CN102930518B - Improved sparse representation based image super-resolution method - Google Patents
Improved sparse representation based image super-resolution method Download PDFInfo
- Publication number
- CN102930518B CN102930518B CN201210195620.6A CN201210195620A CN102930518B CN 102930518 B CN102930518 B CN 102930518B CN 201210195620 A CN201210195620 A CN 201210195620A CN 102930518 B CN102930518 B CN 102930518B
- Authority
- CN
- China
- Prior art keywords
- image
- resolution
- super
- low
- block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 15
- 239000000284 extract Substances 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 6
- 239000006185 dispersion Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000004304 visual acuity Effects 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 12
- 238000012545 processing Methods 0.000 abstract description 5
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The invention aims to disclose an improved sparse representation based image super-resolution method. The improved sparse representation based image super-resolution method comprises the steps of: (1) a training stage; and (2) a reconstruction stage, wherein the training stage comprises sub-steps of: (1) collecting an image sample; (2) extracting image characteristics; (3) sorting the image characteristics; and (4) training a super-complete dictionary; and the reconstruction stage comprises the sub-steps of: (1) pre-processing; (2) extracting characteristics of an image block; (3) coding sparsely; and (4) optimizing globally. Compared with the prior art, as the edge and texture characteristics are adopted, a super-complete dictionary with a better structure is obtained through characteristic classification and sparse coding learning, and the most relevant low-dimensional sub-dictionary can be selected fro an input low-resolution image block for reconstruction. The improved sparse representation based image super-resolution method, disclosed by the invention, has the advantages of improving a processing speed to a certain degree, obtaining a relatively good image effect, realizing the purpose of improving the speed and the effect at the same time, and realizing the purpose of the invention.
Description
Technical field
The present invention relates to a kind of image super-resolution method, particularly a kind of image super-resolution method based on the rarefaction representation improved adopting rarefaction representation to carry out process and analysis chart picture.
Background technology
Image super-resolution technology is intended to the restriction overcoming the physical features such as the intrinsic resolution of imaging sensor, low-resolution image is changed into high-definition picture, thus brings better visual experience.
The mode improving image resolution ratio has two kinds, and a kind of is the hardware device directly improving imaging system, and another is the method adopting signal transacting.At present, from physical optics theory, the manufacturing process technology of sensor reaches Limiting Level, can obtain the limiting resolution that hardware provides.In addition, the high-precision sensor of high cost also orders about us and finds other solutions.
Along with the development of image processing techniques and signal processing theory, there is the low-resolution image adopting one or more Same Scene, combining image represents the method for carrying out image super-resolution with technology such as signature analysises, and these methods have the advantages that cost is low, dirigibility is strong.
Image super-resolution is a popular research field of image processing field, propose first to utilize multiframe sequence low-resolution image to reconstruct high-definition picture from Huang and Tsai in 1984, develop into the nowadays advanced image super-resolution method based on rarefaction representation, people are devoted to discussion always both can obtain better effect, can be used for again the method for process in real time.
But the method for present stage is mainly based on the method for study, and the key of these class methods is the feature that image represents and prior model, directly affects edge and the grain effect of image, and the treatment effeciency of method.
Therefore, the special image super-resolution method needing a kind of rarefaction representation based on improving, to solve above-mentioned existing Problems existing.
Summary of the invention
The object of the present invention is to provide a kind of image super-resolution method of the rarefaction representation based on improving, for the deficiencies in the prior art, good edge and grain effect can be obtained, and there is good treatment effeciency.
