CN110766680B - Leukocyte image segmentation method based on geometric constraint - Google Patents
Leukocyte image segmentation method based on geometric constraint Download PDFInfo
- Publication number
- CN110766680B CN110766680B CN201911027608.2A CN201911027608A CN110766680B CN 110766680 B CN110766680 B CN 110766680B CN 201911027608 A CN201911027608 A CN 201911027608A CN 110766680 B CN110766680 B CN 110766680B
- Authority
- CN
- China
- Prior art keywords
- image
- white blood
- pixel
- incomplete
- cells
- 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
- 210000000265 leukocyte Anatomy 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000003709 image segmentation Methods 0.000 title claims description 6
- 210000004027 cell Anatomy 0.000 claims abstract description 27
- 210000003743 erythrocyte Anatomy 0.000 claims abstract description 12
- 238000003708 edge detection Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 abstract description 17
- 238000012706 support-vector machine Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010186 staining Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000037157 Azotemia Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 210000003651 basophil Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000003979 eosinophil Anatomy 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 210000004698 lymphocyte Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 210000001616 monocyte Anatomy 0.000 description 1
- 210000000440 neutrophil Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 208000009852 uremia Diseases 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Abstract
The invention relates to a method for segmenting an image by white blood cells based on geometric constraint, which comprises the following steps of firstly preparing a data set; then removing the background and red blood cells in the image according to the color channel; then adopting a Canny operator to carry out edge detection to obtain the edge of the white blood cell; and finally, judging whether the incomplete cells exist or not, and filling the incomplete cells by adopting geometric constraint. The invention can effectively improve the accuracy and robustness of the segmentation method.
Description
Technical Field
The invention relates to the technical field of computer image processing, in particular to a leukocyte image segmentation method based on geometric constraint.
Background
Leukocytes are important defense cells of human blood cells, and they contain 5 kinds of cells, i.e., neutrophils, basophils, eosinophils, monocytes, and lymphocytes. Leukocyte segmentation is a varied task for various medical diagnostic applications. For example, visual examination of leukocytes in blood smears collected under a bright field microscope can diagnose various diseases, such as septic bacterial inflammation, uremia, and the like.
The number of leukocyte segmentation methods has been proposed in recent years. They can be divided into two categories: supervised and unsupervised methods. The supervision method comprises a Support Vector Machine (SVM), a random forest, a convolution network and the like. In the method of the support vector machine, one first samples an image using a hierarchical sampling technique based on the EM algorithm. Then, the SVM is trained on-line by using the color features of the sampled pixels, and each pixel in the test image is classified by the SVM. In the stochastic pitch method, one extracts foreground regions from cell images by k-means. The pixels are then classified using SVM. In the convolutional network method, one first divides cell boundaries by active contours, and then precisely subdivides cells using machine learning. Specifically, they turned the manual task into a ground truth, then changed the image through a pre-constructed neural network, and recorded the difference between the original image and the ground truth. Finally, parameters of the neural network are iteratively altered to reduce their differences. In summary, although the results are superior to the conventional methods, a large number of samples are still required. Despite the superior performance of supervised learning, there are still many limitations in feature extraction. Firstly, the feature extraction itself generates a lot of noise, which affects the accuracy of the algorithm. Secondly, these functions still require manual handling and it is difficult to fully generalize all cases.
Unsupervised methods include clustering-based methods, threshold-based segmentation and watershed-based algorithms. In a cluster-based approach, the color space of the white blood cell image is first transformed, and then the color space decomposition is segmented using k-means clustering. Although their method does not have manual labeling, the accuracy of segmentation is not satisfactory. To improve accuracy, one uses mean shift instead of k-means to obtain whole cells, and finally, uses a watershed algorithm for accurate segmentation. In addition, there are also some alternatives to define two transforms to model the color and shape characteristics of the white blood cells, and finally to use a watershed algorithm for efficient segmentation. Unsupervised methods do not require large amounts of training data. However, when regions of interest (ROIs) of cells have large colors, shapes and sizes, they are prone to overfitting or being unsuitable. Therefore, a large number of adjustment parameters are required. In addition, red blood cells are often stuck and, like white blood cells, they are difficult to exclude from red blood cells and other staining impurities.
Disclosure of Invention
In view of this, the present invention provides a method for segmenting a white blood cell image based on geometric constraint, which can effectively improve the accuracy and robustness of the segmentation method.
The invention is realized by adopting the following scheme: a leukocyte image segmentation method based on geometric constraint comprises the following steps:
preparing a data set;
removing background and red blood cells in the image according to the color channel;
adopting a Canny operator to carry out edge detection to obtain the edge of the white blood cell;
and judging whether the incomplete cells exist or not, and filling the incomplete cells by adopting geometric constraint.
Further, the dataset is a dataset comprising a single white blood cell image.
Further, the removing the background and the red blood cells in the image according to the color channel specifically includes:
step S11: removing the high-brightness image of the green channel according to the color channel;
step S12: the high brightness image of the red channel is removed according to the color channel.
Further, the step S11 is specifically: when the green channel is greater than the threshold, the background is removed according to the following formula:
where I is each pixel of the image, I (I, j,1) is the red channel value of the pixel, I (I, j,2) is the green channel value of the pixel, and I (I, j,3) is the blue channel value of the pixel.
Further, step S12 is specifically: when the red channel is greater than the threshold, the background is removed according to the following formula:
where I is each pixel of the image, I (I, j,1) is the red channel value of the pixel, I (I, j,2) is the green channel value of the pixel, and I (I, j,3) is the blue channel value of the pixel.
Further, the edge detection by using the Canny operator to obtain the edge of the white blood cell specifically comprises: and (5) carrying out edge detection on the image after the background and the red blood cells are removed by adopting a canny operator, removing other miscellaneous edges by using a maximum connected threshold algorithm, and only keeping the edges of the white blood cells.
Further, the judging whether the incomplete cells exist is specifically as follows: and detecting the number of breakpoints in the image by using a breakpoint detection technology, and judging that the cell is incomplete if the number of the breakpoints is 2.
Further, the filling of the incomplete cells with geometric constraints specifically comprises the following steps:
step S1: finding two breakpoints of the incomplete leukocyte edge;
step S2: randomly sampling some data points and generating circle candidates using the break points found in step S1; estimating a candidate circle having the largest inner number from the generated circle candidates as an optimal circle; wherein the internal number of the generated candidate circle is calculated as follows:
where n is the number of data points sampled, ξ is the internal noise scale, d (x)iθ) is the data point xiAnd the distance between circle θ;
step S3: cutting the optimal circle into two arcs by using a line segment consisting of two break points, reserving a proper arc, and splicing the proper arc and the incomplete white blood cell image; wherein the suitable arcs are specifically: wherein the central line of the line segment formed by the two breakpoints is intersected with the boundary of the white blood cell to obtain an intersection point, the arc where the intersection point is located is removed, and the other arc is reserved as a proper arc;
step S4: and (4) supplementing the supplemented white blood cell image by adopting a hole filling function to obtain the finally segmented white blood cell.
Compared with the prior art, the invention has the following beneficial effects: according to the method, the robust model is fitted and introduced to cell detection through geometric constraint, so that the robustness of the segmentation method to outliers can be effectively improved, and the segmentation accuracy of the leukocyte segmentation method is further improved.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of completing an incomplete cell image according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating the effect of performing nuclear segmentation on the data set 1 according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating the effect of performing nuclear segmentation on the data set 2 according to an embodiment of the present invention.
In fig. 3 and 4, (a) is an original image group, (b) is an image group recognized by the method of the present embodiment corresponding to (a), and (c) is a standard result image group corresponding to (a).
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the present embodiment provides a method for segmenting a white blood cell image based on geometric constraint, which includes the following steps:
preparing a data set;
removing background and red blood cells in the image according to the color channel;
adopting a Canny operator to carry out edge detection to obtain the edge of the white blood cell;
and judging whether the incomplete cells exist or not, and filling the incomplete cells by adopting geometric constraint.
In this embodiment, the data set is a data set containing a single white blood cell image.
Preferably, in order to better evaluate the accuracy and robustness of the method of the present embodiment, the present embodiment evaluates the performance of the algorithm on two data. Data set 1 is 138 rapidly stained single white blood cell images of size 120 x 120 provided by Jiangxitekang scientific and technological Inc. of China. Data set 2 of 28 standard stained single white blood cell images, provided by the third people hospital in fujian province, the size of which was 250 x 250.
In this embodiment, the removing the background and the red blood cells in the image according to the color channel specifically includes:
step S11: removing the high-brightness image of the green channel according to the color channel;
step S12: the high brightness image of the red channel is removed according to the color channel.
In this embodiment, the step S11 specifically includes: when the green channel is greater than the threshold, the background is removed according to the following formula:
where I is each pixel of the image, I (I, j,1) is the red channel value of the pixel, I (I, j,2) is the green channel value of the pixel, and I (I, j,3) is the blue channel value of the pixel.
In this embodiment, step S12 specifically includes: when the red channel is greater than the threshold, the background is removed according to the following formula:
where I is each pixel of the image, I (I, j,1) is the red channel value of the pixel, I (I, j,2) is the green channel value of the pixel, and I (I, j,3) is the blue channel value of the pixel.
In this embodiment, the edge detection using the Canny operator to obtain the edge of the white blood cell specifically includes: and (5) carrying out edge detection on the image after the background and the red blood cells are removed by adopting a canny operator, removing other miscellaneous edges by using a maximum connected threshold algorithm, and only keeping the edges of the white blood cells.
In this embodiment, the determining whether there are incomplete cells specifically includes: and detecting the number of breakpoints in the image by using a breakpoint detection technology, and judging that the cell is incomplete if the number of the breakpoints is 2.
In this embodiment, as shown in fig. 2, the filling of the incomplete cells with geometric constraints specifically includes the following steps:
step S1: finding two breakpoints of the incomplete leukocyte edge;
step S2: randomly sampling some data points and generating circle candidates using the break points found in step S1; estimating a candidate circle having the largest inner number from the generated circle candidates as an optimal circle; wherein the internal number of the generated candidate circle is calculated as follows:
where n is the number of data points sampled, ξ is the internal noise scale, d (x)iθ) is the data point xiAnd the distance between circle θ;
step S3: cutting the optimal circle into two arcs by using a line segment consisting of two break points, reserving a proper arc, and splicing the proper arc and the incomplete white blood cell image; wherein the suitable arcs are specifically: wherein the central line of the line segment formed by the two breakpoints is intersected with the boundary of the white blood cell to obtain an intersection point, the arc where the intersection point is located is removed, and the other arc is reserved as a proper arc;
step S4: and (4) supplementing the supplemented white blood cell image by adopting a hole filling function to obtain the finally segmented white blood cell.
Table 1 shows the average values of the adaptive Misclassification Error (ME), the False Positive Rate (FPR), the False Negative Rate (FNR), and the Kappa Index (KI) of the cells segmented on data 1 (fast staining) and data 2 (standard staining) respectively in this example and the SVM segmentation algorithm, the watershed segmentation algorithm (WS), the combined image segmentation algorithm (CIS), and the histogram threshold segmentation (AHT). From the table, it can be seen that the method of the invention significantly improves the accuracy and robustness of segmentation and achieves better effect. Fig. 3 and 4 are diagrams illustrating the effect of the embodiment of the invention on the data set 1 and the data set 2, respectively, and it can be seen from fig. 3 and 4 that the segmented white blood cell image of the embodiment of the invention is very close to the standard result, almost consistent with the standard result, and can achieve very good accuracy.
TABLE 1
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (7)
1. A leukocyte image segmentation method based on geometric constraint is characterized by comprising the following steps:
preparing a data set;
removing background and red blood cells in the image according to the color channel;
adopting a Canny operator to carry out edge detection to obtain the edge of the white blood cell;
judging whether incomplete cells exist or not, and supplementing the incomplete cells by adopting geometric constraint;
the filling of incomplete cells with geometric constraints specifically comprises the following steps:
step S1: finding two breakpoints of the incomplete leukocyte edge;
step S2: randomly sampling some data points and generating circle candidates using the break points found in step S1; estimating a candidate circle having the largest inner number from the generated circle candidates as an optimal circle; wherein the internal number of the generated candidate circle is calculated as follows:
where n is the number of data points sampled, ξ is the internal noise scale, d (x)iθ) is the data point xiAnd the distance between circle θ;
step S3: cutting the optimal circle into two arcs by using a line segment consisting of two break points, reserving a proper arc, and splicing the proper arc and the incomplete white blood cell image; wherein the suitable arcs are specifically: wherein the central line of the line segment formed by the two breakpoints is intersected with the boundary of the white blood cell to obtain an intersection point, the arc where the intersection point is located is removed, and the other arc is reserved as a proper arc;
step S4: and (4) supplementing the supplemented white blood cell image by adopting a hole filling function to obtain the finally segmented white blood cell.
2. The method of claim 1, wherein the data set is a data set containing a single white blood cell image.
3. The method according to claim 1, wherein the removing of the background and the red blood cells in the image according to the color channel specifically comprises:
step S11: removing the high-brightness image of the green channel according to the color channel;
step S12: the high brightness image of the red channel is removed according to the color channel.
4. The method for segmenting a leukocyte image based on geometric constraint according to claim 3, wherein said step S11 is specifically as follows: when the green channel is greater than the threshold, the background is removed according to the following formula:
where I is each pixel of the image, I (I, j,1) is the red channel value of the pixel, I (I, j,2) is the green channel value of the pixel, and I (I, j,3) is the blue channel value of the pixel.
5. The method for segmenting a leukocyte image based on geometric constraint according to claim 3, wherein the step S12 is specifically as follows: when the red channel is greater than the threshold, the background is removed according to the following formula:
where I is each pixel of the image, I (I, j,1) is the red channel value of the pixel, I (I, j,2) is the green channel value of the pixel, and I (I, j,3) is the blue channel value of the pixel.
6. The method according to claim 1, wherein the edge detection is performed by using a Canny operator, and the obtaining of the edge of the white blood cell specifically comprises: and (5) carrying out edge detection on the image after the background and the red blood cells are removed by adopting a canny operator, removing other miscellaneous edges by using a maximum connected threshold algorithm, and only keeping the edges of the white blood cells.
7. The method of claim 1, wherein the determining whether the incomplete cell exists is specifically: and detecting the number of breakpoints in the image by using a breakpoint detection technology, and if the number of the breakpoints is 2, judging that the cells are incomplete.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911027608.2A CN110766680B (en) | 2019-10-28 | 2019-10-28 | Leukocyte image segmentation method based on geometric constraint |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911027608.2A CN110766680B (en) | 2019-10-28 | 2019-10-28 | Leukocyte image segmentation method based on geometric constraint |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110766680A CN110766680A (en) | 2020-02-07 |
CN110766680B true CN110766680B (en) | 2021-06-22 |
Family
ID=69333940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911027608.2A Active CN110766680B (en) | 2019-10-28 | 2019-10-28 | Leukocyte image segmentation method based on geometric constraint |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110766680B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112991306B (en) * | 2021-03-25 | 2022-04-22 | 华南理工大学 | Cleavage stage embryo cell position segmentation and counting method based on image processing |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105205489A (en) * | 2015-08-27 | 2015-12-30 | 华南理工大学 | License plate detection method based on color texture analyzer and machine learning |
CN110148126A (en) * | 2019-05-21 | 2019-08-20 | 闽江学院 | Blood leucocyte dividing method based on color component combination and contour fitting |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AT501944B1 (en) * | 2005-06-15 | 2007-06-15 | Tissuegnostics Gmbh | PROCESS FOR SEGMENTING LEUKOCYTES |
GB2478593B (en) * | 2010-03-12 | 2017-05-31 | Inst For Medical Informatics | Optimising the initialization and convergence of active contours for segmentation of cell nuclei in histological sections |
CN106327490A (en) * | 2016-08-22 | 2017-01-11 | 中国计量大学 | Nucleus segmentation method based on white blood cell detection |
-
2019
- 2019-10-28 CN CN201911027608.2A patent/CN110766680B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105205489A (en) * | 2015-08-27 | 2015-12-30 | 华南理工大学 | License plate detection method based on color texture analyzer and machine learning |
CN110148126A (en) * | 2019-05-21 | 2019-08-20 | 闽江学院 | Blood leucocyte dividing method based on color component combination and contour fitting |
Non-Patent Citations (1)
Title |
---|
一种基于H直方图变换的白细胞图像分割方法;汪婧等;《光学与光电技术》;20130430;第11卷(第2期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN110766680A (en) | 2020-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115082683B (en) | Injection molding defect detection method based on image processing | |
CN110334706B (en) | Image target identification method and device | |
CN106803247B (en) | Microangioma image identification method based on multistage screening convolutional neural network | |
Zhang et al. | Automation‐assisted cervical cancer screening in manual liquid‐based cytology with hematoxylin and eosin staining | |
Liao et al. | An accurate segmentation method for white blood cell images | |
Savkare et al. | Automatic system for classification of erythrocytes infected with malaria and identification of parasite's life stage | |
WO2022099598A1 (en) | Video dynamic target detection method based on relative statistical features of image pixels | |
Miao et al. | Simultaneous segmentation of leukocyte and erythrocyte in microscopic images using a marker-controlled watershed algorithm | |
CN115457004B (en) | Intelligent detection method of zinc paste based on computer vision | |
CN112598713A (en) | Offshore submarine fish detection and tracking statistical method based on deep learning | |
CN112634243B (en) | Image classification and recognition system based on deep learning under strong interference factors | |
Shahin et al. | A novel white blood cells segmentation algorithm based on adaptive neutrosophic similarity score | |
CN110148126B (en) | Blood leukocyte segmentation method based on color component combination and contour fitting | |
CN109685045A (en) | A kind of Moving Targets Based on Video Streams tracking and system | |
Razzak | Automatic detection and classification of malarial parasite | |
Zhou et al. | Leukocyte image segmentation based on adaptive histogram thresholding and contour detection | |
CN111986183A (en) | Chromosome scattergram image automatic segmentation and identification system and device | |
CN109117703A (en) | It is a kind of that cell category identification method is mixed based on fine granularity identification | |
Pandit et al. | Literature review on object counting using image processing techniques | |
CN114240978B (en) | Cell edge segmentation method and device based on adaptive morphology | |
Gonçalves et al. | Automatic system for counting cells with elliptical shape | |
CN113160185A (en) | Method for guiding cervical cell segmentation by using generated boundary position | |
CN110766680B (en) | Leukocyte image segmentation method based on geometric constraint | |
CN112419335B (en) | Shape loss calculation method of cell nucleus segmentation network | |
CN109460768B (en) | Text detection and removal method for histopathology microscopic image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240115 Address after: 230000 Room 203, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Hefei Jiuzhou Longteng scientific and technological achievement transformation Co.,Ltd. Address before: 200 xiyuangong Road, Shangjie Town, Minhou County, Fuzhou City, Fujian Province Patentee before: MINJIANG University |
|
TR01 | Transfer of patent right |