CN117974460A - Image enhancement method, system and storage medium - Google Patents
Image enhancement method, system and storage medium Download PDFInfo
- Publication number
- CN117974460A CN117974460A CN202410374352.7A CN202410374352A CN117974460A CN 117974460 A CN117974460 A CN 117974460A CN 202410374352 A CN202410374352 A CN 202410374352A CN 117974460 A CN117974460 A CN 117974460A
- Authority
- CN
- China
- Prior art keywords
- image
- layer
- enhancement
- detail
- enhanced
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000005070 sampling Methods 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 18
- 238000000354 decomposition reaction Methods 0.000 claims description 11
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 8
- 238000005286 illumination Methods 0.000 description 14
- 230000000007 visual effect Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 210000002747 omentum Anatomy 0.000 description 2
- 238000002601 radiography Methods 0.000 description 2
- 230000002207 retinal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The application discloses an image enhancement method, an image enhancement system and a storage medium, wherein the method comprises the following steps: acquiring an original image; decomposing the original image to obtain a multi-layer detail image; respectively carrying out staged enhancement on the multi-layer detail images to obtain enhanced images corresponding to each layer of detail images; reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image. By the method, the contrast ratio and the enhancement effect of the image can be improved.
Description
Technical Field
The application relates to the field of industrial nondestructive inspection and detection, in particular to an image enhancement method, an image enhancement system and a storage medium.
Background
With the widespread use of image processing technology in various layer areas, it is becoming increasingly important how to effectively enhance image contrast, improve image quality to accommodate the demands of visual analysis, machine recognition, and high-quality display. The conventional histogram equalization (Histogram Equalization, HE) algorithm is a widely used technique for image enhancement, which adjusts the dynamic range of an image based on global or local gray distribution, thereby improving the overall contrast. However, this method has limitations in that it mainly focuses on the statistical distribution of pixel intensities and does not consider the spatial correlation of pixels in an image, and thus may lead to undesirable enhancement effects such as excessive smoothing of image details or insufficient precision in processing an image edge region when processing an image containing complex illumination variations and texture details.
On the other hand, the image enhancement method based on the retinal cortex theory provides a new visual angle for image enhancement, and the image is decomposed into an illumination map reflecting illumination conditions and a reflection map reflecting scene surface properties, and the natural contrast of the image is improved by respectively operating the two parts. Although the method for enhancing the image based on the omentum cortex theory can effectively separate illumination and material information, in practical application, accurate estimation of the illumination map and the reflection map has quite challenges, and phenomena such as image noise amplification, excessive enhancement and color distortion are easily caused, so that the visual quality and the practicability of an enhancement result are reduced.
Disclosure of Invention
The application provides an image enhancement method, an image enhancement system and a storage medium, which can facilitate the comparison of multi-layer interfaces.
In a first aspect, the present application provides an image enhancement method, the method comprising:
Acquiring an original image;
decomposing the original image to obtain a multi-layer detail image;
respectively carrying out staged enhancement on the multi-layer detail images to obtain enhanced images corresponding to each layer of detail images;
reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image.
The further technical scheme is that the original image is decomposed to obtain a plurality of layers of detail images, and the method comprises the following steps:
Taking the original image as an initial image to be decomposed;
Sampling an image to be decomposed to obtain a downsampled image and an upsampled image;
Obtaining a detail image based on the image to be decomposed and the up-sampling image;
judging whether the detail image is a preset layer detail image or not, if so, ending the decomposition process; and if not, returning the downsampled image to the image to be decomposed as a new image to be decomposed, and sampling the image to be decomposed to obtain a downsampled image and an upsampled image.
The further technical scheme is that the method comprises the steps of sampling an image to be decomposed to obtain a downsampled image and an upsampled image, and comprises the following steps:
Filtering the image to be decomposed to obtain a first filtered image;
Downsampling the first filtered image to obtain a downsampled image;
filtering the downsampled image to obtain a second filtered image;
and up-sampling the second filtered image to obtain an up-sampled image.
The further technical scheme is that the multi-layer detail images are respectively enhanced in stages to obtain enhanced images corresponding to each layer of detail image, and the method comprises the following steps:
determining an absolute value of each layer of detail image;
And if the absolute value is smaller than the first preset value, taking the detail image as an enhanced image.
The method further comprises the following steps:
if the absolute value is larger than the first preset value and smaller than or equal to the second preset value, the detail image is enhanced according to the first preset enhancement coefficient, and an enhanced image is obtained.
The method further comprises the following steps:
And if the absolute value is larger than a second preset value, carrying out enhancement processing on the detail image according to a second preset enhancement coefficient to obtain an enhanced image, wherein the second preset value is smaller than the first preset value.
The method further comprises the following steps before reconstructing the multi-layer enhanced image:
And respectively carrying out filtering treatment on the multi-layer enhanced image.
The further technical scheme is that the multi-layer enhanced image is reconstructed to obtain a target enhanced image corresponding to the original image, and the method comprises the following steps:
selecting a last layer of downsampling image obtained in the decomposition process as an input image for the initial reconstruction process;
Obtaining a restored image based on the input image and the corresponding enhanced image, and upsampling the restored image to obtain a restored sampling image;
judging whether the reconstruction times reach the preset reconstruction times, if so, taking the obtained restored sampling image as a target enhanced image corresponding to the original image;
And if not, returning the restored sample image to the step of obtaining the restored image based on the input image and the corresponding enhanced image by taking the restored sample image as the input image of the next layer iteration, and upsampling the restored image to obtain the restored sample image. In a second aspect, the present application provides an image enhancement system comprising a memory for storing program data and a processor for executing the program data to perform the steps of the method as described in any of the preceding claims.
In a third aspect, the present application provides a computer readable storage medium for storing a computer program for implementing the steps of any one of the methods described above when the computer program is executed by a processor.
The beneficial effects of the application are as follows: compared with the prior art, the method and the device have the advantages that the original image is decomposed into multiple layers of detail layers, the differentiation operation can be carried out aiming at different resolutions or frequency components of the image, the problem that spatial information is ignored in the traditional methods such as global histogram equalization is solved, in the enhancement processing process, the staged enhancement processing is carried out according to the specific characteristics of each layer of detail image, the contrast of each layer of detail level can be controlled more finely, the phenomenon of over enhancement or under enhancement is effectively prevented, and the authenticity and visual comfort of the image content are maintained. In addition, the application reconstructs the multi-layer enhanced image to obtain the target enhanced image corresponding to the original image, namely, the original image is not directly subjected to integral operation based on multi-scale processing, so that the contrast is improved, and meanwhile, the inherent structure and texture characteristics of the original image can be better reserved, so that the enhanced image is more natural. For various images containing complex illumination changes, weak signals and rich details, the method can flexibly adapt to different enhancement requirements through preset reconstruction times and enhancement strategies, and has strong flexibility and applicability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a schematic flow chart of a first embodiment of an image enhancement method provided by the present application;
FIG. 2 is a flowchart of a second embodiment of an image enhancement method according to the present application;
FIG. 3 is a schematic diagram of an original image in the image enhancement method provided by the present application;
FIG. 4 is a schematic view of a detail image of layer 0 in the image enhancement method provided by the present application;
FIG. 5 is a flowchart of a third embodiment of an image enhancement method according to the present application;
FIG. 6 is a schematic diagram of a reconstructed image in an image enhancement method provided by the present application;
Fig. 7 is a schematic structural diagram of an embodiment of a computer readable storage medium according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present application are shown in the drawings. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one layer embodiment of the application. The appearances of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
With the widespread use of image processing technology in various layer areas, it is becoming increasingly important how to effectively enhance image contrast, improve image quality to accommodate the demands of visual analysis, machine recognition, and high-quality display. The conventional histogram equalization (Histogram Equalization, HE) algorithm is a widely used technique for image enhancement, which adjusts the dynamic range of an image based on global or local gray distribution, thereby improving the overall contrast. However, this method has limitations in that it mainly focuses on the statistical distribution of pixel intensities and does not consider the spatial correlation of pixels in an image, and thus may lead to undesirable enhancement effects such as excessive smoothing of image details or insufficient precision in processing an image edge region when processing an image containing complex illumination variations and texture details.
On the other hand, the image enhancement method based on the retinal cortex theory provides a new visual angle for image enhancement, and the image is decomposed into an illumination map reflecting illumination conditions and a reflection map reflecting scene surface properties, and the natural contrast of the image is improved by respectively operating the two parts. Although the method for enhancing the image based on the omentum cortex theory can effectively separate illumination and material information, in practical application, accurate estimation of the illumination map and the reflection map has quite challenges, and phenomena such as image noise amplification, excessive enhancement and color distortion are easily caused, so that the visual quality and the practicability of an enhancement result are reduced.
