CN114419074B - 4K medical image processing method - Google Patents
4K medical image processing method Download PDFInfo
- Publication number
- CN114419074B CN114419074B CN202210297689.3A CN202210297689A CN114419074B CN 114419074 B CN114419074 B CN 114419074B CN 202210297689 A CN202210297689 A CN 202210297689A CN 114419074 B CN114419074 B CN 114419074B
- Authority
- CN
- China
- Prior art keywords
- medical image
- image frame
- gradient
- sub
- filter window
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 28
- 238000001914 filtration Methods 0.000 claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims abstract description 27
- 239000011159 matrix material Substances 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 29
- 230000005540 biological transmission Effects 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 7
- 230000001965 increasing effect Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 13
- 230000008901 benefit Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 229940127554 medical product Drugs 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a 4K medical image processing method, which comprises the following steps: acquiring a medical image frame of a preset type; a primary segmentation step, segmenting the medical image frame into a plurality of sub-images; performing parallel gradient calculation on the subimages to obtain a gradient matrix of each subimage; combining the gradient matrixes of all the sub-images into a total gradient matrix according to the positions of the sub-images in the medical image frame; a secondary segmentation step, which is to perform gradient feature analysis on the total gradient matrix and segment the medical image frame into a plurality of areas according to the analysis result; and carrying out filtering and noise reduction processing on each region in parallel to obtain a processed image. The 4K medical image processing method improves the calculation efficiency in a parallel calculation mode. Especially for the processing of medical image frames with ultra-high definition, the processing speed is ensured. And edge information can be prevented from being filtered out during filtering, so that more detailed characteristics of the medical image frame can be reserved.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a 4K medical image processing method.
Background
With the advent of the intelligent era, the performance of most medical products is developing towards the intelligent direction, the medical-grade images are more and more obvious in effect, excellent medical-grade images enable focuses, related organs and tissues to be presented to doctors perfectly, the difficulty of the operation can be reduced, the success rate of the operation is improved, and the medical-grade images are indispensable devices of minimally invasive operations and medical endoscopic systems.
The medical grade image adopts 4K resolution, belongs to ultra-high definition resolution, and can obtain an internal tissue image of a human body or a certain part of the human body in a non-invasive mode. It contains the following two relatively independent directions of study: medical imaging and medical image processing. The former refers to the process of image formation, including the study of problems such as imaging mechanism, imaging equipment, imaging system analysis, etc.; the latter refers to further processing of the acquired images, which aims to either restore the original image with insufficient sharpness, highlight some characteristic information in the image, or perform pattern classification on the image, etc.
The general medical image processing process comprises the following steps: corresponding parameters are preset for image acquisition and transmission, and image optimization (denoising, enhancing, sharpening and the like) processing is carried out after the acquisition. The existing medical image processing method has the following two defects: 1. the processing speed is slow, and for an ultra-high resolution image with a resolution of 4K, the existing processing method takes a long time to process a single image due to a large data volume, so that the problems of poor real-time performance and hysteresis exist in the processing and transmission of a video stream containing a plurality of image frames.
2. The traditional image denoising processing algorithm adopts the same denoising standard to process the whole image, the denoising is too light to eliminate slight noise, and the denoising is too heavy to remove a lot of details, so the effect is not ideal.
The above information disclosed in this background section is only for enhancement of understanding of the background section of the application and therefore it may contain prior art that does not constitute known technology to those of ordinary skill in the art.
Disclosure of Invention
The invention provides a 4K medical image processing method aiming at the technical problems of low processing speed and poor noise reduction effect of a 4K ultra-high definition medical image processing mode in the prior art, and can solve the problems.
In order to realize the purpose of the invention, the invention is realized by adopting the following technical scheme:
A4K medical image processing method comprises the following steps:
acquiring a medical image frame of a preset type;
a primary segmentation step, segmenting the medical image frame into a plurality of sub-images;
performing gradient calculation on the subimages in parallel to obtain a gradient matrix of each subimage;
combining the gradient matrixes of all the sub-images into a total gradient matrix according to the positions of the sub-images in the medical image frame;
a secondary segmentation step, which is to perform gradient feature analysis on the total gradient matrix and segment the medical image frame into a plurality of regions according to the analysis result;
and carrying out filtering and noise reduction processing on each region in parallel to obtain a processed image.
Further, the method for performing gradient computation on the sub-images in parallel comprises the following steps:
taking derivatives of the subimage f (x, y) in the x axis and the y axis respectively to obtain a gradient matrix G (x, y): g (x, y) = dx (i, j) + dy (i, j);
wherein dx (I, j) = I (I +1, j) -I (I, j);
dy(i,j)=I(i,j+1)-I(i,j);
i is the pixel value matrix of the sub-image.
Further, the method for performing secondary segmentation on the medical image frame comprises the following steps:
and finding out pixel points with gradient larger than a set threshold value in the total gradient matrix, and carrying out secondary segmentation on the medical image frame by taking the pixel points as segmentation boundaries to segment the medical image frame into a plurality of regions.
Further, the method for performing filtering and denoising processing on each region in parallel comprises the following steps:
setting a filter window;
and traversing and judging the pixel points of each region according to the filter window, if any pixel point in the filter window is judged as a noise point, filtering the noise point, enlarging the filter window, and continuously judging the next pixel, otherwise, keeping the current filter window and continuously judging the next pixel.
Further, the method for judging the noise point comprises the following steps:
and if the difference value between the pixel value of the pixel point and the average pixel value in the filter window is larger than a set value, judging the pixel point as a noise point.
Further, after the filter window is enlarged, the next pixel point is continuously judged according to the enlarged filter window, when the continuous N pixel points are all non-noise points, the filter window is retracted to the original size, and N is a positive integer not less than 2.
Further, the filtering processing method is any one of average filtering, peak filtering and median filtering.
Furthermore, in the step of once segmentation, the medical image frame is equally segmented into a plurality of sub-images.
Further, the image processing module executes the 4K medical image processing method;
the image processing module receives the medical image frames acquired by the image acquisition module, and when the transmission distance is greater than a set distance value, the parallel transmission is converted into a serial transmission mode for transmission.
Further, before the step of segmenting, the method further comprises the step of preprocessing the medical image frame.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the 4K medical image processing method, the medical image frame is divided twice, the first division is used for calculating the gradient of the medical image frame, and the calculation efficiency is improved in a parallel calculation mode. Especially for the processing of medical image frames with ultra-high definition, the processing speed is ensured.
The gradient feature analysis is carried out through the total gradient matrix obtained in the previous step, and the medical image frame is subjected to secondary segmentation according to the gradient feature, so that on one hand, the whole medical image frame belongs to small block operation during filtering, details and speed can be guaranteed, and the whole medical image frame can be controlled in one frame, so that an ideal image effect is achieved. On the other hand, the gradient features reflect the edge information of the image, and the edge information can be prevented from being filtered out during filtering by dividing the gradient features into a plurality of areas, so that the detail features of the medical image frame can be reserved.
Other features and advantages of the present invention will become more apparent from the following detailed description of the invention when taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a transmission method of an embodiment of a 4K medical image processing method according to the present invention;
FIG. 2 is a flowchart of an embodiment of a 4K medical image processing method according to the present invention;
FIG. 3 is a diagram illustrating the effect of an original image in an embodiment of the 4K medical image processing method of the present invention;
FIG. 4 is a schematic diagram illustrating secondary segmentation in an embodiment of a 4K medical image processing method according to the present invention;
FIG. 5 is a diagram illustrating the effect of the 4K medical image processing method according to an embodiment of the present invention after processing;
fig. 6 is a graph showing the local contrast effect before and after the 4K medical image processing method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Example one
The present embodiment provides a method for processing 4K medical images, as shown in fig. 2, including:
acquiring a preset type of medical image frame, wherein the step of acquiring an original image can be seen in fig. 3;
a primary segmentation step, segmenting the medical image frame into a plurality of sub-images;
performing gradient calculation on the subimages in parallel to obtain a gradient matrix of each subimage;
combining the gradient matrixes of all the sub-images into a total gradient matrix according to the positions of the sub-images in the original medical image frame;
a secondary segmentation step, which is to perform gradient feature analysis on the total gradient matrix and segment the medical image frame into a plurality of regions according to the analysis result, wherein the schematic diagram of the step can be seen in fig. 4 and is divided into A, B, C, D and other regions according to the gradient features;
filtering and denoising are performed on each region in parallel to obtain a processed image, and a processed effect graph is shown in fig. 5.
Medical staff usually needs to display the medical image generated by the medical image generating device and check or operate the medical image according to the medical image.
In addition, the medical images need to continuously collect image frames and transmit the image frames to the display device for displaying, so that the real-time performance and high definition of the medical image transmission are very important. The processing time of the image of each frame can be controlled to be processed in one frame, and then the next frame can be processed in time when being transmitted to the display equipment, so that the continuity of image display and no time delay are guaranteed.
In the 4K medical image processing method of this embodiment, the image is divided twice, the first division is used to calculate the gradient of the medical image frame, and all the sub-images after division are calculated in parallel, so that the calculation efficiency is improved. The method is particularly suitable for processing ultra-high definition medical image frames and ensures the processing speed.
The gradient characteristic analysis is carried out through the total gradient matrix obtained in the previous step, the medical image frame is subjected to secondary segmentation according to the gradient characteristic, and a plurality of regions subjected to secondary segmentation are processed in parallel during filtering and denoising, so that on one hand, the operation belongs to small block operation relative to the whole medical image frame during filtering, details and speed can be guaranteed, and the operation can be controlled in one frame, and therefore an ideal image effect is achieved. On the other hand, the gradient features reflect the edge information of the image, the edge information can be prevented from being filtered by dividing the gradient features into a plurality of areas, the detail features of the medical image frame can be reserved, the detail comparison graph before and after processing can be seen in fig. 6, as can be seen from fig. 6, a large number of noise points existing in the image before processing can be effectively eliminated, the detail texture information can be reserved, the image collected in the actual processing is a color graph, and the comparison effect of the color graph is more obvious.
In some embodiments, the image processing module performs the 4K medical image processing method described above.
In some embodiments, the image processing module may be implemented using, but not limited to, an FPGA (programmable array logic). In the primary segmentation step, each sub-image is distributed to a plurality of threads of the image processing module for parallel gradient calculation. Each thread is responsible for processing the distributed sub-images, the threads do not interfere with each other, and after calculation is completed, calculation results are stored in the shared memory.
In some embodiments, the method for performing gradient computation on the sub-images in parallel is as follows:
taking derivatives of the subimages f (x, y) in the x axis and the y axis respectively to obtain a gradient matrix G (x, y): g (x, y) = dx (i, j) + dy (i, j);
wherein dx (I, j) = I (I +1, j) -I (I, j);
dy(i,j)=I(i,j+1)-I(i,j);
i is a matrix of pixel values of the sub-images, and I (I, j) represents a pixel value of the image f (x, y) when the x-axis position is I and the y-axis position is j.
In some embodiments, in the one-time segmentation step, the medical image frame is equally segmented into a number of sub-images.
The average segmentation mode is simplest and fastest, and the length and the width of the specifically segmented sub-images can be set according to the length and the width of the medical image frame. If the medical image frame can be divided into 3 × 3 sub-images with the aspect ratio consistent with that of the original medical image frame, or can be divided into 3 × 4 sub-images with the aspect ratio inconsistent with that of the original medical image frame, the method can be specifically set according to actual requirements, and the method belongs to the protection scope of the patent of the invention.
After the primary segmentation is finished, parallel threads with the number consistent with that of the sub-images are started, and gradient calculation is carried out on each sub-image.
The gradient matrixes of all the sub-images are combined together according to the positions of the sub-images in the medical image frame to analyze the gradient characteristics of the sub-images, and the combined sub-images are combined together to analyze the gradient characteristics, so that the detail contour condition and the texture information of the medical image frame can be integrally reflected.
In some embodiments, the method for performing the secondary segmentation on the medical image frame is:
and finding out pixel points with gradient larger than a set threshold value in the total gradient matrix, and performing secondary segmentation on the medical image frame by taking the pixel points as segmentation boundaries to segment the medical image frame into a plurality of regions.
It is understood that the several regions divided by the secondary division may have different sizes and shapes. Image edges are reactions of discontinuities in local characteristics of an image (abrupt changes in gray scale, abrupt changes in color, etc.) that mark the end of one region and the beginning of another region. By performing secondary segmentation on the medical image frame according to the gradient characteristics, the segmented regions can reflect the edges between different human tissues or the edges between normal tissues and focuses, and the like. By respectively carrying out filtering processing on each region, the problem that edge information is filtered out if the whole medical image frame is filtered can be prevented, more texture detail information can be kept, and the medical personnel can conveniently and accurately observe and operate.
In some embodiments, the method for performing filtering and denoising processing on each region in parallel is:
setting a filter window;
and traversing and judging the pixel points of each region according to the filter window, if any pixel point in the filter window is judged as a noise point, increasing the filter window, processing the noise point, and then continuously judging the next pixel, otherwise, keeping the current filter window to continuously judge the next pixel.
The filter window is larger than an image with an image processing effect, the scheme firstly performs traversal judgment on pixel points of each region by setting a relatively smaller filter window, and fully utilizes the advantages of small calculation amount and high speed of the small window. If current pixel point judges when being the noise point, then increase the filter window, filter this noise point, the filter window has increased, the number of pixels that falls into the filter window increases, it is good to have a filter effect, can not lose the advantage of image detail, and this scheme is through looking for the noise point and the size of changing the filter window in the filtering process, collects both advantages in an organic whole, and it is fast again to have guaranteed to filter, and the effect is good again.
In some embodiments, the noise point is determined by:
and if the difference value between the pixel value of the pixel point and the average pixel value in the filter window is larger than a set value, judging the pixel point as a noise point.
In some embodiments, in order to prevent the filter window from being frequently switched to reduce the processing speed, after the filter window is increased, the next pixel point is continuously determined according to the increased filter window, and when N consecutive pixel points are non-noise points, the filter window is retracted to the original size, where N is a positive integer not less than 2, so as to ensure that the processing method is rapidly and stably executed.
In some embodiments, the method of filtering processing is any one of average filtering, peak filtering, and median filtering.
In some embodiments, the image processing module performs a 4K medical image processing method;
as shown in fig. 1, the image processing module receives the medical image frames acquired by the image acquisition module, and when the transmission distance is not greater than the set distance, a parallel transmission mode can be adopted, so that the image processing module is fast and efficient.
And when the transmission distance is greater than the set distance value, converting the parallel transmission into a serial transmission mode for transmission. The accuracy of transmission is guaranteed.
Before the step of segmenting, the method further comprises the step of preprocessing the medical image frame.
Firstly, image acquisition is carried out through an image acquisition module and an LED cold light source, parallel-to-serial conversion can be carried out by a transmission control module for remote transmission after image acquisition, and the image is transmitted into an image processing module for image related processing (noise reduction, enhancement, color mixing, display coding and the like) after the image is received and then is output to a medical display for display and output.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (9)
1. A4K medical image processing method is characterized by comprising the following steps:
acquiring a medical image frame of a preset type;
a primary segmentation step, segmenting the medical image frame into a plurality of sub-images;
performing gradient calculation on the subimages in parallel to obtain a gradient matrix of each subimage;
combining the gradient matrixes of all the sub-images into a total gradient matrix according to the positions of the sub-images in the medical image frame;
a secondary segmentation step, performing gradient characteristic analysis on the total gradient matrix, and segmenting the medical image frame into a plurality of regions according to an analysis result;
carrying out filtering and noise reduction processing on each region in parallel to obtain a processed image;
the method for secondarily segmenting the medical image frame comprises the following steps:
and finding out pixel points with gradient larger than a set threshold value in the total gradient matrix, and carrying out secondary segmentation on the medical image frame by taking the pixel points as segmentation boundaries to segment the medical image frame into a plurality of regions.
2. The method for processing 4K medical image according to claim 1,
the method for performing gradient calculation on the subimages in parallel comprises the following steps:
taking derivatives of the subimages f (x, y) in the x axis and the y axis respectively to obtain a gradient matrix G (x, y): g (x, y) = dx (i, j) + dy (i, j);
wherein dx (I, j) = I (I +1, j) -I (I, j);
dy(i,j)=I(i,j+1)-I(i,j);
i is the pixel value matrix of the sub-image.
3. The 4K medical image processing method according to claim 1, wherein the filtering and denoising process is performed in parallel for each region by:
setting a filter window;
and traversing and judging the pixel points of each region according to the filter window, if the pixel points in the filter window are judged to be noise points, increasing the filter window, filtering the noise points, and then continuously judging the next pixel, otherwise, keeping the current filter window to continuously judge the next pixel.
4. The 4K medical image processing method according to claim 3, wherein the noise determination method comprises:
and if the difference value between the pixel value of the pixel point and the average pixel value in the filter window is larger than a set value, judging the pixel point as a noise point.
5. The method of claim 3, wherein after the filter window is enlarged, the next pixel is determined according to the enlarged filter window, and when N consecutive pixels are all non-noise, the filter window is reduced to the original size, where N is a positive integer not less than 2.
6. The 4K medical image processing method according to claim 3, wherein the filtering process is any one of average filtering, peak filtering and median filtering.
7. The method of any of claims 1-6, wherein the medical image frame is equally divided into a plurality of sub-images in a single segmentation step.
8. The 4K medical image processing method according to any one of claims 1-6,
the image processing module executes the 4K medical image processing method;
the image processing module receives the medical image frames acquired by the image acquisition module, and when the transmission distance is greater than a set distance value, the parallel transmission is converted into a serial transmission mode for transmission.
9. The method of claim 8, further comprising the step of preprocessing the medical image frames prior to the step of segmenting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210297689.3A CN114419074B (en) | 2022-03-25 | 2022-03-25 | 4K medical image processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210297689.3A CN114419074B (en) | 2022-03-25 | 2022-03-25 | 4K medical image processing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114419074A CN114419074A (en) | 2022-04-29 |
CN114419074B true CN114419074B (en) | 2022-07-12 |
Family
ID=81264533
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210297689.3A Active CN114419074B (en) | 2022-03-25 | 2022-03-25 | 4K medical image processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114419074B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117726525B (en) * | 2023-12-28 | 2024-06-11 | 四川新视创伟超高清科技有限公司 | Distributed panoramic image processing method and processing system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335683A (en) * | 2014-05-26 | 2016-02-17 | 富士通株式会社 | Object detection method and object detection apparatus |
CN109064475A (en) * | 2018-09-11 | 2018-12-21 | 深圳辉煌耀强科技有限公司 | For the image partition method and device of cervical exfoliated cell image |
CN109767406A (en) * | 2019-01-28 | 2019-05-17 | 中南林业科技大学 | A kind of adaptive median filter denoising method applied to image procossing |
CN112070788A (en) * | 2020-09-03 | 2020-12-11 | 武汉工程大学 | Image processing method for rapidly counting deformation twin crystal based on block gradient segmentation |
CN114140462A (en) * | 2021-12-10 | 2022-03-04 | 江苏牛犇轴承有限公司 | Bearing wear degree evaluation method based on image processing |
CN114170209A (en) * | 2021-12-14 | 2022-03-11 | 北京柏惠维康科技有限公司 | Method and device for determining gradient features in image and spine surgery robot |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6326847B2 (en) * | 2014-02-14 | 2018-05-23 | 富士通株式会社 | Image processing apparatus, image processing method, and image processing program |
CN104035751B (en) * | 2014-06-20 | 2016-10-12 | 深圳市腾讯计算机***有限公司 | Data parallel processing method based on multi-graphics processor and device |
WO2018036893A1 (en) * | 2016-08-23 | 2018-03-01 | Koninklijke Philips N.V. | Image processing apparatus and method for segmenting a region of interest |
-
2022
- 2022-03-25 CN CN202210297689.3A patent/CN114419074B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335683A (en) * | 2014-05-26 | 2016-02-17 | 富士通株式会社 | Object detection method and object detection apparatus |
CN109064475A (en) * | 2018-09-11 | 2018-12-21 | 深圳辉煌耀强科技有限公司 | For the image partition method and device of cervical exfoliated cell image |
CN109767406A (en) * | 2019-01-28 | 2019-05-17 | 中南林业科技大学 | A kind of adaptive median filter denoising method applied to image procossing |
CN112070788A (en) * | 2020-09-03 | 2020-12-11 | 武汉工程大学 | Image processing method for rapidly counting deformation twin crystal based on block gradient segmentation |
CN114140462A (en) * | 2021-12-10 | 2022-03-04 | 江苏牛犇轴承有限公司 | Bearing wear degree evaluation method based on image processing |
CN114170209A (en) * | 2021-12-14 | 2022-03-11 | 北京柏惠维康科技有限公司 | Method and device for determining gradient features in image and spine surgery robot |
Also Published As
Publication number | Publication date |
---|---|
CN114419074A (en) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7218763B2 (en) | Method for automated window-level settings for magnetic resonance images | |
JP4709604B2 (en) | Image display device, image display method, storage medium, and program | |
CN111710012B (en) | OCTA imaging method and device based on two-dimensional composite registration | |
CN110796612B (en) | Image enhancement method and system | |
CN114419074B (en) | 4K medical image processing method | |
CN103198501A (en) | Tooth panoramic picture automatic reconstruction method | |
CN116385436A (en) | Cholelithiasis auxiliary detection system based on CT image | |
CN113487553A (en) | Intestinal tract endoscope withdrawal speed smoothing method | |
US20230401675A1 (en) | Method for enhancing object contour of image in real-time video | |
CN116152500A (en) | Full-automatic tooth CBCT image segmentation method based on deep learning | |
JP4035216B2 (en) | Image processing method and image processing apparatus | |
CN106691505B (en) | Method and device for processing uniformity and contrast of ultrasonic image | |
US20080165247A1 (en) | Image processing apparatus and method | |
CN116993764B (en) | Stomach CT intelligent segmentation extraction method | |
CN110648333B (en) | Real-time segmentation system of mammary gland ultrasonic video image based on middle-intelligence theory | |
CN110097610B (en) | Speech synthesis system and method based on ultrasound and magnetic resonance imaging | |
JP2004030596A (en) | Image gradation conversion method, image gradation conversion apparatus, system, program, and storage medium | |
CN109350091A (en) | High frequency angiographic instrument drive system | |
CN116071337A (en) | Endoscopic image quality evaluation method based on super-pixel segmentation | |
CN111798387B (en) | Image processing method and system for confocal endoscope | |
CN114240893A (en) | Method for measuring and calculating spinal Cobb angle in external image | |
CN111652805A (en) | Image preprocessing method for fundus image splicing | |
Karthikeyan et al. | Wavelet-based Image Enhancement Techniques for Improving Visual Quality of Ultrasonic Images | |
CN116883249B (en) | Super-resolution endoscope imaging device and method | |
CN117911716B (en) | Arthritis CT image feature extraction method based on machine vision |
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 |