Technical matters solved by the invention can realize by the following technical solutions:
Based on an image super-resolution method for the rarefaction representation improved, it is characterized in that, it comprises the steps:
(1) training stage
1) image pattern collection, by the high-definition picture that camera acquisition is a large amount of, comprises buildings, animal, flowers and plants, people etc.;
2) image characteristics extraction, first, extracts a pair image block as characteristics of image at random to the height collected and low-resolution image sample; Then, according to set experimental bias threshold value, cutting is carried out to characteristics of image, retain the characteristics of image contained much information; Finally, characteristics of image is normalized;
3) characteristics of image classification, the characteristics of image according to obtaining in above-mentioned steps is classified, and each class is had more structural, and preserves all cluster centre values;
4) train super complete dictionary, according to each category feature obtained in above-mentioned steps, adopt sparse coding training to obtain the sub-dictionary of equal classification, and be merged into as a whole super complete dictionary with the cluster centre value that obtains in above-mentioned steps;
(2) reconstruction stage
1) pre-service, rises to low-resolution image application bicubic interpolation method to be measured the image that sampling obtains target cun size, and image is converted into YCbCr form;
2) image block characteristics extracts, and extracts the image block characteristics of low-resolution image, determine which kind of feature is this feature belong to according to the cluster centre value that above-mentioned steps obtains in the mode of overlapping block, also preserves the average pixel value of this image block simultaneously;
3) sparse coding, carry out sparse coding according to the sub-dictionary of low resolution of the corresponding class of all kinds of feature selecting obtained in above-mentioned steps and try to achieve rarefaction representation coefficient, obtain high-resolution image block characteristics in conjunction with the sub-dictionary of high resolving power, and be added with the average pixel value of the correspondence image block preserved in above-mentioned steps and obtain final high-definition picture block;
4) all high-definition picture blocks obtained in above-mentioned steps are averaged by after correspondence position superposition by global optimization: first; Then, merge with Cb and the Cr passage that obtains in above-mentioned steps and be converted into original picture format; Finally, after utilizing iterative backprojection method to carry out global optimization, Output rusults image.
In one embodiment of the invention, the step 2 in the above-mentioned training stage) in, described low-resolution image again obtains through carrying out the sampling of bicubic interpolation liter to the low-resolution image in step 1).
In one embodiment of the invention, described characteristics of image comprises edge feature and textural characteristics respectively, first, utilizes Canny algorithm to extract binary edge map, ask single order and second order to lead obtain four width gradient images to low-resolution image high-definition picture block; Then, with image block central point be whether edge pixel for benchmark, obtain edge image block and texture image block respectively.
In one embodiment of the invention, what low-resolution image extracted is Gradient Features, and what high-definition picture extracted is the value that image block pixel deducts its average pixel value.
In one embodiment of the invention, described experimental bias threshold value is set as 10, if image block is levied be greater than this threshold value, then retains, otherwise abandons.
In one embodiment of the invention, in the step 3) of above-mentioned training stage, described tagsort process comprises: first, classifies to low-resolution image feature, and obtains all kinds of cluster centre values; Then, according to the low-resolution image feature of having divided class, in the mode of sitting in the right seat, high-definition picture feature is classified;
In one embodiment of the invention, described cluster centre value have employed overlapping clustering method, when keeping original cluster centre value constant, making all kinds of marginal points belong to multiple class by calculating simultaneously, reducing the error caused because of information dispersion.
In one embodiment of the invention, the step 2 in above-mentioned reconstruction stage) in, the size of image block is determined according to the information that super complete dictionary is given, and its overlaid pixel value then can freely be determined; Described image block characteristics comprises edge feature and textural characteristics.
In one embodiment of the invention, in the step 4) of above-mentioned reconstruction stage, after average is got in the superposition of described high-definition picture block, also will fill the pixel that now pixel value is zero, the value of filling is a liter respective pixel value for the illumination passage of the low-resolution image of sampling.
Compared with prior art, the image super-resolution method of the rarefaction representation based on improving of the present invention has following beneficial effect:
1) employ edge feature and textural characteristics respectively, than before based on single features based on rarefaction representation method acquired by edge effect and grain effect good;
2) before the sparse coding stage, devise the tagsort stage, may learn and have more structural dictionary; Also the dictionary of maximally related low dimension can be selected to be reconstructed for the low-resolution image block of input in reconstruction stage, therefore can improve treatment effeciency and image effect;
3) propose there is overlapping clustering method, solve the information dispersion problem caused because of cluster, reduce reconstructed error, further increase image effect.
The image super-resolution method of the rarefaction representation based on improving of the present invention, compared with prior art adopt edge and texture bicharacteristic, obtain having more structural super complete dictionary by tagsort and sparse coding study, the sub-dictionary of maximally related low dimension can be selected to be reconstructed for the low-resolution image block of input, improve processing speed to a certain extent, and obtain good image effect, reach the object simultaneously improving speed and effect, realize object of the present invention.
The detailed description and obtaining that feature of the present invention can consult the graphic and following better embodiment of this case is well understood to.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of training stage of the present invention;
Fig. 2 is the schematic flow sheet of reconstruction stage of the present invention;
Fig. 3 is the schematic flow sheet of feature extraction of the present invention;
Fig. 4 is the schematic flow sheet having overlapping cluster of the present invention.
Embodiment
The technological means realized to make the present invention, creation characteristic, reaching object and effect is easy to understand, below in conjunction with concrete diagram, setting forth the present invention further.
As depicted in figs. 1 and 2, the image super-resolution method of the rarefaction representation based on improving of the present invention, it comprises the steps:
(1) training stage
1) image pattern collection, by the high-definition picture that camera acquisition is a large amount of, comprises buildings, animal, flowers and plants, people etc.;
2) image characteristics extraction, first, carries a pair image block as characteristics of image at random to the height collected and low-resolution image sample; Then, according to set experimental bias threshold value, cutting is carried out to image spy, retain the characteristics of image contained much information; Finally, characteristics of image is normalized;
3) characteristics of image classification, the characteristics of image according to obtaining in above-mentioned steps is classified, and each class is had more structural, and preserves all cluster centre values;
4) train super complete dictionary, according to each category feature obtained in above-mentioned steps, adopt sparse coding training to obtain the sub-dictionary of equal classification, and be merged into as a whole super complete dictionary with the cluster centre value that obtains in above-mentioned steps;
In training dictionary process, setting degree of rarefication parameter is 0.15, after alternate cycles 40 suboptimization, can obtain thinking the super complete dictionary of restraining.Described dictionary comprises edge dictionary and texture dictionary respectively, and wherein each dictionary comprises high resolving power dictionary and low-resolution dictionary;
(2) reconstruction stage
1) pre-service, rises to low-resolution image application bicubic interpolation method to be measured the image that sampling obtains target size size, and image is converted into YCbCr form;
2) image block characteristics extracts, and extracts the image block characteristics of low-resolution image, determine which kind of feature is this feature belong to according to the cluster centre value that above-mentioned steps obtains in the mode of overlapping block, also preserves the average pixel value of this image block simultaneously;
3) sparse coding, carry out sparse coding according to the sub-dictionary of low resolution of the corresponding class of all kinds of feature selecting obtained in above-mentioned steps and try to achieve rarefaction representation coefficient, obtain high-resolution image block characteristics in conjunction with the sub-dictionary of high resolving power, and be added with the average pixel value of the correspondence image block preserved in above-mentioned steps and obtain final high-definition picture block;
4) all high-definition picture blocks obtained in above-mentioned steps are averaged by after correspondence position superposition by global optimization: first; Then, merge with Cb and the Cr passage that obtains in above-mentioned steps and be converted into original picture format; Finally, after utilizing iterative backprojection method to carry out global optimization, export fruit image.
In the present invention, the step 2 in the above-mentioned training stage) in, described low-resolution image again obtains through carrying out the sampling of bicubic interpolation liter to the low-resolution image in step 1).
As shown in Figure 3, described characteristics of image comprises edge feature and textural characteristics respectively, first, utilizes Canny algorithm to extract binary edge map, ask single order and second order to lead obtain four width gradient images to low-resolution image high-definition picture block; Then, with image block central point be whether edge pixel for benchmark, obtain edge image block and texture image block respectively.
In the present invention, what low-resolution image extracted is Gradient Features, and what high-definition picture extracted is the value that image block pixel deducts its average pixel value.In fact the tile size extracted should be 7*7, so finally obtains the low resolution proper vector of 4* (7*7)=196 dimension, the high-resolution features vector of 7*7=49 dimension.
Described experimental bias threshold value is set as 10, if image block characteristics is greater than this threshold value, then retains, otherwise abandons.
In the present invention, in the step 3) of above-mentioned training stage, described tagsort process comprises: first, classifies to low-resolution image feature, and obtains all kinds of cluster centre values; Then, according to the low-resolution image feature of having divided class, in the mode of sitting in the right seat, high-definition picture feature is classified.
As shown in Figure 4, described cluster centre value have employed overlapping clustering method, when keeping original cluster centre value constant, making all kinds of marginal points belong to multiple class simultaneously, reducing the error caused because of information dispersion by calculating.In the present invention, get R=0.1 comparatively suitable.
In the present invention, the step 2 in above-mentioned reconstruction stage) in, the size of image block is determined according to the information that super complete dictionary is given, and its overlaid pixel value then can freely be determined; Described image block characteristics comprises edge feature and textural characteristics.
In the present invention, in the step 4) of above-mentioned reconstruction stage, described high-definition picture block is folded get average after, also will fill the pixel that now pixel value is zero, the value of filling is a liter respective pixel value for the illumination passage of the low-resolution image of sampling.
More than show and describe ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; what describe in above-described embodiment and instructions just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications; these changes and improvements all fall in the claimed scope of the invention, and application claims protection domain is defined by appending claims and equivalent thereof.
Claims (7)
1., based on an image super-resolution method for the rarefaction representation improved, it is characterized in that, it comprises the steps:
(1) training stage
1) image pattern collection, by the high-definition picture that camera acquisition is a large amount of, comprises buildings, animal, flowers and plants, people;
2) image characteristics extraction, first, extracts a pair image block as characteristics of image at random to the height collected and low-resolution image sample; Then, according to set experimental bias threshold value, cutting is carried out to characteristics of image, retain the characteristics of image contained much information; Finally, characteristics of image is normalized;
3) characteristics of image classification, the characteristics of image according to obtaining in above-mentioned steps is classified, and each class is had more structural, and preserves all cluster centre values; Described tagsort process comprises: first, classifies to low-resolution image feature, and obtains all kinds of cluster centre values; Then, according to the low-resolution image feature of having divided class, in the mode of sitting in the right seat, high-definition picture feature is classified;
4) train super complete dictionary, according to each category feature obtained in above-mentioned steps, adopt sparse coding training to obtain the sub-dictionary of identical category, and be merged into as a whole super complete dictionary with the cluster centre value that obtains in above-mentioned steps;
(2) reconstruction stage
1) pre-service, rises to low-resolution image application bicubic interpolation method to be measured the image that sampling obtains target size size, and image is converted into YCbCr form;
2) image block characteristics extracts, and extracts the image block characteristics of low-resolution image, determine which kind of feature is this feature belong to according to the cluster centre value that above-mentioned steps obtains in the mode of overlapping block, also preserves the average pixel value of this image block simultaneously;
3) sparse coding, carry out sparse coding according to the sub-dictionary of low resolution of the corresponding class of all kinds of feature selecting obtained in above-mentioned steps and try to achieve rarefaction representation coefficient, obtain high-resolution image block characteristics in conjunction with the sub-dictionary of high resolving power, and be added with the average pixel value of the correspondence image block preserved in above-mentioned steps and obtain final high-definition picture block;
4) all high-definition picture blocks obtained in above-mentioned steps are averaged by after correspondence position superposition by global optimization: first; Then, merge with Cb and the Cr passage that obtains in above-mentioned steps and be converted into original picture format; Finally, after utilizing iterative backprojection method to carry out global optimization, Output rusults image.
2. as claimed in claim 1 based on the image super-resolution method of the rarefaction representation improved, it is characterized in that, described characteristics of image comprises edge feature and textural characteristics respectively, first, utilize Canny algorithm to extract binary edge map to high-definition picture block, ask single order and second order to lead to low-resolution image and obtain four width gradient images; Then, with image block central point be whether edge pixel for benchmark, obtain edge image block and texture image block respectively.
3. as claimed in claim 1 based on the image super-resolution method of the rarefaction representation improved, it is characterized in that, what low-resolution image extracted is Gradient Features, and what high-definition picture extracted is the value that image block pixel deducts its average pixel value.
4., as claimed in claim 1 based on the image super-resolution method of the rarefaction representation improved, it is characterized in that, described experimental bias threshold value is set as 10, if image block characteristics is greater than this threshold value, then retains, otherwise abandons.
5. as claimed in claim 1 based on the image super-resolution method of the rarefaction representation improved, it is characterized in that, described cluster centre value have employed overlapping clustering method, when keeping original cluster centre value constant, making all kinds of marginal points belong to multiple class by calculating simultaneously, reducing the error caused because of information dispersion.
6. as claimed in claim 1 based on the image super-resolution method of the rarefaction representation improved, it is characterized in that, step 2 in above-mentioned reconstruction stage) in, the size of image block is determined according to the information that super complete dictionary is given, and its overlaid pixel value then can freely be determined; Described image block characteristics comprises edge feature and textural characteristics.
7. as claimed in claim 1 based on the image super-resolution method of the rarefaction representation improved, it is characterized in that, step 4 in above-mentioned reconstruction stage) in, after average is got in described high-definition picture block superposition, also will fill the pixel that now pixel value is zero, the value of filling is a liter respective pixel value for the illumination passage of the low-resolution image of sampling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210195620.6A CN102930518B (en) | 2012-06-13 | 2012-06-13 | Improved sparse representation based image super-resolution method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210195620.6A CN102930518B (en) | 2012-06-13 | 2012-06-13 | Improved sparse representation based image super-resolution method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102930518A CN102930518A (en) | 2013-02-13 |
| CN102930518B true CN102930518B (en) | 2015-06-24 |
Family
ID=47645308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210195620.6A Active CN102930518B (en) | 2012-06-13 | 2012-06-13 | Improved sparse representation based image super-resolution method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102930518B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015180055A1 (en) * | 2014-05-28 | 2015-12-03 | 北京大学深圳研究生院 | Super-resolution image reconstruction method and apparatus based on classified dictionary database |
| CN104113789B (en) * | 2014-07-10 | 2017-04-12 | 杭州电子科技大学 | On-line video abstraction generation method based on depth learning |
| CN104677309B (en) * | 2015-03-24 | 2017-04-26 | 哈尔滨理工大学 | Highlight inhibition method for strong reflection surface encoding light measurement based on sparse expression |
| CN105678728A (en) * | 2016-01-19 | 2016-06-15 | 西安电子科技大学 | High-efficiency super-resolution imaging device and method with regional management |
| CN106600536B (en) * | 2016-12-14 | 2020-02-14 | 同观科技（深圳）有限公司 | Video image super-resolution reconstruction method and device |
| CN106780342A (en) * | 2016-12-28 | 2017-05-31 | 深圳市华星光电技术有限公司 | Single-frame image super-resolution reconstruction method and device based on the reconstruct of sparse domain |
| CN108932697B (en) * | 2017-05-26 | 2020-01-17 | 杭州海康威视数字技术股份有限公司 | Distortion removing method and device for distorted image and electronic equipment |
| TWI635752B (en) | 2017-08-31 | 2018-09-11 | Yuan Ze University | Method, and image processing device, and display system for power-constrained image enhancement |
| CN107967669B (en) * | 2017-11-24 | 2022-08-09 | 腾讯科技（深圳）有限公司 | Picture processing method and device, computer equipment and storage medium |
| CN108830792B (en) * | 2018-05-09 | 2022-03-11 | 浙江师范大学 | Image super-resolution method using multi-class dictionary |
| CN111612691A (en) * | 2020-04-17 | 2020-09-01 | 重庆大学 | Image super-resolution processing improvement method based on sparse representation |
| CN114697543B (en) * | 2020-12-31 | 2023-05-19 | 华为技术有限公司 | Image reconstruction method, related device and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556690A (en) * | 2009-05-14 | 2009-10-14 | 复旦大学 | Image super-resolution method based on overcomplete dictionary learning and sparse representation |
| CN102142137A (en) * | 2011-03-10 | 2011-08-03 | 西安电子科技大学 | High-resolution dictionary based sparse representation image super-resolution reconstruction method |
| CN102156875A (en) * | 2011-03-25 | 2011-08-17 | 西安电子科技大学 | Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning |
-
2012
- 2012-06-13 CN CN201210195620.6A patent/CN102930518B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556690A (en) * | 2009-05-14 | 2009-10-14 | 复旦大学 | Image super-resolution method based on overcomplete dictionary learning and sparse representation |
| CN102142137A (en) * | 2011-03-10 | 2011-08-03 | 西安电子科技大学 | High-resolution dictionary based sparse representation image super-resolution reconstruction method |
| CN102156875A (en) * | 2011-03-25 | 2011-08-17 | 西安电子科技大学 | Image super-resolution reconstruction method based on multitask KSVD (K singular value decomposition) dictionary learning |
Non-Patent Citations (3)
| Title |
|---|
| 基于图像块分类稀疏表示的超分辨率重构算法;练秋生等;《电子学报》;20120531;第40卷(第5期);第4-6部分 * |
| 基于词典学习和稀疏表示的超分辨率方法;浦剑等;《模式识别与人工智能》;20100630;第23卷(第3期);全文 * |
| 稀疏字典编码的超分辨率重建;李民等;《软件学报》;20110526;第23卷(第5期);第2.3部分 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102930518A (en) | 2013-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102930518B (en) | Improved sparse representation based image super-resolution method | |
| WO2021184891A1 (en) | Remotely-sensed image-based terrain classification method, and system | |
| CN109886986B (en) | Dermatoscope image segmentation method based on multi-branch convolutional neural network | |
| Li et al. | Joint example-based depth map super-resolution | |
| CN101976435B (en) | Combination learning super-resolution method based on dual constraint | |
| CN103077505B (en) | Based on the image super-resolution rebuilding method of dictionary learning and documents structured Cluster | |
| CN105046672A (en) | Method for image super-resolution reconstruction | |
| CN107358576A (en) | Depth map super resolution ratio reconstruction method based on convolutional neural networks | |
| CN106204449A (en) | A kind of single image super resolution ratio reconstruction method based on symmetrical degree of depth network | |
| CN102629374B (en) | Image super resolution (SR) reconstruction method based on subspace projection and neighborhood embedding | |
| CN105069746A (en) | Video real-time human face substitution method and system based on partial affine and color transfer technology | |
| CN105335929A (en) | Depth map super-resolution method | |
| CN104751432A (en) | Image reconstruction based visible light and infrared image fusion method | |
| CN103984963B (en) | Method for classifying high-resolution remote sensing image scenes | |
| CN103854268A (en) | Image super-resolution reconstruction method based on multi-core gaussian process regression | |
| KR101028628B1 (en) | Image texture filtering method, storage medium of storing program for executing the same and apparatus performing the same | |
| CN106169174A (en) | A kind of image magnification method | |
| CN104036468A (en) | Super-resolution reconstruction method for single-frame images on basis of pre-amplification non-negative neighbor embedding | |
| CN103971354A (en) | Method for reconstructing low-resolution infrared image into high-resolution infrared image | |
| CN110111272A (en) | A kind of artificial intelligence infrared image processing instrument, control system and control method | |
| CN107563963B (en) | Super-resolution reconstruction method based on single depth map | |
| CN113221869A (en) | Medical invoice structured information extraction method, device and equipment and storage medium | |
| Dai et al. | Salient object detection from multi-spectral remote sensing images with deep residual network | |
| CN106157240A (en) | Remote sensing image super resolution method based on dictionary learning | |
| CN104992407A (en) | Image super-resolution method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 201505 Jinshan District, Shanghai, Lin Ting Town, Temple Ping Road, room 16, No. 599 Applicant after: SHANGHAI WINNER INFORMATION TECHNOLOGY CO., INC. Address before: 201505 Jinshan District, Shanghai, Lin Ting Town, Temple Ping Road, room 16, No. 599 Applicant before: Huina Network Information Science & Technology Co., Ltd. |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: HUINA NETWORK INFORMATION SCIENCE + TECHNOLOGY CO., LTD. TO: SHANGHAI WINNER INFORMATION TECHNOLOGY CO., INC. |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 201505 Shanghai city Jinshan District ting Lin Zhen Ting Feng Road No. 333, room 216 Patentee after: Winner Technology Co.,Ltd. Address before: 201505, room 16, No. 599, Ping Nan Road, ting Lin Town, Shanghai, Jinshan District Patentee before: SHANGHAI WINNER INFORMATION TECHNOLOGY Co.,Inc. |
|
| CP03 | Change of name, title or address | ||
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 201203 No. 6, Lane 55, Chuanhe Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai Patentee after: Winner Technology Co.,Ltd. Address before: 201505 Room 216, 333 Tingfeng Highway, Tinglin Town, Jinshan District, Shanghai Patentee before: Winner Technology Co.,Ltd. |