Therefore, in order to solve the technical problems of poor image enhancement effect and low applicability caused by the adoption of a traditional histogram equalization enhancement algorithm and an image enhancement method based on retina cortex theory in the prior art, the application provides the image enhancement method which can improve the contrast of an image and further improve the enhancement effect and applicability of the image. See in particular the examples below.
Referring to fig. 1, fig. 1 is a flowchart of a first embodiment of an image enhancement method according to the present application. The method comprises the following steps:
Step 110: an original image is acquired.
The original image may be obtained by performing X-ray scanning on the target object by using a digital radiation imaging device, and the original image may be a 16-bit digital radiography (Digital Radiography, DR) image, where the image can reflect detailed information of an internal structure of the object, but some minor defects or objects with low signal strength may not be obvious in the original image and are difficult to be observed due to a wide dynamic range of the image. Therefore, in order to be able to more clearly identify and analyze these targets, it is necessary to highlight them by improving the image contrast, enhancing the visibility of details and small defects, facilitating the subsequent observation and detection work.
Step 120: and decomposing the original image to obtain a multi-layer detail image.
Wherein the original image can be decomposed into multiple layers of detail images of different resolution levels using multi-scale analysis techniques (e.g., image pyramid, wavelet transform, etc.). These hierarchical images represent features of different scales from global to local, respectively, which help to improve contrast at a specific scale in a targeted manner.
Step 130: and carrying out staged enhancement on the multi-layer detail images to obtain enhanced images corresponding to each layer of detail images.
And processing each layer of detail image obtained by decomposition by adopting different enhancement strategies and parameters according to the characteristics of each layer of detail image. For example, the adjustment of the overall contrast is mainly focused on the low frequency layer, while the enhancement of the minute defect and the edge information is focused on the high frequency layer. This ensures that the enhancement process does not result in excessive enhancement to produce noise, but sufficiently highlights weak signals and small defects hidden in the image.
Step 140: reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image.
After the enhancement of all the detail images is completed, the detail images enhanced by each layer, namely the enhanced images, are recombined according to the spatial position relation of the detail images when the detail images are decomposed, and a final target enhanced image, namely a target enhanced image corresponding to the original image, is formed.
According to the embodiment, the original image is decomposed into multiple layers of detail levels, the differentiation operation can be carried out aiming at different resolution or frequency components of the image, the problem that spatial information is ignored in the traditional method such as global histogram equalization is solved, in the enhancement processing process, the staged enhancement processing is carried out according to the specific characteristics of each layer of detail image, the contrast of each layer of detail level can be controlled more finely, the phenomenon of over enhancement or under enhancement is effectively prevented, and the authenticity and visual comfort of the image content are maintained. In addition, the application reconstructs the multi-layer enhanced image to obtain the target enhanced image corresponding to the original image, namely, the original image is not directly subjected to integral operation based on multi-scale processing, so that the contrast is improved, and meanwhile, the inherent structure and texture characteristics of the original image can be better reserved, so that the enhanced image is more natural. For various images containing complex illumination changes, weak signals and rich details, the method can flexibly adapt to different enhancement requirements through preset reconstruction times and enhancement strategies, and has strong flexibility and applicability.
Referring to fig. 2, fig. 2 is a flowchart of a second embodiment of an image enhancement method according to the present application. The method comprises the following steps:
step 210: an original image is acquired.
Step 220: the original image is taken as an initial image to be decomposed.
Step 230: and sampling the image to be decomposed to obtain a downsampled image and an upsampled image.
Wherein step 230 comprises the steps of:
Step 231: and filtering the image to be decomposed to obtain a first filtered image.
The filtering process may be gaussian filtering, mean filtering, etc.
Step 232: and downsampling the first filtered image to obtain a downsampled image.
The first filtered image obtained after the processing in step 231 is subjected to a downsampling operation, typically using an interlaced sampling method, so that the size of the downsampled image is reduced by half, thereby forming a downsampled image. This step reduces the spatial resolution of the image, preserving the general structure of the image and the lower frequency information.
Step 233: and filtering the downsampled image to obtain a second filtered image.
And carrying out Gaussian filtering processing on the downsampled image again to generate a second filtered image, further eliminating high-frequency noise possibly existing and maintaining the basic structural characteristics of the image.
Step 234: and up-sampling the second filtered image to obtain an up-sampled image.
In order to restore the image to the same size as the original image for the subsequent subtraction operation, the second filtered image is enlarged to the size of the original image by an up-sampling technique, resulting in an up-sampled image. Common upsampling methods include nearest neighbor interpolation, bilinear interpolation, etc., to ensure image size matching while minimizing distortion.
Step 240: and obtaining a detail image based on the image to be decomposed and the up-sampling image.
The original image to be decomposed and the up-sampled image can be subtracted, and the obtained difference value is the detail image of the current layer, wherein the detail image contains the detail information with relatively high frequency in the original image.
Step 250: judging whether the detail image is a preset layer detail image or not.
If yes, the decomposition process is ended, and step 270-step 280 are executed; if not, go back to step 230 after execution of step 260.
Step 260: the downsampled image is taken as the new image to be decomposed.
For the steps 240 and 250, the number of layers L of the gaussian pyramid decomposition, that is, the preset decomposition times, may be set, and steps 231-234 are repeated for each layer in sequence, so as to obtain detailed images of some columns.
Wherein the following formula may be employed:
。
Wherein D i is the laplacian pyramid difference map of the ith layer, i.e., the detail image of the ith layer, G i is the image to be decomposed of the ith layer, and G ii is the upsampled image of the ith layer.
Specifically, an initial image to be decomposed, i.e., an original image G 0(G0 is shown in fig. 3), is subjected to gaussian filtering to obtain a first filtered image, downsampling is performed on the filtered image, i.e., the first filtered image, to obtain a downsampled image G 1, (wherein the row-column size of G 1 is half of that of G 0), after the downsampled image G 1 is subjected to gaussian filtering to obtain a second filtered image, the second filtered image is upsampled to obtain an upsampled image G 00, and the original image G 0 and the upsampled image G 00 are subtracted to obtain a laplace pyramid difference image (i.e., a detail image) D 0(D0 is shown in fig. 4.
Namely D 0=G0-G00, where D 0 is a laplacian pyramid disparity map of layer 0, i.e., a detail image, G 0 is an image to be decomposed of layer 0, and G 00 is an upsampled image of layer 0.
Taking G 1 as a new image to be decomposed, namely a layer 1 image to be decomposed, carrying out Gaussian filtering on G 1 to obtain a first filtered image, carrying out downsampling processing on the filtered image, namely the first filtered image to obtain a downsampled image G 2, (wherein the row and column size of G 2 is half of that of G 1), carrying out Gaussian filtering on the downsampled image G 2 to obtain a second filtered image, carrying out upsampling on the second filtered image to obtain an upsampled image G 11, and subtracting the image G 1 to be decomposed from the upsampled image G 11 to obtain a Laplace pyramid difference image (namely a detail image) D 1.
Similarly, G 2 is taken as a new image to be decomposed, namely, a layer 2 image to be decomposed, and the above operation is repeated to obtain a third layer laplacian pyramid difference image (namely, a detail image) D 2=G2-G22, wherein G 2 is a downsampled image obtained by the layer 1, and G 22 is an upsampled image obtained by the layer 2.
Step 270: and carrying out staged enhancement on the multi-layer detail images to obtain enhanced images corresponding to each layer of detail images.
Step 270 includes the following steps:
1) The absolute value of each layer of detail image is determined.
2-1) If the absolute value is smaller than the first preset value, the detail image is used as the enhanced image.
2-2) If the absolute value is larger than the first preset value and smaller than or equal to the second preset value, carrying out enhancement processing on the detail image according to the first preset enhancement coefficient to obtain an enhanced image.
2-3) If the absolute value is larger than a second preset value, carrying out enhancement processing on the detail image according to a second preset enhancement coefficient to obtain an enhanced image.
Wherein the second preset value is smaller than the first preset value.
For 2-1) -2-3), reference may be made in particular to the following formula:
。
Wherein, i D (x, y) is an absolute value of the detail image, T1 is a first preset value, T2 is a second preset value, a is a first preset enhancement coefficient, which may be a value greater than 1, and b is a second preset enhancement coefficient, which may be a value less than 1.
That is, the upper and lower threshold limits, such as the first preset value T1 and the second preset value T2, are set, and the range of the upper and lower threshold limits is enhanced. When the value of the I D (x, y) is smaller than T1, the area is considered as a smooth area, and the detail image can be directly used as an enhanced image without enhancement; when the value of |d (x, y) | is greater than T2, which is considered here to be a strong edge region, the second preset enhancement coefficient b may be set to a value less than 1; when the value of |d (x, y) | is intermediate between T1 and T2, the region where enhancement is required is considered here, and the first preset enhancement coefficient a is set to a value greater than 1.
The enhanced image corresponding to each layer of detail image is different processing results obtained by performing different processing in different absolute value intervals of the detail image.
In some embodiments, the multi-layer enhanced image may also be separately filtered prior to being reconstructed.
In the frequency domain analysis, since the frequency truncation phenomenon can generate a ringing effect at the boundary or edge position, when the detail image is enhanced in stages, a phenomenon of discontinuous gray scale, namely similar ringing effect, can occur at the edge position in the restored image, so that filtering (such as Gaussian filtering) is required to be performed on the enhanced image obtained after the processing, the ringing effect is lightened, and the finally enhanced detail image is obtained.
Step 280: reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image.
According to the embodiment, the original image is decomposed into multiple layers of detail levels, the differentiation operation can be carried out aiming at different resolution or frequency components of the image, the problem that spatial information is ignored in the traditional method such as global histogram equalization is solved, in the enhancement processing process, the staged enhancement processing is carried out according to the specific characteristics of each layer of detail image, the contrast of each layer of detail level can be controlled more finely, the phenomenon of over enhancement or under enhancement is effectively prevented, and the authenticity and visual comfort of the image content are maintained. In addition, the application reconstructs the multi-layer enhanced image to obtain the target enhanced image corresponding to the original image, namely, the original image is not directly subjected to integral operation based on multi-scale processing, so that the contrast is improved, and meanwhile, the inherent structure and texture characteristics of the original image can be better reserved, so that the enhanced image is more natural. For various images containing complex illumination changes, weak signals and rich details, the method can flexibly adapt to different enhancement requirements through preset reconstruction times and enhancement strategies, and has strong flexibility and applicability.
Referring to fig. 5, fig. 5 is a flowchart of a third embodiment of an image enhancement method according to the present application. The method comprises the following steps:
Step 310: an original image is acquired.
Step 320: and decomposing the original image to obtain a multi-layer detail image.
Step 330: and carrying out staged enhancement on the multi-layer detail images to obtain enhanced images corresponding to each layer of detail images.
Step 340: and selecting the last layer of downsampling image obtained in the multi-layer downsampling process as an input image for the initial reconstruction process.
Step 350: and obtaining a restored image based on the initial input image and the corresponding enhanced image of the last layer, and upsampling the restored image to obtain a restored sampling image.
Step 360: and judging whether the reconstruction times reach the preset reconstruction times.
If yes, go to step 380; if not, then step 370 is performed.
The preset reconfiguration times and the preset decomposition times can be equal, and specific numerical values can be determined according to actual conditions.
Step 370: the restored sampling image is taken as an input image of the next layer iteration.
Step 380: and taking the finally obtained restored image as a target enhanced image corresponding to the original image.
For steps 340-380, the following formula may be specifically employed:
。
Wherein R i is a restored image of the i-th layer, E i is an input image of the i-th layer, α is a coefficient, and D i is an enhanced image of the i-th layer.
When the pyramid is at the top layer, the last layer of downsampled image is taken as an initial input image E i, that is, E i is equal to G L-1, and then the last layer of downsampled image G L-1 and the enhanced L-1 layer pyramid difference map, that is, the last layer of enhanced image, are linearly added to obtain an L-1 layer restored image R L-1.
The restored image R L-1 of the L-1 layer is used as an input image of the L-2 layer, the restored image R L-1 is subjected to up-sampling operation to obtain a first restored sample image, the first restored sample image is assigned to E i, and the restored image R L-2 of the L-2 layer is obtained by adding the first restored sample image and the enhanced image of the L-2 layer.
And performing up-sampling operation on the restored image R L-2 of the L-2 layer to obtain a second restored sample image, and assigning the second restored sample image to E L-3 as an input image of the L-3 layer, wherein the restored image R L-3 of the L-3 layer is obtained by adding the second restored sample image and the enhanced image of the L-3 layer.
I.e. at each layer, R i-1 is up-sampled and assigned to E i, and added to the enhanced image D i to obtain a restored image of the current layer until i=0. The final restored image R 0 is obtained by this cycle, which is the target enhanced image corresponding to the original image, see fig. 6.
The steps 310 and 320 have the same or similar technical schemes as the above embodiments, and are not described herein.
According to the embodiment, the original image is decomposed into multiple layers of detail levels, the differentiation operation can be carried out aiming at different resolution or frequency components of the image, the problem that spatial information is ignored in the traditional method such as global histogram equalization is solved, in the enhancement processing process, the staged enhancement processing is carried out according to the specific characteristics of each layer of detail image, the contrast of each layer of detail level can be controlled more finely, the phenomenon of over enhancement or under enhancement is effectively prevented, and the authenticity and visual comfort of the image content are maintained. In addition, the application reconstructs the multi-layer enhanced image to obtain the target enhanced image corresponding to the original image, namely, the original image is not directly subjected to integral operation based on multi-scale processing, so that the contrast is improved, and meanwhile, the inherent structure and texture characteristics of the original image can be better reserved, so that the enhanced image is more natural. For various images containing complex illumination changes, weak signals and rich details, the method can flexibly adapt to different enhancement requirements through preset reconstruction times and enhancement strategies, and has strong flexibility and applicability.
The present application also provides an image enhancement apparatus including an acquisition unit, a decomposition unit, an enhancement unit, and a reconstruction unit, corresponding to the image enhancement method of the above embodiments.
The acquisition unit is used for acquiring an original image;
The decomposition unit is used for decomposing the original image to obtain a multi-layer detail image;
the enhancement unit is used for enhancing the multi-layer detail image in stages to obtain an enhanced image corresponding to each layer of detail image;
And the reconstruction unit is used for reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image.
It will be appreciated that the above units are also used to implement the technical solution of any of the embodiments of the present application.
The application also provides an image enhancement system comprising a memory and a processor, wherein the memory has a computer program stored thereon; the processor is configured to implement the image enhancement method provided by any one of the foregoing method embodiments when executing the computer program.
Referring to fig. 7, fig. 7 is a structural illustration of an embodiment of a computer readable storage medium 70 provided by the present application, the computer readable storage medium 70 storing a computer program 71, the computer program 71, when executed by a processor, is configured to implement the following method steps:
Acquiring an original image;
decomposing the original image to obtain a multi-layer detail image;
the multi-layer detail images are enhanced in stages, and an enhanced image corresponding to each layer of detail image is obtained;
reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image.
It will be appreciated that the computer program 71, when being executed by a processor, is also adapted to carry out the solution of any one of the embodiments of the present application.
In the several layers of embodiments provided in the present application, it should be understood that the disclosed methods and apparatus may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., two layers of units or components may be combined or integrated into another layer system, or some features may be omitted or not performed.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one layer, or may be distributed on two layers of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each layer of the embodiments of the present application may be integrated into one layer of processing unit, each layer of unit may exist alone physically, or two or more layers of units may be integrated into one layer of unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units of the other embodiments described above may be stored in a layer of computer readable storage medium if implemented in the form of software functional units and sold or used as stand alone products. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a layer of storage medium, including several instructions for causing a computer device (which may be a layer of personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the layers of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is only the embodiments of the present application, and therefore, the patent scope of the application is not limited thereto, and all equivalent structures or equivalent processes using the descriptions of the present application and the accompanying drawings, or direct or indirect application in other related technical fields, are included in the scope of the application.
Claims (10)
1. A method of image enhancement, the method comprising:
Acquiring an original image;
decomposing the original image to obtain a multi-layer detail image;
Respectively carrying out staged enhancement on the multiple layers of detail images to obtain enhanced images corresponding to each layer of detail images;
reconstructing the multi-layer enhanced image to obtain a target enhanced image corresponding to the original image.
2. The image enhancement method according to claim 1, wherein decomposing the original image to obtain a multi-layer detail image comprises:
taking the original image as an initial image to be decomposed;
sampling the image to be decomposed to obtain a downsampled image and an upsampled image;
obtaining the detail image based on the image to be decomposed and the up-sampling image;
Judging whether the detail image is a preset layer detail image or not, if so, ending the decomposition process; and if not, returning the downsampled image to the step of sampling the image to be decomposed to obtain a downsampled image and an upsampled image.
3. The image enhancement method according to claim 2, wherein said sampling said image to be decomposed to obtain a downsampled image and an upsampled image comprises:
filtering the image to be decomposed to obtain a first filtered image;
Downsampling the first filtered image to obtain a downsampled image;
filtering the downsampled image to obtain a second filtered image;
And up-sampling the second filtered image to obtain the up-sampled image.
4. The image enhancement method according to claim 1, wherein the step of enhancing the detail images in multiple layers to obtain an enhanced image corresponding to each layer of detail image includes:
determining the absolute value of each layer of detail image;
And if the absolute value is smaller than a first preset value, taking the detail image as the enhanced image.
5. The image enhancement method according to claim 4, characterized in that the method further comprises:
And if the absolute value is larger than the first preset value and smaller than or equal to the second preset value, carrying out enhancement processing on the detail image according to a first preset enhancement coefficient to obtain the enhanced image.
6. The image enhancement method according to claim 4, characterized in that the method further comprises:
And if the absolute value is larger than a second preset value, carrying out enhancement processing on the detail image according to a second preset enhancement coefficient to obtain the enhanced image, wherein the second preset value is smaller than the first preset value.
7. The image enhancement method of claim 1, wherein prior to said reconstructing a plurality of layers of said enhanced image, said method further comprises:
And respectively carrying out filtering treatment on the plurality of layers of the enhanced images.
8. The image enhancement method according to any one of claims 1 to 7, wherein reconstructing the plurality of layers of the enhanced image to obtain a target enhanced image corresponding to the original image includes:
selecting a last layer of downsampling image obtained in the decomposition process as an input image for the initial reconstruction process;
Obtaining a restored image based on the input image and the corresponding enhanced image, and upsampling the restored image to obtain a restored sampling image;
judging whether the reconstruction times reach the preset reconstruction times, if so, taking the obtained restored sampling image as a target enhanced image corresponding to the original image;
And if not, returning the restored sampling image to the step of obtaining a restored image based on the input image and the corresponding enhanced image by taking the restored sampling image as the input image of the next layer iteration, and upsampling the restored image to obtain the restored sampling image.
9. An image enhancement system, characterized in that the image enhancement system comprises a memory for storing program data and a processor for executing the program data to implement the image enhancement method according to any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores program data for implementing the image enhancement method according to any of claims 1-7 when being executed by a processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410374352.7A CN117974460B (en) | 2024-03-29 | 2024-03-29 | Image enhancement method, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410374352.7A CN117974460B (en) | 2024-03-29 | 2024-03-29 | Image enhancement method, system and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117974460A true CN117974460A (en) | 2024-05-03 |
CN117974460B CN117974460B (en) | 2024-06-11 |
Family
ID=90866051
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410374352.7A Active CN117974460B (en) | 2024-03-29 | 2024-03-29 | Image enhancement method, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117974460B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101201937A (en) * | 2007-09-18 | 2008-06-18 | 上海医疗器械厂有限公司 | Digital image enhancement method and device based on wavelet restruction and decompose |
US20100142790A1 (en) * | 2008-12-04 | 2010-06-10 | New Medical Co., Ltd. | Image processing method capable of enhancing contrast and reducing noise of digital image and image processing device using same |
US20100195886A1 (en) * | 2007-07-20 | 2010-08-05 | Agfa Healthcare N.V. | Method of Generating a Multiscale Contrast Enhanced Image |
CN106875359A (en) * | 2017-02-16 | 2017-06-20 | 阜阳师范学院 | A kind of sample block image repair method based on layering boot policy |
CN108805950A (en) * | 2018-05-28 | 2018-11-13 | 牙博士医疗控股集团有限公司 | Dental piece information conversion method and device |
CN111462004A (en) * | 2020-03-30 | 2020-07-28 | 北京推想科技有限公司 | Image enhancement method and device, computer equipment and storage medium |
CN112070664A (en) * | 2020-07-31 | 2020-12-11 | 华为技术有限公司 | Image processing method and device |
CN113674173A (en) * | 2021-08-19 | 2021-11-19 | Oppo广东移动通信有限公司 | Image processing method and device, terminal and readable storage medium |
CN115272871A (en) * | 2022-09-27 | 2022-11-01 | 长春理工大学 | Method for detecting dim small target under space-based background |
CN116645281A (en) * | 2023-05-06 | 2023-08-25 | 桂林电子科技大学 | Low-light-level image enhancement method based on multi-stage Laplace feature fusion |
-
2024
- 2024-03-29 CN CN202410374352.7A patent/CN117974460B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100195886A1 (en) * | 2007-07-20 | 2010-08-05 | Agfa Healthcare N.V. | Method of Generating a Multiscale Contrast Enhanced Image |
CN101201937A (en) * | 2007-09-18 | 2008-06-18 | 上海医疗器械厂有限公司 | Digital image enhancement method and device based on wavelet restruction and decompose |
US20100142790A1 (en) * | 2008-12-04 | 2010-06-10 | New Medical Co., Ltd. | Image processing method capable of enhancing contrast and reducing noise of digital image and image processing device using same |
CN106875359A (en) * | 2017-02-16 | 2017-06-20 | 阜阳师范学院 | A kind of sample block image repair method based on layering boot policy |
CN108805950A (en) * | 2018-05-28 | 2018-11-13 | 牙博士医疗控股集团有限公司 | Dental piece information conversion method and device |
CN111462004A (en) * | 2020-03-30 | 2020-07-28 | 北京推想科技有限公司 | Image enhancement method and device, computer equipment and storage medium |
CN112070664A (en) * | 2020-07-31 | 2020-12-11 | 华为技术有限公司 | Image processing method and device |
CN113674173A (en) * | 2021-08-19 | 2021-11-19 | Oppo广东移动通信有限公司 | Image processing method and device, terminal and readable storage medium |
CN115272871A (en) * | 2022-09-27 | 2022-11-01 | 长春理工大学 | Method for detecting dim small target under space-based background |
CN116645281A (en) * | 2023-05-06 | 2023-08-25 | 桂林电子科技大学 | Low-light-level image enhancement method based on multi-stage Laplace feature fusion |
Also Published As
Publication number | Publication date |
---|---|
CN117974460B (en) | 2024-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2380132B1 (en) | Denoising medical images | |
CN109242888B (en) | Infrared and visible light image fusion method combining image significance and non-subsampled contourlet transformation | |
US5715334A (en) | Digital pixel-accurate intensity processing method for image information enhancement | |
JP7010983B2 (en) | Image quality improvement methods and systems for low coherence interferometry | |
US5933540A (en) | Filter system and method for efficiently suppressing noise and improving edge definition in a digitized image | |
JP6283850B2 (en) | Image processing method, image processing apparatus, and program | |
JP2014505491A (en) | Reduction of non-linear resolution of medical images | |
Moran et al. | Using super-resolution generative adversarial network models and transfer learning to obtain high resolution digital periapical radiographs | |
CN110610498A (en) | Mammary gland molybdenum target image processing method, system, storage medium and equipment | |
CN114240797B (en) | OCT image denoising method, device, equipment and medium | |
CN110866870B (en) | Super-resolution processing method for amplifying medical image by any multiple | |
CN116739899A (en) | Image super-resolution reconstruction method based on SAUGAN network | |
CN106023116B (en) | A kind of compressed sensing image rebuilding method and device based on block Weighted Constraint | |
CN113689337B (en) | Ultrasonic image super-resolution reconstruction method and system based on generation countermeasure network | |
CN117974460B (en) | Image enhancement method, system and storage medium | |
Dasgupta | Comparative analysis of non-blind deblurring methods for noisy blurred images | |
Paul et al. | MR image enhancement using an extended neighborhood filter | |
CN114066778B (en) | InSAR interferogram iterative self-adaptive filtering method based on Laplacian pyramid | |
WO1995024694A1 (en) | Digital pixel-accurate intensity processing method for image information enhancement | |
Denton et al. | Deep-layer training of cnn for sar with two-stage data augmentation | |
CN111613302A (en) | Tumor Ai processing method and product based on VRDS4D medical image | |
CN112927196B (en) | Calcification score method and device | |
Kumar et al. | New Ultrasound Image Watermarking Enhancement algorithm for cardiovascular disease | |
Truc et al. | A new approach to vessel enhancement in angiography images | |
Jothi et al. | An Efficient Denoising Architecture for Impulse Noise Removal in Colour Image Using Combined Filter. |
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 |