CN105931253A - Image segmentation method combined with semi-supervised learning - Google Patents
Image segmentation method combined with semi-supervised learning Download PDFInfo
- Publication number
- CN105931253A CN105931253A CN201610321142.7A CN201610321142A CN105931253A CN 105931253 A CN105931253 A CN 105931253A CN 201610321142 A CN201610321142 A CN 201610321142A CN 105931253 A CN105931253 A CN 105931253A
- Authority
- CN
- China
- Prior art keywords
- image
- gained
- node
- mark
- semi
- 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 29
- 238000003709 image segmentation Methods 0.000 title abstract description 12
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000011218 segmentation Effects 0.000 claims abstract description 6
- 230000006835 compression Effects 0.000 claims abstract description 4
- 238000007906 compression Methods 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000002372 labelling Methods 0.000 claims description 14
- 230000000007 visual effect Effects 0.000 claims description 12
- 238000005192 partition Methods 0.000 claims description 9
- 239000003550 marker Substances 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 6
- 238000005530 etching Methods 0.000 claims description 3
- 238000003707 image sharpening Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 abstract 3
- 238000004891 communication Methods 0.000 abstract 1
- 238000000605 extraction Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T2207/20036—Morphological image processing
- G06T2207/20041—Distance transform
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image segmentation method combined with semi-supervised learning, and the method comprises the following steps: obtaining a gradient image of a to-be-segmented image, sequentially carrying out the compression, sharpening, binarization processing and distance transformation of the to-be-segmented image, and obtaining a distance topographic map of the to-be-segmented image; extracting one point or point set with the biggest gray value in each communication region of an obtained distance transformation image, and enabling the point or point set to serve as a foreground mark; carrying out the watershed transformation of the obtained distance topographic map, and enabling an obtained watershed ridge line to serve as a background mark; shielding a local minimum value in the gradient image, marking the local minimum value of the gradient image according to the obtained foreground mark and background mark, and obtaining the corrected gradient image; and carrying out the obtaining of multi-angle data, the building of a prediction matrix, the building of a training model and the segmentation of an image through a semi-supervised learning method. The image segmentation method can improve the precision of image segmentation.
Description
Technical field
The present invention relates to a kind of pattern dividing method, be specifically related to a kind of image partition method combined based on semi-supervised learning.
Background technology
Image segmentation and Objective extraction, as image procossing and an important branch in computer vision field, attract the concern of numerous researcher always.Meanwhile, image segmentation also has a wide range of applications in fields such as pattern recognition, computer vision, artificial intelligences with Objective extraction.Therefore, the further investigation to image segmentation with Objective extraction not only facilitates image segmentation and the perfect solution of Objective extraction, and contributes to promoting the development in the fields such as pattern recognition, computer vision, artificial intelligence.
At present, image segmentation is mainly used to realize the classification of the data of unknown classification, has great meaning in fields such as Analysis of Medical Treatment Data, the credit classification of the credit card and image classification, once studies success and puts into application, will produce huge Social and economic benef@.But the data in real world (image in such as the Internet) are without class label mostly, and the artificial calibration process of sample wastes time and energy very much and costliness so that the Accurate classification of data acquires a certain degree of difficulty.Recently, semi-supervised learning method based on similar diagram structure has risen the effective tool becoming powerful and popular in the association area such as data mining and pattern classification.Based on the data characteristics in real world, semi-supervised learning is mainly by there being the classification demarcating sample, and has the similarity between label and unlabeled exemplars, discloses the classification of unlabeled exemplars
Traditional image partition method has: mean shift process, normalization dividing method and K Mean Method etc., generally there is segmentation precision low, it is impossible to segmentation adhesion region is without the target on obvious border, and easily mutually obscures cause less divided with image background.
Summary of the invention
For solving the problems referred to above, the invention provides a kind of image partition method combined based on semi-supervised learning, improve the precision that image separates.
For achieving the above object, the technical scheme that the present invention takes is:
A kind of image partition method combined based on semi-supervised learning, comprises the steps:
S1, extract the noise level of image to be split, and adjust bit rate and the resolution of this image to be split according to gained noise level, and with the bit rate of gained and this image to be split of resolution compression；
S2, generate gray-scale map according to the pixel edge strength of step S1 gained image, and based on the described gray-scale map Edge contrast to gained image, and obtain the gradient image of the image of gained；
S3, the image sharpening gained is carried out binary conversion treatment and range conversion successively, obtain the range conversion figure of image to be split, and complete the conversion of range conversion figure, obtain the distance topography of image to be split；
S4, extract the gray value of each connected region in gained range conversion figure maximum a little or point set, as prospect labelling；The distance topography of gained is carried out watershed transform, using the watershed crestal line that obtains as context marker；
S5, the local minimum shielded in described gradient image, according to the local minimum of gradient image described in gained prospect labelling and context marker labelling, obtain described revised gradient image；
S6, revised gradient image is divided into a number of region unit, each image-region after segmentation is considered as a node, set up three images mapping to graphics of each region unit, and add up the weight on the limit on the syntopy between summit, two summits of calculating connection；
S7, all nodes being divided into mark node and do not mark node, wherein mark node occupies the minority；
S8, obtain include mark node and do not mark node by the different visual angles sample data of various visual angles character representation；
S9, the different visual angles sample data of gained is carried out similarity-based learning, construct similar neighborhoods figure, be calculated weight coefficient matrix, and described weight coefficient matrix is carried out symmetrization, normalized；
S10, according to described prospect labelling, initialize a class label matrix；
S11, carry out the iterative process of non-negative sparse label propagation based on the weight coefficient matrix after described class label matrix and symmetrization, normalized, obtain prediction matrix；
S12, the similarity probabilities characterized according to gained prediction matrix, it was predicted that do not mark the accurate classification of node image different visual angles sample data, obtain direct-push image classification results, trained semisupervised classification to model, generate training pattern；
S13, utilize gained training pattern that the node image pattern to be sorted that do not marks in test set is carried out the prediction of classification information, obtain the class label not marking node image pattern to be sorted in test set, to realize the cutting procedure to view data.
Wherein, in described gray-scale map, the gray scale of each pixel is the edge strength of corresponding pixel points in described video image.
Wherein, described Edge contrast includes:
Described gray-scale map is carried out expansive working and/or Gaussian Blur operation, obtains intermediate image A；
Described intermediate image A is performed etching operation, obtains intermediate image A1；
Based on described intermediate image A1, described video image is sharpened process.
The method have the advantages that
By optionally image being sharpened process, it is to avoid doing over-sharpening；The context marker that the prospect labelling obtained beforehand through range conversion and watershed transform obtain revises the gradient image of image to be split, use semi-supervised dividing method that this revised gradient image is split again, obtain image segmentation result, so both having remained, gradient image was carried out watershed transform, can effectively position target object edge, the advantage being partitioned into target object integrity profile, the adhesion region target without obvious border can be distinguished again by prospect labelling and context marker, make not have the phenomenon of less divided and over-segmentation, the image segmentation field of object edge adhesion can well be applicable to, improve the precision of image segmentation, contribute to promoting pattern recognition, computer vision, the development in the fields such as artificial intelligence.
Detailed description of the invention
In order to make objects and advantages of the present invention clearer, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Embodiments provide a kind of image partition method combined based on semi-supervised learning, comprise the steps:
S1, extract the noise level of image to be split, and adjust bit rate and the resolution of this image to be split according to gained noise level, and with the bit rate of gained and this image to be split of resolution compression；
S2, generate gray-scale map according to the pixel edge strength of step S1 gained image, and based on the described gray-scale map Edge contrast to gained image, and obtain the gradient image of the image of gained；
S3, the image sharpening gained is carried out binary conversion treatment and range conversion successively, obtain the range conversion figure of image to be split, and complete the conversion of range conversion figure, obtain the distance topography of image to be split；
S4, extract the gray value of each connected region in gained range conversion figure maximum a little or point set, as prospect labelling；The distance topography of gained is carried out watershed transform, using the watershed crestal line that obtains as context marker；
S5, the local minimum shielded in described gradient image, according to the local minimum of gradient image described in gained prospect labelling and context marker labelling, obtain described revised gradient image；
S6, revised gradient image is divided into a number of region unit, each image-region after segmentation is considered as a node, set up three images mapping to graphics of each region unit, and add up the weight on the limit on the syntopy between summit, two summits of calculating connection；
S7, all nodes being divided into mark node and do not mark node, wherein mark node occupies the minority；
S8, obtain include mark node and do not mark node by the different visual angles sample data of various visual angles character representation；
S9, the different visual angles sample data of gained is carried out similarity-based learning, construct similar neighborhoods figure, be calculated weight coefficient matrix, and described weight coefficient matrix is carried out symmetrization, normalized；
S10, according to described prospect labelling, initialize a class label matrix；
S11, carry out the iterative process of non-negative sparse label propagation based on the weight coefficient matrix after described class label matrix and symmetrization, normalized, obtain prediction matrix；
S12, the similarity probabilities characterized according to gained prediction matrix, it was predicted that do not mark the accurate classification of node image different visual angles sample data, obtain direct-push image classification results, trained semisupervised classification to model, generate training pattern；
S13, utilize gained training pattern that the node image pattern to be sorted that do not marks in test set is carried out the prediction of classification information, obtain the class label not marking node image pattern to be sorted in test set, to realize the cutting procedure to view data.
Wherein, in described gray-scale map, the gray scale of each pixel is the edge strength of corresponding pixel points in described video image.
Wherein, described Edge contrast includes:
Described gray-scale map is carried out expansive working and/or Gaussian Blur operation, obtains intermediate image A；
Described intermediate image A is performed etching operation, obtains intermediate image A1；
Based on described intermediate image A1, described video image is sharpened process.
The above is only the preferred embodiment of the present invention; it should be pointed out that, for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (3)
1. the image partition method combined based on semi-supervised learning, it is characterised in that comprise the steps:
S1, extract the noise level of image to be split, and adjust bit rate and the resolution of this image to be split according to gained noise level, and with the bit rate of gained and this image to be split of resolution compression；
S2, generate gray-scale map according to the pixel edge strength of step S1 gained image, and based on the described gray-scale map Edge contrast to gained image, and obtain the gradient image of the image of gained；
S3, the image sharpening gained is carried out binary conversion treatment and range conversion successively, obtain the range conversion figure of image to be split, and complete the conversion of range conversion figure, obtain the distance topography of image to be split；
S4, extract the gray value of each connected region in gained range conversion figure maximum a little or point set, as prospect labelling；The distance topography of gained is carried out watershed transform, using the watershed crestal line that obtains as context marker；
S5, the local minimum shielded in described gradient image, according to the local minimum of gradient image described in gained prospect labelling and context marker labelling, obtain described revised gradient image；
S6, revised gradient image is divided into a number of region unit, each image-region after segmentation is considered as a node, set up three images mapping to graphics of each region unit, and add up the weight on the limit on the syntopy between summit, two summits of calculating connection；
S7, all nodes being divided into mark node and do not mark node, wherein mark node occupies the minority；
S8, obtain include mark node and do not mark node by the different visual angles sample data of various visual angles character representation；
S9, the different visual angles sample data of gained is carried out similarity-based learning, construct similar neighborhoods figure, be calculated weight coefficient matrix, and described weight coefficient matrix is carried out symmetrization, normalized；
S10, according to described prospect labelling, initialize a class label matrix；
S11, carry out the iterative process of non-negative sparse label propagation based on the weight coefficient matrix after described class label matrix and symmetrization, normalized, obtain prediction matrix；
S12, the similarity probabilities characterized according to gained prediction matrix, it was predicted that do not mark the accurate classification of node image different visual angles sample data, obtain direct-push image classification results, trained semisupervised classification to model, generate training pattern；
S13, utilize gained training pattern that the node image pattern to be sorted that do not marks in test set is carried out the prediction of classification information, obtain the class label not marking node image pattern to be sorted in test set, to realize the cutting procedure to view data.
A kind of image partition method combined based on semi-supervised learning the most according to claim 1, it is characterised in that the edge strength of corresponding pixel points during the gray scale of each pixel is described video image in described gray-scale map.
A kind of image partition method combined based on semi-supervised learning the most according to claim 1, described Edge contrast includes:
Described gray-scale map is carried out expansive working and/or Gaussian Blur operation, obtains intermediate image A；
Described intermediate image A is performed etching operation, obtains intermediate image A1；
Based on described intermediate image A1, described video image is sharpened process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610321142.7A CN105931253B (en) | 2016-05-16 | 2016-05-16 | A kind of image partition method being combined based on semi-supervised learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610321142.7A CN105931253B (en) | 2016-05-16 | 2016-05-16 | A kind of image partition method being combined based on semi-supervised learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105931253A true CN105931253A (en) | 2016-09-07 |
| CN105931253B CN105931253B (en) | 2018-11-06 |
Family
ID=56835930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610321142.7A Expired - Fee Related CN105931253B (en) | 2016-05-16 | 2016-05-16 | A kind of image partition method being combined based on semi-supervised learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105931253B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527349A (en) * | 2017-06-27 | 2017-12-29 | 广州城建职业学院 | Image partition method based on network dynamics evolutionary strategy |
| CN107808162A (en) * | 2017-09-27 | 2018-03-16 | 广东电网有限责任公司江门供电局 | A kind of transformer substation protection pressure plate state comparison method and device |
| CN107967688A (en) * | 2017-12-21 | 2018-04-27 | 联想(北京)有限公司 | The method and system split to the object in image |
| CN108629777A (en) * | 2018-04-19 | 2018-10-09 | 麦克奥迪（厦门）医疗诊断系统有限公司 | A kind of number pathology full slice image lesion region automatic division method |
| CN108898618A (en) * | 2018-06-06 | 2018-11-27 | 上海交通大学 | A kind of Weakly supervised video object dividing method and device |
| CN109460735A (en) * | 2018-11-09 | 2019-03-12 | 中国科学院自动化研究所 | Document binary processing method, system, device based on figure semi-supervised learning |
| CN109523563A (en) * | 2018-11-01 | 2019-03-26 | 华东师范大学 | A method of improving micro-image annotating efficiency |
| CN109740658A (en) * | 2018-12-28 | 2019-05-10 | 陕西师范大学 | A kind of semi-supervision image classification method based on weighted graph |
| CN109829472A (en) * | 2018-12-24 | 2019-05-31 | 陕西师范大学 | Semisupervised classification method based on probability neighbour |
| CN109834941A (en) * | 2019-04-09 | 2019-06-04 | 张柯 | Saving box body 3D printing system |
| CN110119965A (en) * | 2019-05-17 | 2019-08-13 | 浙江和也健康科技有限公司 | A kind of mattress information collector, mattress after-sale service system and method |
| CN110517217A (en) * | 2019-01-23 | 2019-11-29 | 任成付 | Computer overall data identifying platform |
| CN111204046A (en) * | 2019-04-09 | 2020-05-29 | 张柯 | Saving type box body 3D printing system and method |
| CN111767920A (en) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | Region-of-interest extraction method and device, electronic equipment and storage medium |
| CN112348826A (en) * | 2020-10-26 | 2021-02-09 | 陕西科技大学 | Interactive liver segmentation method based on geodesic distance and V-net |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102013017A (en) * | 2010-11-26 | 2011-04-13 | 华中科技大学 | Method for roughly sorting high-resolution remote sensing image scene |
| US20120093381A1 (en) * | 2010-06-25 | 2012-04-19 | Institute Of Automation, Chinese Academy Of Sciences | Method and system for brain tumor segmentation in multi-parameter 3d mr images via robust statistic information propagation |
| CN102902978A (en) * | 2012-08-31 | 2013-01-30 | 电子科技大学 | Object-oriented high-resolution remote-sensing image classification method |
| CN104408731A (en) * | 2014-12-09 | 2015-03-11 | 西安电子科技大学 | Region graph and statistic similarity coding-based SAR (synthetic aperture radar) image segmentation method |
-
2016
- 2016-05-16 CN CN201610321142.7A patent/CN105931253B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120093381A1 (en) * | 2010-06-25 | 2012-04-19 | Institute Of Automation, Chinese Academy Of Sciences | Method and system for brain tumor segmentation in multi-parameter 3d mr images via robust statistic information propagation |
| CN102013017A (en) * | 2010-11-26 | 2011-04-13 | 华中科技大学 | Method for roughly sorting high-resolution remote sensing image scene |
| CN102902978A (en) * | 2012-08-31 | 2013-01-30 | 电子科技大学 | Object-oriented high-resolution remote-sensing image classification method |
| CN104408731A (en) * | 2014-12-09 | 2015-03-11 | 西安电子科技大学 | Region graph and statistic similarity coding-based SAR (synthetic aperture radar) image segmentation method |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527349A (en) * | 2017-06-27 | 2017-12-29 | 广州城建职业学院 | Image partition method based on network dynamics evolutionary strategy |
| CN107808162A (en) * | 2017-09-27 | 2018-03-16 | 广东电网有限责任公司江门供电局 | A kind of transformer substation protection pressure plate state comparison method and device |
| CN107967688A (en) * | 2017-12-21 | 2018-04-27 | 联想(北京)有限公司 | The method and system split to the object in image |
| CN108629777A (en) * | 2018-04-19 | 2018-10-09 | 麦克奥迪（厦门）医疗诊断系统有限公司 | A kind of number pathology full slice image lesion region automatic division method |
| CN108898618B (en) * | 2018-06-06 | 2021-09-24 | 上海交通大学 | Weak surveillance video object segmentation method and device |
| CN108898618A (en) * | 2018-06-06 | 2018-11-27 | 上海交通大学 | A kind of Weakly supervised video object dividing method and device |
| CN109523563A (en) * | 2018-11-01 | 2019-03-26 | 华东师范大学 | A method of improving micro-image annotating efficiency |
| CN109460735A (en) * | 2018-11-09 | 2019-03-12 | 中国科学院自动化研究所 | Document binary processing method, system, device based on figure semi-supervised learning |
| CN109829472A (en) * | 2018-12-24 | 2019-05-31 | 陕西师范大学 | Semisupervised classification method based on probability neighbour |
| CN109829472B (en) * | 2018-12-24 | 2024-05-14 | 陕西师范大学 | Semi-supervised classification method based on probability nearest neighbor |
| CN109740658A (en) * | 2018-12-28 | 2019-05-10 | 陕西师范大学 | A kind of semi-supervision image classification method based on weighted graph |
| CN109740658B (en) * | 2018-12-28 | 2023-04-18 | 陕西师范大学 | Semi-supervised image classification method based on weighted graph |
| CN110517217A (en) * | 2019-01-23 | 2019-11-29 | 任成付 | Computer overall data identifying platform |
| CN109834941A (en) * | 2019-04-09 | 2019-06-04 | 张柯 | Saving box body 3D printing system |
| CN111204046A (en) * | 2019-04-09 | 2020-05-29 | 张柯 | Saving type box body 3D printing system and method |
| CN110119965A (en) * | 2019-05-17 | 2019-08-13 | 浙江和也健康科技有限公司 | A kind of mattress information collector, mattress after-sale service system and method |
| CN111767920A (en) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | Region-of-interest extraction method and device, electronic equipment and storage medium |
| CN111767920B (en) * | 2020-06-30 | 2023-07-28 | 北京百度网讯科技有限公司 | Method and device for extracting region of interest, electronic equipment and storage medium |
| CN112348826A (en) * | 2020-10-26 | 2021-02-09 | 陕西科技大学 | Interactive liver segmentation method based on geodesic distance and V-net |
| CN112348826B (en) * | 2020-10-26 | 2023-04-07 | 陕西科技大学 | Interactive liver segmentation method based on geodesic distance and V-net |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105931253B (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105931253A (en) | Image segmentation method combined with semi-supervised learning | |
| Liu et al. | Curved scene text detection via transverse and longitudinal sequence connection | |
| CN103049763B (en) | Context-constraint-based target identification method | |
| CN108509881A (en) | A kind of the Off-line Handwritten Chinese text recognition method of no cutting | |
| CN105469047A (en) | Chinese detection method based on unsupervised learning and deep learning network and system thereof | |
| Mahmoud | Recognition of writer-independent off-line handwritten Arabic (Indian) numerals using hidden Markov models | |
| CN103793926B (en) | Method for tracking target based on sample reselection procedure | |
| CN107437100A (en) | A kind of picture position Forecasting Methodology based on the association study of cross-module state | |
| CN111027443B (en) | Bill text detection method based on multitask deep learning | |
| Liu et al. | Road centerlines extraction from high resolution images based on an improved directional segmentation and road probability | |
| CN103745233B (en) | The hyperspectral image classification method migrated based on spatial information | |
| CN111340034A (en) | Text detection and identification method and system for natural scene | |
| CN102708384B (en) | Bootstrapping weak learning method based on random fern and classifier thereof | |
| Shu et al. | Center-point-guided proposal generation for detection of small and dense buildings in aerial imagery | |
| CN102945553A (en) | Remote sensing image partition method based on automatic difference clustering algorithm | |
| CN103854290A (en) | Extended target tracking method based on combination of skeleton characteristic points and distribution field descriptors | |
| Zhou et al. | Building segmentation from airborne VHR images using Mask R-CNN | |
| CN104346814A (en) | SAR (specific absorption rate) image segmentation method based on hierarchy visual semantics | |
| CN102436645B (en) | Spectral clustering image segmentation method based on MOD dictionary learning sampling | |
| CN105894035B (en) | SAR image classification method based on SAR-SIFT and DBN | |
| Lin et al. | Radical-based extract and recognition networks for Oracle character recognition | |
| CN102034102B (en) | Image-based significant object extraction method as well as complementary significance graph learning method and system | |
| CN117197459A (en) | Weak supervision semantic segmentation method based on saliency map and attention mechanism | |
| CN106997460A (en) | SAR target identification methods based on depth curve ripple convolutional network | |
| CN102999763B (en) | Based on the top-down vision significance extracting method of scale selection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181106 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |