CN106296663A - A kind of SAR sea ice image partition method and system - Google Patents
A kind of SAR sea ice image partition method and system Download PDFInfo
- Publication number
- CN106296663A CN106296663A CN201610616286.5A CN201610616286A CN106296663A CN 106296663 A CN106296663 A CN 106296663A CN 201610616286 A CN201610616286 A CN 201610616286A CN 106296663 A CN106296663 A CN 106296663A
- Authority
- CN
- China
- Prior art keywords
- sea ice
- ice image
- sar sea
- sar
- split
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Radar Systems Or Details Thereof (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of SAR sea ice image partition method and system.The method includes: read SAR sea ice image area to be split;SAR sea ice image area to be split is carried out regular partition, and being divided into several pixel sizes ism×mSub-block;Use clustering algorithm to SAR sea ice image area primary segmentation to be split;Primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.This system includes: image reading module, regular partition module, primary segmentation module, medium filtering module, and the method for regular partition is combined by the present invention with traditional KLFCM dividing method, from largely decreasing the noise impact on segmentation result.Owing to regular partition is poor to edge fitting effect, the method of medium filtering is combined with first two method, carries out post-processing operation, the most preferably achieve the matching to edge, and completely eliminate the noise impact on SAR sea ice image, obtain the segmentation result that precision is high.
Description
Technical field
The present invention relates to technical field of image processing, be specifically related to a kind of SAR sea ice image partition method and system.
Background technology
Sea ice information is to the hydrology of particularly arctic regions, high latitude area, atmospheric heat circulation, ocean current and ecosystem all
There is earth shaking impact.Once sea ice extension history, will cause closing a port or harbour, and navigation channel blocks, the problems such as boats and ships are impaired, therefore, it is achieved
Quickly, accurately, the navigation effective to safety of ship of real-time sea ice monitoring is particularly significant.Synthetic aperture radar (Synthetic
Aperture Radar, SAR) system not climate condition and the impact at sunshine, can full weather round-the-clock be entered by sea ice situation
Row monitoring, has become as the instrument that sea ice monitoring is maximally efficient at present.And SAR sea ice image is segmented to sea ice image
During reason, occupy critical role.But in SAR sea ice image, it is the fuzzyyest that its distinctive speckle noise leads image, and this makes
Obtain people and be difficult to accurately differentiate position and the shape of sea ice.Therefore, carry out being partitioned into image procossing neck for SAR sea ice image
The focus of territory research and difficulties.
In terms of SAR sea ice image segmentation, it has been proposed that many methods, including: threshold method, clustering method, combination
Rim detection and region merging technique mixed method, based on markov random file method etc..Owing to the special image-forming mechanism of SAR system makes
Obtaining SAR image and produce distinctive speckle noise, the gray scale of each pixel presents bigger uncertainty, studies discovery, mould through scholar
Stick with paste theory to be more suitable for studying this uncertainty.And fuzzy C-mean algorithm (FCM) clustering algorithm is the classics in fuzzy cluster analysis
Algorithm, therefore processes SAR sea ice image frequently with FCM.But owing to traditional FCM uses the mode of exponential weighting to represent its mould
Paste degree, and exponential weighting does not has clear and definite physical interpretation, therefore uses KLFCM (Kullback-Lerbler
InformationFCM, KLFCM) algorithm replaces traditional FCM algorithm, and KL information is drawn in the way of arithmetic weight by this algorithm
Enter in FCM algorithm object function, to represent segmentation fog-level.But KLFCM is a kind of fuzzy clustering image based on pixel to be divided
Segmentation method, it is difficult to the speckle noise of SAR image is completely eliminated.For solving this problem, propose binding rule and divide and the side of KLFCM
Method carries out the segmentation of SAR sea ice image.
Summary of the invention
The deficiency existed for prior art, the present invention provides a kind of SAR sea ice image partition method and system.
A kind of SAR sea ice image partition method, it is characterised in that including:
Step 1: read SAR sea ice image area to be split;
Step 2: SAR sea ice image area to be split is carried out regular partition, being divided into several pixel sizes is m × m's
Sub-block;
Step 3: use fuzzy clustering algorithm to SAR sea ice image area primary segmentation to be split;
Step 4: primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.
Described step 3 is to use KLFCM algorithm to SAR sea ice image area primary segmentation to be split.
Described step 4 carries out medium filtering process to primary segmentation result, specifically comprises the following steps that
Step 4.1: set window size;
Step 4.2: choose a certain pixel in primary segmentation result, with this pixel as window center, by institute in window
The gray value having pixel sorts, and substitutes the gray value of this pixel by the gray value intermediate value after sequence, ties primary segmentation
In Guo, all pixels perform this process, obtain medium filtering result.
The present invention also provides for a kind of SAR sea ice image segmentation system, including:
Image reading module: read SAR sea ice image area to be split;
Regular partition module: SAR sea ice image area to be split is carried out regular partition, being divided into several pixel sizes is
The sub-block of m × m;
Primary segmentation module: use clustering algorithm to SAR sea ice image area primary segmentation to be split;
Medium filtering module: primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.
Described primary segmentation module: use KLFCM algorithm to SAR sea ice image area primary segmentation to be split.
Described medium filtering module, including:
Window setting module: set window size;
Processing module: choose a certain pixel in primary segmentation result, with this pixel as window center, by institute in window
The gray value having pixel sorts, and substitutes the gray value of this pixel by the gray value intermediate value after sequence, ties primary segmentation
In Guo, all pixels perform this process, obtain medium filtering result.
Beneficial effect:
1, traditional KLFCM dividing method is difficult to overcome the SAR distinctive speckle noise of sea ice image, and rule is drawn by the present invention
The method divided is combined with it, from largely decreasing the noise impact on segmentation result.
2, poor to edge fitting effect due to regular partition, the present invention is again by the method for medium filtering and first two method
Combine, carry out post-processing operation, the most preferably achieve the matching to edge, and completely eliminate noise to SAR sea
The impact of ice atlas picture, has obtained the segmentation result that precision is high.
3, the method is easily achieved, and speed, it is adaptable to large scale image.
Accompanying drawing explanation
Fig. 1 is SAR sea ice image partition method flow chart in the specific embodiment of the invention;
Fig. 2 is regular partition schematic diagram in the specific embodiment of the invention, and (a) is the regular partition of SAR sea ice image area,
(b) regular partition result;
Fig. 3 is the particular flow sheet of step 3 in the specific embodiment of the invention;
Fig. 4 is the particular flow sheet of step 4 in the specific embodiment of the invention;
Fig. 5 is SAR sea ice image in the specific embodiment of the invention, and (a) is the template containing 4 homogeneous regions, and (b) is
Synthesis analog image;
Fig. 6 is the experimental result in the specific embodiment of the invention, and (a) represents the inventive method segmentation result, and (b) represents
The segmentation result of control methods;
Fig. 7 is the visual evaluation result of the inventive method in the specific embodiment of the invention, and (a) represents the wheel of segmentation result
Profile, (b) represents contour line and artwork stack result;
Fig. 8 is the visual evaluation result of control methods in the specific embodiment of the invention, and (a) represents the profile of segmentation result
Line, (b) represents contour line and artwork stack result;
Fig. 9 (a)~(b) are respectively the two width true SAR sea ice image in the specific embodiment of the invention;
Figure 10 (a)~(b) are respectively two width true SAR sea ice figure primary segmentation result;
Figure 11 (a)~(b) are respectively the two width true SAR final segmentation result of sea ice figure;
Figure 12 (a)~(b) are respectively the contour line extracting two width true SAR sea ice image segmentation result, and (c), (d) are respectively
For by contour line and true SAR sea ice image overlay result;
Figure 13 is SAR sea ice image segmentation system block diagram in the specific embodiment of the invention;
Figure 14 is medium filtering module frame chart in the specific embodiment of the invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings the detailed description of the invention of the present invention is elaborated.
A kind of SAR sea ice image partition method, as it is shown in figure 1, include:
Step 1: read SAR sea ice image area to be split;
Pixel (x in SAR sea ice image area D to be spliti, yi) gray value collection be combined into z={zi=z (xi, yi);I=
1 ..., n, (xi, yi) ∈ D}, wherein (xi, yi) for being defined on pixel on SAR sea ice image area D to be split, i is pixel
Index, n is total pixel number, ziGray value for ith pixel point.
Step 2: SAR sea ice image area to be split is carried out regular partition, being divided into several pixel sizes is m × m's
Sub-block;As in figure 2 it is shown, the regular partition that (a) is SAR sea ice image area, (b) regular partition result;Regular partition is utilized to be drawn by D
It is divided into N number of containing m × m pixel rule sub-block Pj, D={Pj, j=1 ..., N}, wherein, N=n/m2, each in present embodiment
Sub-block contains 4 × 4 pixels;
Step 3: use KLFCM algorithm to SAR sea ice image area primary segmentation to be split;
Concrete steps are as shown in Figure 3:
Step 3.1: objective function J;
Wherein, ujkDegree of membership kth clustered for jth sub-block, 0≤ujk≤ 1, Wherein, k ∈ 1 ..., and c} is cluster index, and c is total cluster numbers, if it is variable, and λ
For parameter;All ujkConstitute fuzzy membership matrix U=[ujk]N×c, and U describes the mould to SAR sea ice image area D to be split
Stick with paste segmentation i.e. primary segmentation;
djkNon-similarity for jth sub-block with kth cluster centre is estimated, and utilizes Euclidean distance to define djk=| | xj-
vk||2, wherein, xjFor sub-block PjAverage gray value, vkFor cluster centre;djhFor jth sub-block and h cluster centre
Non-similarity is estimated;
πkControl for kth cluster clusters scale parameter,πhIt it is the control cluster yardstick of the h cluster
Parameter;
Step 3.2: each parameter of KLFCM algorithm is set: loop iteration indicator t=0, cluster numbers c SAR the most to be split sea ice
Classification number in image area and iteration stopping conditional parameter ε;
Step 3.3: random initializtion membership function ujk (0)With object function J(0)=0, by membership function ujk (0)Instead
Obfuscation, obtains the generic of each sub-block;
Step 3.4: according to membership function ujk (t)Calculate and control cluster scale parameter πk (t+1);
Step 3.5: by object function J(t)To cluster centre vk (t+1)Derivation, and make it be equal to zero, obtain cluster centre vk (t +1),According to cluster centre vk (t+1)Calculate non-similarity and estimate djk (t+1);
Step 3.6: by object function J(t)To membership function ujk (t+1)Derivation, and make it be equal to zero, obtain degree of membership letter
Number ujk (t+1),
Step 3.7: calculating target function J (t+1)If, max | J(t)-J(t+1) | < ε, exits circulation, obtains primary segmentation
As a result, otherwise make t=t+1 and return step 3.4 and continue iteration.
Step 4: primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.
Described step 3 is to use KLFCM algorithm to SAR sea ice image area primary segmentation to be split.
Described step 4 carries out medium filtering process to primary segmentation result, as shown in Figure 4, specifically comprises the following steps that
Step 4.1: setting window size (2a+1) × (2a+1), wherein a={1,2 ..., for self-defined constant;
Step 4.2: choose in primary segmentation result images that (s, l) pixel, wherein s, l are respectively line index and Lie Suo
Draw, s=1 ..., nl, l=1 ..., n2, n1, n2 are the respectively line number in primary segmentation result images and columns, with this picture
Vegetarian refreshments is window center, is sorted by the gray value of pixels all in window, and substitutes this picture by the gray value intermediate value after sequence
The gray value of vegetarian refreshments, until pixels all in primary segmentation result are carried out this operation, process terminates.
The present invention also provides for a kind of SAR sea ice image segmentation system, as shown in figure 13, and including:
Image reading module: read SAR sea ice image area to be split;
Regular partition module: SAR sea ice image area to be split is carried out regular partition, being divided into several pixel sizes is
The sub-block of m × m;
Primary segmentation module: use clustering algorithm to SAR sea ice image area primary segmentation to be split;
Medium filtering module: primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.
Described primary segmentation module: use KLFCM algorithm to SAR sea ice image area primary segmentation to be split.
Described medium filtering module, as shown in figure 14, including:
Window setting module: set window size;
Processing module: choose a certain pixel in primary segmentation result, with this pixel as window center, by institute in window
The gray value having pixel sorts, and substitutes the gray value of this pixel by the gray value intermediate value after sequence, ties primary segmentation
In Guo, all pixels perform this process, obtain medium filtering result.
In present embodiment design a template containing 4 homogeneous regions as shown in Fig. 5 (a), and according to template with
Parameter synthesis one width analog image as shown in Fig. 5 (b) in table 1, application the inventive method and control methods (KLFCM) are right respectively
Analog image is split.
Table 1
As shown in Figure 6, wherein Fig. 6 (a) represents the segmentation result of the inventive method to experimental result, and Fig. 6 (b) represents analogy
Method segmentation result.Fig. 7 is the visual evaluation result of the inventive method, and (a) represents the contour line of segmentation result, and (b) represents will wheel
Profile and artwork stack result;Fig. 8 is the visual evaluation result of control methods in the specific embodiment of the invention, and (a) represents and divide
Cutting the contour line of result, (b) represents contour line and artwork stack result;According to template image, the segmentation to both approaches
Result takes the mode of confusion matrix to carry out quantitative assessment, and result is as shown in table 2.
Table 2
For the effectiveness of further verification method, the 2 width true SAR sea ice image as shown in Fig. 9 (a), (b) is carried out
Experiment, Figure 10 (a), (b) are to 2 width true SAR sea ice image primary segmentation result, according to result it can be seen that just segmentation takes
Obtained preferable experimental result, and substantially by the elimination of spot noise of SAR image, only remained sub-fraction noise, and edge is the most not
It is particularly smooth;Figure 11 (a), (b) for test final segmentation result, from final result it can be seen that not only noise disappeared completely
Remove, and border also becomes more to smooth.Visual evaluation result such as figure to the 2 width true SAR final segmentation result of sea ice image
Shown in 12, wherein Figure 12 (a), (b) are for extracting segmentation result contour line, and Figure 12 (c), (d) are by contour line and true SAR sea ice
The result of image overlay, the more preferable matching in boundary line from stack result it can be seen that after being filtered true SAR figure
Picture.
Particular embodiments described above, has been carried out the purpose of the present invention, technical scheme and beneficial effect the most in detail
Describe in detail bright, be it should be understood that the specific embodiment that the foregoing is only the present invention, be not limited to the present invention, all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvement etc. done, should be included in the guarantor of the present invention
Within the scope of protecting.
Claims (6)
1. a SAR sea ice image partition method, it is characterised in that including:
Step 1: read SAR sea ice image area to be split;
Step 2: SAR sea ice image area to be split is carried out regular partition, being divided into several pixel sizes ism×mSub-block;
Step 3: use fuzzy clustering algorithm to SAR sea ice image area primary segmentation to be split;
Step 4: primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.
SAR sea ice image partition method the most according to claim 1, it is characterised in that described step 3 is to use KLFCM
Algorithm is to SAR sea ice image area primary segmentation to be split.
SAR sea ice image partition method the most according to claim 1, it is characterised in that to primary segmentation in described step 4
Result carries out medium filtering process, specifically comprises the following steps that
Step 4.1: set window size;
Step 4.2: choose a certain pixel in primary segmentation result, with this pixel as window center, by pictures all in window
The gray value sequence of vegetarian refreshments, and substitute the gray value of this pixel by the gray value intermediate value after sequence, in primary segmentation result
All pixels perform this process, obtain medium filtering result.
4. a SAR sea ice image segmentation system, it is characterised in that including:
Image reading module: read SAR sea ice image area to be split;
Regular partition module: SAR sea ice image area to be split is carried out regular partition, being divided into several pixel sizes ism×m
Sub-block;
Primary segmentation module: use fuzzy clustering algorithm to SAR sea ice image area primary segmentation to be split;
Medium filtering module: primary segmentation result is carried out medium filtering process, obtains SAR sea ice image segmentation result.
System the most according to claim 4, it is characterised in that described primary segmentation module: use KLFCM algorithm to treat point
Cut SAR sea ice image area primary segmentation.
System the most according to claim 4, it is characterised in that described medium filtering module, including:
Window setting module: set window size;
Processing module: choose a certain pixel in primary segmentation result, with this pixel as window center, by pictures all in window
The gray value sequence of vegetarian refreshments, and substitute the gray value of this pixel by the gray value intermediate value after sequence, in primary segmentation result
All pixels perform this process, obtain medium filtering result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610616286.5A CN106296663A (en) | 2016-08-01 | 2016-08-01 | A kind of SAR sea ice image partition method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610616286.5A CN106296663A (en) | 2016-08-01 | 2016-08-01 | A kind of SAR sea ice image partition method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106296663A true CN106296663A (en) | 2017-01-04 |
Family
ID=57663648
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610616286.5A Pending CN106296663A (en) | 2016-08-01 | 2016-08-01 | A kind of SAR sea ice image partition method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106296663A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107170006A (en) * | 2017-06-01 | 2017-09-15 | 中国科学院遥感与数字地球研究所 | The separation method and device of sea ice and Seawater Information in diameter radar image |
CN107230209A (en) * | 2017-05-26 | 2017-10-03 | 辽宁工程技术大学 | With reference to K S distances and the SAR image segmentation method of RJMCMC algorithms |
CN108508427A (en) * | 2018-07-04 | 2018-09-07 | 鲁东大学 | A kind of sea ice method for detecting area, device and equipment based on pathfinder |
CN109447993A (en) * | 2018-10-25 | 2019-03-08 | 哈尔滨工程大学 | A kind of sea ice image partition method based on mixing true and false sample strategy |
CN110374045A (en) * | 2019-07-29 | 2019-10-25 | 哈尔滨工业大学 | A kind of intelligence de-icing method |
CN115760748A (en) * | 2022-11-14 | 2023-03-07 | 江苏科技大学 | Ice body annular crack size measurement method based on deep learning |
-
2016
- 2016-08-01 CN CN201610616286.5A patent/CN106296663A/en active Pending
Non-Patent Citations (3)
Title |
---|
HIDETOMO ICHIHASHI 等: "《Fuzzy c-Means Clustering with Regularization by K-L Information》", 《2001 IEEE INTERNATIONAL FUZZY SYSTEMS CONFERENCE》 * |
YUANYUAN HU 等: "《SAR Image Unsupervised Segmentation Based on A Modified Fuzzy C-means Algorithm》", 《SIXTH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY》 * |
郭庆燕 等: "《一种提取MRI图像感兴趣区域的分割方法》", 《福州大学学报(自然科学版)》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107230209A (en) * | 2017-05-26 | 2017-10-03 | 辽宁工程技术大学 | With reference to K S distances and the SAR image segmentation method of RJMCMC algorithms |
CN107230209B (en) * | 2017-05-26 | 2020-11-10 | 辽宁工程技术大学 | SAR image segmentation method combining K-S distance and RJMCMC algorithm |
CN107170006A (en) * | 2017-06-01 | 2017-09-15 | 中国科学院遥感与数字地球研究所 | The separation method and device of sea ice and Seawater Information in diameter radar image |
CN107170006B (en) * | 2017-06-01 | 2019-12-03 | 中国科学院遥感与数字地球研究所 | The separation method and device of sea ice and Seawater Information in diameter radar image |
CN108508427A (en) * | 2018-07-04 | 2018-09-07 | 鲁东大学 | A kind of sea ice method for detecting area, device and equipment based on pathfinder |
CN108508427B (en) * | 2018-07-04 | 2020-07-07 | 烟台雷奥电子科技有限公司 | Sea ice area detection method, device and equipment based on navigation radar |
CN109447993A (en) * | 2018-10-25 | 2019-03-08 | 哈尔滨工程大学 | A kind of sea ice image partition method based on mixing true and false sample strategy |
CN110374045A (en) * | 2019-07-29 | 2019-10-25 | 哈尔滨工业大学 | A kind of intelligence de-icing method |
CN115760748A (en) * | 2022-11-14 | 2023-03-07 | 江苏科技大学 | Ice body annular crack size measurement method based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106296663A (en) | A kind of SAR sea ice image partition method and system | |
CN106384344B (en) | A kind of remote sensing image surface vessel target detection and extracting method | |
CN109740460B (en) | Optical remote sensing image ship detection method based on depth residual error dense network | |
CN104573646B (en) | Chinese herbaceous peony pedestrian detection method and system based on laser radar and binocular camera | |
Zhang et al. | A new algorithm for character segmentation of license plate | |
CN104834922B (en) | Gesture identification method based on hybrid neural networks | |
CN103198332B (en) | A kind of far infrared vehicle-mounted pedestrian detection method of real-time robust | |
CN105373779B (en) | A kind of vehicle safety belt intelligent detecting method and intelligent checking system | |
CN108921066B (en) | Optical remote sensing image ship detection method based on feature fusion convolutional network | |
CN109325418A (en) | Based on pedestrian recognition method under the road traffic environment for improving YOLOv3 | |
CN104408707B (en) | Rapid digital imaging fuzzy identification and restored image quality assessment method | |
CN103530600B (en) | Licence plate recognition method under complex illumination and system | |
CN101944174B (en) | Identification method of characters of licence plate | |
CN106023220A (en) | Vehicle exterior part image segmentation method based on deep learning | |
CN104036246B (en) | Lane line positioning method based on multi-feature fusion and polymorphism mean value | |
CN107992819B (en) | Method and device for determining vehicle attribute structural features | |
CN105022990A (en) | Water surface target rapid-detection method based on unmanned vessel application | |
CN110837870A (en) | Sonar image target identification method based on active learning | |
CN105261017A (en) | Method for extracting regions of interest of pedestrian by using image segmentation method on the basis of road restriction | |
CN104732215A (en) | Remote-sensing image coastline extracting method based on information vector machine | |
CN106295653A (en) | A kind of water quality image classification method | |
CN104217215A (en) | Classification and identification method for foggy water surface image and clear water surface image | |
CN101403676A (en) | Insulator hydrophobicity rank amalgamation judging method based on D-S evidence theory | |
CN106570439B (en) | Vehicle detection method and device | |
CN106845458B (en) | Rapid traffic sign detection method based on nuclear overrun learning machine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |