CN115330593A - Super-resolution single image construction method and equipment - Google Patents
Super-resolution single image construction method and equipment Download PDFInfo
- Publication number
- CN115330593A CN115330593A CN202210802001.2A CN202210802001A CN115330593A CN 115330593 A CN115330593 A CN 115330593A CN 202210802001 A CN202210802001 A CN 202210802001A CN 115330593 A CN115330593 A CN 115330593A
- Authority
- CN
- China
- Prior art keywords
- image
- resolution
- super
- edge
- fusion
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 39
- 230000004927 fusion Effects 0.000 claims abstract description 35
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 239000013589 supplement Substances 0.000 claims abstract description 9
- 230000000694 effects Effects 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 7
- 238000007500 overflow downdraw method Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 5
- 230000003321 amplification Effects 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Picture Signal Circuits (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention provides a super-resolution single image construction method and equipment, which comprise the following steps: s1, performing detail enhancement on an image edge part; s2, performing detail supplement and enhancement on the non-edge part of the image by using a single image self-learning algorithm; and S3, image fusion enhancement, namely performing image weighted superposition and filtering denoising on the images output in the step S1 and the step S2 to obtain a finally output high-resolution image. The invention effectively enhances the image display effect and optimizes the visual experience of the user.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a super-resolution single image construction method and equipment.
Background
In a human visual perception system, a High Resolution (HR) image is an important medium for clearly expressing information such as a spatial structure, detailed features, edge textures and the like of the image, and has a very wide practical value in the fields of medicine, industry, satellite remote sensing, road monitoring, safety monitoring, audio-visual entertainment and the like. However, currently, many images are Low Resolution images (LR) at the time of initial acquisition, and how to reconstruct the Low Resolution images into high Resolution images containing clear detail features is a difficult problem in the fields of computer vision and image processing. Therefore, it is an urgent technical problem in the art to develop a super-resolution single image construction method and apparatus, which can effectively overcome the above-mentioned problems in the related art.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a super-resolution single image construction method and equipment.
In a first aspect, an embodiment of the present invention provides a super-resolution single image construction method, including: s1, detail enhancement is carried out on the edge part of an image, and as the edge of the image contains the most important information in an image, the visual quality of the image after super-resolution is seriously affected by the sawtooth phenomenon and the fuzzy phenomenon which occur after the super-resolution of the edge part of the image, detail supplement and enhancement are carried out on the edge part of the image; s2, detail enhancement is carried out on the non-edge part of the image, and because the non-edge part of the image influences the visual experience of a user, detail supplement and enhancement are carried out on the non-edge part of the image by using a single image self-learning algorithm based on the self-similarity of the image detail; and S3, image fusion enhancement, namely performing image weighted superposition and filtering denoising on the images output in the step S1 and the step S2, and integrally enhancing image details through image fusion to obtain a finally output high-resolution image.
On the basis of the content of the embodiment of the method, the super-resolution single image construction method provided by the embodiment of the invention specifically comprises the following steps of S1: s101, acquiring a low-resolution image I; s102, amplifying the low-resolution image I by using an interpolation algorithm to obtain an image A; s103, judging the RGB image of the image A, if the image A is a gray image, selecting S105 to execute, and if the image A is an RGB color image, selecting S104 to execute; s104, performing RGB color fusion operation on the image A to obtain an image B; s105, carrying out operator edge detection on the input image to obtain a binary image C; s106, extracting the edge contour of the binary image C to generate an edge pixel position database W; s107, creating a contrast enhancement filter; s108, performing contrast stretching on the image A to obtain an image D; s109, carrying out multi-dimensional image filtering operation on the image D and the contrast enhancement filter; s110, the edge-enhanced high-resolution image Y is obtained by the processing of S109.
On the basis of the content of the above method embodiment, in the super-resolution single image construction method provided in the embodiment of the present invention, step S2 specifically includes: s201, acquiring a low-resolution image I; s202, reducing the image I by using an interpolation algorithm to obtain an image E; s203, carrying out small block image segmentation on the image I, wherein an empirical value is 5 multiplied by 5 small blocks; s204, taking out a small image L of the segmented image I in a sliding circulation mode, and obtaining a pixel block position T after amplification; s205, obtaining an edge pixel position database W generated in the step S1; s206, searching whether the intersection with the position T exists in the edge pixel position database W; s207, if no intersecting element is found, the position T is a non-edge part, detail enhancement is needed, and in the image E, K nearest neighbor algorithm searching is carried out on the small block image L to find out a similar small block N smaller than a threshold value; s208, after the small block N is amplified, the small block M at the corresponding position is taken from the image I to obtain a high-low image pair; s209, circulating S207, and performing sliding search on the image E in S208 to obtain an LR-HR image pair database U; s210, obtaining the image A generated in the step S1; s211, taking out all M in the database U by the LR-HR image corresponding to the small image L, and performing pixel weighted fusion to obtain an image small block Q; s212, directly copying the image small block Q to the amplified pixel area of the small block image L in the image A; looping S204 to S211 to finish the detail enhancement of the non-edge part of the image A; and S213, obtaining a non-edge enhanced high-resolution image Z.
On the basis of the content of the above method embodiment, step S3 of the super-resolution single image construction method provided in the embodiment of the present invention specifically includes: s301, acquiring the edge enhanced high-resolution image Y generated in the step S1; s302, acquiring the non-edge enhanced high-resolution image Z generated in the step S2; s303, performing multi-image fusion reconstruction on the image Y and the image Z by using a pixel weighting fusion method; s304, adding median filtering to the image subjected to multi-image fusion reconstruction to remove noise; s305, generating a high resolution image O as a final output.
In a second aspect, an embodiment of the present invention provides a super-resolution single-image construction apparatus, including: the first main module is used for realizing S1 and carrying out detail enhancement on an image edge part; the second main module is used for realizing S2 and performing detail supplement and enhancement on the non-edge part of the image by using a single image self-learning algorithm; and the third main module is used for realizing S3 and image fusion enhancement, and performing image weighted superposition and filtering denoising on the images output in the S1 and the S2 to obtain a finally output high-resolution image.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor calling the program instructions being capable of performing the super-resolution single-image construction method provided by any of the various implementations of the first aspect.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the super-resolution single-image construction method provided in any one of the various implementations of the first aspect.
According to the super-resolution single image construction method and the super-resolution single image construction equipment, provided by the embodiment of the invention, the sawtooth phenomenon and the fuzzy phenomenon after the super-resolution of the image are effectively solved and the key details of the image are supplemented through edge detail reconstruction optimization and single image feature self-learning. The method can be used on various media devices, for example, a single-image super-resolution method is added in a set-top box media center application program, and the set-top box outputs the image processed by the super-resolution algorithm to a television for direct display, so that the image display effect is effectively enhanced, and the visual experience of a user is optimized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below to the drawings required for the description of the embodiments or the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a super-resolution single image construction method provided by an embodiment of the invention;
FIG. 2 is a schematic structural diagram of a super-resolution single-image construction apparatus according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of a specific process of step S1 according to an embodiment of the present invention;
fig. 5 is a schematic flowchart of a specific process of step S2 according to an embodiment of the present invention;
fig. 6 is a schematic flowchart of step S3 according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In addition, technical features of various embodiments or individual embodiments provided by the present invention may be arbitrarily combined with each other to form a feasible technical solution, and such combination is not limited by the sequence of steps and/or the structural composition mode, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, such a technical solution combination should not be considered to exist and is not within the protection scope of the present invention.
The embodiment of the invention provides a super-resolution single image construction method, and with reference to fig. 1, the method comprises the following steps: s1, detail enhancement is carried out on the edge part of an image, and as the edge of the image contains the most important information in an image, the visual quality of the image after super-resolution is seriously affected by the sawtooth phenomenon and the fuzzy phenomenon which occur after the super-resolution of the edge part of the image, detail supplement and enhancement are carried out on the edge part of the image; s2, detail enhancement is carried out on the non-edge part of the image, and because the non-edge part of the image influences the visual experience of a user, detail supplement and enhancement are carried out on the non-edge part of the image by using a single image self-learning algorithm based on the self-similarity of the image detail; and S3, image fusion enhancement, namely performing image weighted superposition and filtering denoising on the images output in the step S1 and the step S2, and integrally enhancing image details through image fusion to obtain a finally output high-resolution image.
Based on the content of the above method embodiment, as an optional embodiment, the super-resolution single image construction method provided in the embodiment of the present invention specifically includes, in step S1: s101, acquiring a low-resolution image I; s102, amplifying the low-resolution image I by using an interpolation algorithm to obtain an image A; s103, judging the RGB image of the image A, if the image A is a gray image, selecting S105 to execute, and if the image A is an RGB color image, selecting S104 to execute; s104, performing RGB color fusion operation on the image A to obtain an image B; s105, performing operator edge detection on the input image to obtain a binary image C; s106, extracting the edge contour of the binary image C to generate an edge pixel position database W; s107, creating a contrast enhancement filter; s108, performing contrast stretching on the image A to obtain an image D; s109, carrying out multi-dimensional image filtering operation on the image D and the contrast enhancement filter; and S110, obtaining the edge enhanced high-resolution image Y through the processing of S109. It should be noted that RGB color fusion is a prior art in the industry that converts RGB images into gray-scale images by eliminating hue and saturation information while preserving brightness.
Specifically, referring to fig. 4, S101, an input low-resolution image I is obtained; s102, amplifying the image I by X times by using a traditional interpolation algorithm to obtain an image A; s103, judging the RGB (Red, green, blue, red, green and Blue) image of the image A, if the image A is a gray image, selecting S105 to execute, and if the image A is an RGB color image, selecting S104 to execute; s104, performing RGB color fusion operation on the image A to obtain an image B; s105, performing operator edge detection on the input image to obtain a binary image C; s106, extracting the edge contour of the binary image C to generate an edge pixel position database W; s107, creating a contrast enhancement filter; s108, performing contrast stretching on the image A to obtain an image D; s109, carrying out multidimensional image N-dimensional filtering operation on the image D and the contrast enhancement filter; and S110, obtaining an edge enhanced high-resolution image Y (magnified by X times) through the processing of S109.
Based on the content of the above method embodiment, as an optional embodiment, the super-resolution single image construction method provided in the embodiment of the present invention specifically includes, in step S2: s201, acquiring a low-resolution image I; s202, reducing the image I by using an interpolation algorithm to obtain an image E; s203, carrying out small-block image segmentation on the image I, wherein the empirical value is 7 × 7 to 9 × 9 small blocks (which can be 5 × 5 small blocks in another embodiment); s204, taking out a small image L of the segmented image I in a sliding circulation mode, and obtaining a pixel block position T after amplification; s205, obtaining an edge pixel position database W generated in the step S1; s206, searching whether the position T is intersected with the edge pixel position database W; s207, if no intersecting element is found, the position T is a non-edge part, detail enhancement is needed, and in the image E, K nearest neighbor algorithm searching is carried out on the small block image L to find out a similar small block N smaller than a threshold value; s208, after the small block N is amplified, the small block M at the corresponding position is taken from the image I to obtain a high-low image pair (it needs to be noted that the small block L is a low-resolution image small block corresponding to L (LR), the small block M is a high-resolution image small block corresponding to M (HR), the small block M and the small block M are a group of high-low resolution image pairs, the image E is the reduced X times of the image I, a similar small block N is found in the image E, the corresponding image small block coordinate is obtained, and after the small block N is amplified by X times, the small block M at the corresponding position can be found in the image I, so that the high-low image pair of L-M is obtained; s209, circulating S207, S208, performing sliding search on the image E to obtain an LR-HR image pair database U (through the sliding search, a plurality of M high and low image pairs of L can be obtained, and thus after traversing the image E, an L, a plurality of M LR-HR image pairs database can be generated); s210, obtaining the image A generated in the step S1; s211, taking out all M in the database U by the LR-HR image pair corresponding to the small block image L, and performing pixel weighted fusion to obtain an image small block Q; s212, directly copying the image small block Q to the amplified pixel area of the small block image L in the image A; looping S204 to S211 to finish the detail enhancement of the non-edge part of the image A; and S213, obtaining a non-edge enhanced high-resolution image Z.
Specifically, referring to fig. 5, S201, acquiring an input low-resolution image I; s202, carrying out X-time reduction on the image I by using a traditional interpolation algorithm to obtain an image E; and S203, carrying out small-block image segmentation on the image I. The empirical value is 5 × 5 small blocks; s204, taking out a small image L of the segmented image I in a sliding circulation manner, and amplifying by X times to obtain a pixel block position T; s205, obtaining an edge pixel position database W generated in the S1 process; s206, searching whether the intersection with the position T exists in the edge pixel position database W; and S207, if no intersected element is found, the position T is a non-edge part, and detail enhancement is needed. In the image E, searching the small block image L by a K nearest neighbor algorithm to find out a similar small block N smaller than a threshold value; s208, after the small block N is amplified by X times, the small block M at the corresponding position is taken from the image I to obtain an (L, M) high-low image pair; s209, circulating S207, and performing sliding search on the image E in S208 to obtain an LR-HR image pair database U; s210, obtaining an image A (magnified by X times) generated in the S1 process; s211, taking out all M in the database U of the LR-HR image pair corresponding to the L, and performing pixel weighted fusion to obtain an image small block Q; s212, directly copying the small image block Q to a pixel area of the image A, wherein the L is amplified by X times; looping S204 to S211 to finish the detail enhancement of the non-edge part of the image A; s213, obtaining a non-edge enhanced high-resolution image Z (magnified by X times).
Based on the content of the above method embodiment, as an optional embodiment, the super-resolution single image construction method provided in the embodiment of the present invention specifically includes, in step S3: s301, acquiring the edge enhanced high-resolution image Y generated in the step S1; s302, acquiring a non-edge enhanced high-resolution image Z generated in the step S2; s303, performing multi-image fusion reconstruction on the image Y and the image Z by using a pixel weighting fusion method; s304, adding median filtering to the image subjected to multi-image fusion reconstruction to remove noise; s305, generating a high resolution image O as a final output.
Specifically, referring to fig. 6, S301, an edge-enhanced high-resolution image Y (magnified X times) generated by the S1 process is acquired; s302, acquiring a non-edge enhanced high-resolution image Z (magnified X times) generated by the S2 process; s303, performing multi-image fusion reconstruction on the image Y and the image Z by using a pixel weighting fusion method; s304, adding median filtering to the image after multi-image fusion reconstruction to remove noise; s305, generating a high-resolution image 0 (outputting, amplifying by X times) as a scheme final output.
Based on the content of the foregoing method embodiment, as an optional embodiment, in the super-resolution single-image construction method provided in the embodiment of the present invention, the loop S207 and S208 performs sliding search on the image E to obtain the LR-HR image pair database U, including: and (4) performing sliding search in the image reduced by X times by using a K nearest neighbor algorithm, thereby circularly obtaining an LR-HR high-low image pair database.
Based on the content of the above method embodiment, as an optional embodiment, the super-resolution single image construction method provided in the embodiment of the present invention specifically includes, in steps S211 to S213: and performing weighted fusion on all the HR high images corresponding to one LR in the database by taking out the LR-HR high-low image pair to finally obtain a high-quality image block, and replacing the low-quality image block to enhance the non-edge part of the image.
Based on the content of the foregoing method embodiment, as an optional embodiment, the super-resolution single image construction method provided in the embodiment of the present invention further includes, after obtaining the final output high-resolution image: and enhancing the multi-image fusion effect by using a preset multi-image fusion method template according to the corresponding scene mode of the image selected by the user. For example: and in the portrait mode, gaussian filtering and a gray matrix are added, and filtering processing is performed on the RGB channels, so that the softness and the naturalness of the skin color of the image object are ensured. Another example is: and in a night scene mode, double histogram equalization processing is added, and a low-illumination image object is enhanced.
According to the super-resolution single image construction method provided by the embodiment of the invention, through edge detail reconstruction optimization and single image feature self-learning, the sawtooth phenomenon and the fuzzy phenomenon after the image is super-resolved are effectively solved, and the key details of the image are supplemented, so that the image display effect is effectively enhanced, and the visual experience of a user is optimized.
The implementation basis of the various embodiments of the present invention is realized by programmed processing performed by a device having a processor function. Therefore, in engineering practice, the technical solutions and functions thereof of the embodiments of the present invention can be packaged into various modules. Based on this reality, on the basis of the above embodiments, embodiments of the present invention provide a super-resolution single-image construction apparatus for performing the super-resolution single-image construction method in the above method embodiments. Referring to fig. 2, the apparatus includes: the first main module is used for realizing S1 and performing detail enhancement on the edge part of the image; the second main module is used for realizing S2 and performing detail supplement and enhancement on the non-edge part of the image by using a single image self-learning algorithm; and the third main module is used for realizing S3 and image fusion enhancement, and performing image weighted superposition and filtering denoising on the images output in the S1 and the S2 to obtain a finally output high-resolution image.
According to the super-resolution single image construction device provided by the embodiment of the invention, a plurality of modules in the figure 2 are adopted, a single image super-resolution method is added in a set top box media center application program, the sawtooth phenomenon and the fuzzy phenomenon after the image super-resolution are effectively solved through edge detail reconstruction optimization and single image characteristic self-learning, the key details of the image are supplemented, and the set top box outputs the image after the super-resolution algorithm processing to a television for direct display, so that the image display effect is effectively enhanced, and the visual experience of a user is optimized.
It should be noted that, the apparatus in the apparatus embodiment provided by the present invention may be used to implement methods in other method embodiments provided by the present invention, except that corresponding function modules are provided, and the principle thereof is basically the same as that of the apparatus embodiment provided by the present invention, so long as a person skilled in the art obtains corresponding technical means by combining technical features on the basis of the above apparatus embodiment and referring to specific technical solutions in other method embodiments, and the technical solutions formed by these technical means, on the premise of ensuring that the technical solutions have practicability, the apparatus in the apparatus embodiment may be modified to obtain corresponding apparatus-class embodiments for implementing methods in other method-class embodiments. For example:
based on the content of the above-mentioned device embodiment, as an optional embodiment, the super-resolution single image construction device provided in the embodiment of the present invention further includes: the first sub-module is configured to implement step S1 and specifically includes: s101, acquiring a low-resolution image I; s102, amplifying the low-resolution image I by using an interpolation algorithm to obtain an image A; s103, judging the RGB image of the image A, if the image A is a gray image, selecting S105 to execute, and if the image A is an RGB color image, selecting S104 to execute; s104, performing RGB color fusion operation on the image A to obtain an image B; s105, performing operator edge detection on the input image to obtain a binary image C; s106, extracting the edge contour of the binary image C to generate an edge pixel position database W; s107, creating a contrast enhancement filter; s108, performing contrast stretching on the image A to obtain an image D; s109, carrying out multi-dimensional image filtering operation on the image D and the contrast enhancement filter; s110, the edge-enhanced high-resolution image Y is obtained by the processing of S109.
Based on the content of the above-mentioned device embodiment, as an optional embodiment, the super-resolution single image construction device provided in the embodiment of the present invention further includes: the second sub-module is configured to implement step S2 and specifically includes: s201, acquiring a low-resolution image I; s202, reducing the image I by using an interpolation algorithm to obtain an image E; s203, carrying out small block image segmentation on the image I, wherein an empirical value is 5 multiplied by 5 small blocks; s204, taking out a small image L of the segmented image I in a sliding circulation manner, and obtaining a pixel block position T after amplification; s205, obtaining an edge pixel position database W generated in the step S1; s206, searching whether the intersection with the position T exists in the edge pixel position database W; s207, if no intersecting element is found, the position T is a non-edge part, detail enhancement is needed, and in the image E, K nearest neighbor algorithm searching is carried out on the small block image L to find out a similar small block N smaller than a threshold value; s208, after the small block N is amplified, the small block M at the corresponding position is taken from the image I to obtain a high-low image pair; s209, circulating S207, and S208 performing sliding search on the image E to obtain an LR-HR image pair to a database U; s210, obtaining the image A generated in the step S1; s211, taking out all M in the database U by the LR-HR image corresponding to the small image L, and performing pixel weighted fusion to obtain an image small block Q; s212, directly copying the image small block Q to the amplified pixel area of the small block image L in the image A; circulating S204-S211, and finishing the detail enhancement of the non-edge part of the image A; and S213, obtaining a non-edge enhanced high-resolution image Z.
Based on the content of the above-mentioned device embodiment, as an optional embodiment, the super-resolution single image construction device provided in the embodiment of the present invention further includes: the third sub-module is configured to implement that step S3 specifically includes: s301, acquiring the edge enhanced high-resolution image Y generated in the step S1; s302, acquiring the non-edge enhanced high-resolution image Z generated in the step S2; s303, performing multi-image fusion reconstruction on the image Y and the image Z by using a pixel weighting fusion method; s304, adding median filtering to the image subjected to multi-image fusion reconstruction to remove noise points; s305, a high-resolution image O is generated as a final output.
The method of the embodiment of the invention is realized by depending on the electronic equipment, so that the related electronic equipment is necessarily introduced. With this object in mind, an embodiment of the present invention provides an electronic device, as shown in fig. 3, including: the system comprises at least one processor (processor), a communication Interface (communication Interface), at least one memory (memory) and a communication bus, wherein the at least one processor, the communication Interface and the at least one memory are communicated with each other through the communication bus. The at least one processor may invoke logic instructions in the at least one memory to perform all or a portion of the steps of the methods provided by the various method embodiments described above.
Furthermore, the logic instructions in the at least one memory may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. Based on this recognition, each block in the flowchart or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It should be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A super-resolution single image construction method is characterized by comprising the following steps: s1, performing detail enhancement on an image edge part; s2, performing detail supplement and enhancement on the non-edge part of the image by using a single image self-learning algorithm; and S3, image fusion enhancement, namely performing image weighted superposition and filtering denoising on the images output in the step S1 and the step S2 to obtain a high-resolution image which is finally output.
2. The super-resolution single image construction method according to claim 1, wherein step S1 specifically comprises: s101, acquiring a low-resolution image I; s102, amplifying the low-resolution image I by using an interpolation algorithm to obtain an image A; s103, judging the RGB image of the image A, if the image A is a gray image, selecting S105 to execute, and if the image A is an RGB color image, selecting S104 to execute; s104, performing RGB color fusion operation on the image A to obtain an image B; s105, performing operator edge detection on the input image to obtain a binary image C; s106, extracting the edge contour of the binary image C to generate an edge pixel position database W; s107, creating a contrast enhancement filter; s108, performing contrast stretching on the image A to obtain an image D; s109, carrying out multi-dimensional image filtering operation on the image D and the contrast enhancement filter; and S110, obtaining the edge enhanced high-resolution image Y through the processing of S109.
3. The super-resolution single image construction method according to claim 2, wherein step S2 specifically comprises: s201, acquiring a low-resolution image I; s202, reducing the image I by using an interpolation algorithm to obtain an image E; s203, carrying out small image segmentation on the image I; s204, taking out a small image L of the segmented image I in a sliding circulation mode, and obtaining a pixel block position T after amplification; s205, obtaining an edge pixel position database W generated in the step S1; s206, searching whether the position T is intersected with the edge pixel position database W; s207, if no intersecting element is found, the position T is a non-edge part, detail enhancement is needed, and in the image E, K nearest neighbor algorithm searching is carried out on the small block image L to find out a similar small block N smaller than a threshold value; s208, after the small block N is amplified, the small block M at the corresponding position is taken from the image I to obtain a high-low image pair; s209, circulating S207, and S208 performing sliding search on the image E to obtain an LR-HR image pair to a database U; s210, obtaining the image A generated in the step S1; s211, taking out all M in the database U by the LR-HR image pair corresponding to the small block image L, and performing pixel weighted fusion to obtain an image small block Q; s212, directly copying the image small block Q to the pixel area of the amplified small block image L in the image A; looping S204 to S211 to finish the detail enhancement of the non-edge part of the image A; and S213, obtaining a non-edge enhanced high-resolution image Z.
4. The super-resolution single image construction method according to claim 3, wherein step S3 specifically comprises: s301, acquiring the edge enhanced high-resolution image Y generated in the step S1; s302, acquiring the non-edge enhanced high-resolution image Z generated in the step S2; s303, performing multi-image fusion reconstruction on the image Y and the image Z by using a pixel weighting fusion method; s304, adding median filtering to the image subjected to multi-image fusion reconstruction to remove noise points; s305, generating a high resolution image O as a final output.
5. The super-resolution single-image construction method according to claim 4, wherein in the loop S207 and S208, a sliding search is performed on the image E to obtain an LR-HR image pair database U, and the method comprises: and (4) performing sliding search in the image reduced by X times by using a K nearest neighbor algorithm, thereby circularly obtaining an LR-HR high-low image pair database.
6. The super-resolution single image construction method according to claim 4, wherein steps S211 to S213 specifically include: and performing weighted fusion on all high-low HR images corresponding to one LR in the LR-HR image database by taking out the high-low HR images to finally obtain a high-quality image block, and replacing the low-quality image block to enhance the non-edge part of the image.
7. The super-resolution single-image construction method according to claim 4, further comprising, after the obtaining of the final output high-resolution image: and enhancing the multi-image fusion effect by using a preset multi-image fusion weighted value according to the image corresponding mode scene selected by the user.
8. A super-resolution single image construction apparatus, comprising: the first main module is used for realizing S1 and performing detail enhancement on the edge part of the image; the second main module is used for realizing S2 and performing detail supplement and enhancement on the non-edge part of the image by using a single image self-learning algorithm; and the third main module is used for realizing S3 and image fusion enhancement, and performing image weighted superposition and filtering denoising on the images output in the S1 and the S2 to obtain a finally output high-resolution image.
9. An electronic device, comprising:
at least one processor, at least one memory, and a communication interface; wherein, the first and the second end of the pipe are connected with each other,
the processor, the memory and the communication interface are communicated with each other;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210802001.2A CN115330593A (en) | 2022-07-07 | 2022-07-07 | Super-resolution single image construction method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210802001.2A CN115330593A (en) | 2022-07-07 | 2022-07-07 | Super-resolution single image construction method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115330593A true CN115330593A (en) | 2022-11-11 |
Family
ID=83917208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210802001.2A Pending CN115330593A (en) | 2022-07-07 | 2022-07-07 | Super-resolution single image construction method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115330593A (en) |
-
2022
- 2022-07-07 CN CN202210802001.2A patent/CN115330593A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mahmoud | A new fast skin color detection technique | |
| WO2018082185A1 (en) | Image processing method and device | |
| CN111402258A (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| JP2016505186A (en) | Image processor with edge preservation and noise suppression functions | |
| CN112602088B (en) | Method, system and computer readable medium for improving quality of low light images | |
| CN112184585B (en) | Image completion method and system based on semantic edge fusion | |
| CN107767356B (en) | Image processing method and device | |
| KR101028628B1 (en) | Image texture filtering method, storage medium of storing program for executing the same and apparatus performing the same | |
| CN114627034A (en) | Image enhancement method, training method of image enhancement model and related equipment | |
| CN111353955A (en) | Image processing method, device, equipment and storage medium | |
| CN113939845A (en) | Method, system and computer readable medium for improving image color quality | |
| CN113592776A (en) | Image processing method and device, electronic device and storage medium | |
| CN112991165B (en) | Image processing method and device | |
| US10650499B1 (en) | Fast and effective image inpainting for reticle removal | |
| JP2010286959A (en) | Method, device and program for enhancing face image resolution | |
| CN111429371A (en) | Image processing method and device and terminal equipment | |
| CN112801879A (en) | Image super-resolution reconstruction method and device, electronic equipment and storage medium | |
| CN115578294B (en) | Image enhancement method, device, equipment and storage medium | |
| DE102012201024B4 (en) | A method of processing an image to clarify text in the image | |
| US8538163B2 (en) | Method and system for detecting edges within an image | |
| CN115330593A (en) | Super-resolution single image construction method and equipment | |
| US20160284056A1 (en) | Image processing apparatus and method | |
| CN115471413A (en) | Image processing method and device, computer readable storage medium and electronic device | |
| CN113469889B (en) | Image noise reduction method and device | |
| CN113689333A (en) | Image enhancement method and device |
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 |