圳市安健科技有限公司 | Method and system for self-adaptive enhancement of contrast ratio of X-ray image |
| CN104599270A (en) * | 2015-01-18 | 2015-05-06 | 北京工业大学 | Breast neoplasms ultrasonic image segmentation method based on improved level set algorithm |
| CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
| CN105488768A (en) * | 2015-11-27 | 2016-04-13 | 天津工业大学 | Contrast enhancement method for eye fundus image |
Non-Patent Citations (2)
| Title |
|---|
| 一种实用数字医疗图像增强方法研究;马旭 等;《沈阳师范大学学报（自然科学版）》;20080430;第26卷(第2期);第187-188页 * |
| 图像增强中优化算法适应度函数设计;施泽波;《电光与控制》;20130531;第20卷(第5期);第49-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106780413A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Agarwal et al. | Medical image contrast enhancement using range limited weighted histogram equalization | |
| CN106780413B (en) | Image enhancement method and device | |
| CN108921800A (en) | Non-local mean denoising method based on form adaptive search window | |
| CN107292815B (en) | Method and device for processing mammary gland image and mammary gland imaging equipment | |
| CN104574316B (en) | A kind of digitized X-ray machine system | |
| Bhairannawar | Efficient medical image enhancement technique using transform HSV space and adaptive histogram equalization | |
| CN109636745B (en) | Optimal order image enhancement method based on fractional order differential image enhancement algorithm | |
| CN107316291B (en) | Mammary gland image processing method and mammary gland imaging equipment | |
| CN111340717A (en) | Image preprocessing device for uncooled thermal infrared imager | |
| CN110246090B (en) | Image processing method and device | |
| CN105976309B (en) | U.S. face mobile terminal that is a kind of efficient and being easy to Parallel Implementation | |
| CN114693682B (en) | Spine feature identification method based on image processing | |
| CN108447033A (en) | The gray level image self-adapting enhancement method of singular value decomposition and longicorn palpus optimizing algorithm | |
| CN117474823B (en) | CT data processing system for pediatric infectious inflammation detection assistance | |
| CN107578374B (en) | Stretching method of X-ray image and computer readable storage medium | |
| CN104463807B (en) | Method and system for self-adaptive enhancement of contrast ratio of X-ray image | |
| CN109859138B (en) | Infrared image enhancement method based on human visual characteristics | |
| Malik et al. | Comparative study of digital image enhancement approaches | |
| Omarova et al. | Application of the Clahe method contrast enhancement of X-Ray Images | |
| Yang et al. | Adaptive Non-Local Generative Adversarial Networks for Low-Dose CT Image Denoising | |
| CN110288540A (en) | A kind of online imaging standards method of carbon-fibre wire radioscopic image | |
| Hong et al. | Multi-focus image fusion algorithm based on non-uniform rectangular partition and generative adversarial network | |
| Li et al. | Medical image enhancement in F-shift transformation domain | |
| CN112560808B (en) | In-vivo vein identification method and device based on gray information | |
| Kandeel et al. | A study of a modified histogram based fast enhancement algorithm (MHBFE) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |