CN112634240A - Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation - Google Patents
Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation Download PDFInfo
- Publication number
- CN112634240A CN112634240A CN202011561899.6A CN202011561899A CN112634240A CN 112634240 A CN112634240 A CN 112634240A CN 202011561899 A CN202011561899 A CN 202011561899A CN 112634240 A CN112634240 A CN 112634240A
- Authority
- CN
- China
- Prior art keywords
- image
- interference
- area
- interface
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/10132—Ultrasound 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
- G06T2207/30—Subject of image; Context of image processing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation. Belonging to the technical field of medical image segmentation; the invention can carry out binarization processing on the image on the basis of the initial set threshold value so as to obtain the most initial shade; no matter the size difference between the region of interest and the operation interface, the extraction can be completed as long as most of the region of interest is positioned in the middle of the whole image; for character identification interference outside the image region of interest, morphological operations can be used to reduce its impact and thereby acquire the region of interest. The method is innovative mainly in automatic judgment of the interference of the operation interface, and can meet the requirement of removing the interference of the operation interfaces with different sizes and positions. Compared with the prior art, the method can quickly and automatically identify and remove the edge interference of the ultrasonic thyroid image, extracts the region of interest and provides convenience for subsequent segmentation, feature extraction and classification.
Description
Technical Field
The invention belongs to the technical field of medical image segmentation, relates to a thyroid ultrasonic image interference interface automatic identification and removal method based on threshold segmentation, and particularly relates to a method for automatically identifying and removing an interference interface for a thyroid ultrasonic image based on threshold segmentation.
Background
Thyroid nodules are common thyroid diseases, ultrasound is an effective image examination means due to the fact that imaging is convenient and fast, and radiation and trauma are avoided, and doctors often need to use an ultrasound image segmentation technology when distinguishing diseased regions and conducting quantitative analysis. However, the screenshot after the ultrasound image scanning often includes interference background information such as irrelevant software operation interfaces, and the position and image proportion range of the interference information are not fixed, which greatly interferes with the subsequent thyroid image segmentation operation, so that the segmentation result is inaccurate, and the image identification and analysis of doctors are difficult. Therefore, before the focus image of the thyroid ultrasound is segmented, if irrelevant interference background can be removed in advance, reading and analysis of the shot focus image information can be effectively improved.
The current method for removing the irrelevant operation interface is a pure manual removal method, namely, the irrelevant operation interface is completely cut off manually, only a required thyroid ultrasound image area is left, and then the subsequent focus area segmentation is carried out. While this approach works well, it is time consuming and laborious for large batches of image processing, increasing the workload on medical personnel and the waiting time for the patient. Another method for removing the irrelevant operation interface is an image segmentation method combining with a computer to perform semi-automatic human-computer interaction, namely, a computer algorithm is utilized to manually select an interested region to achieve the effect of removing the irrelevant operation interface. Therefore, how to automatically and accurately remove the irrelevant operation interface is a problem which needs to be solved at present.
Some researchers have been working on improving the image processing performance by removing extraneous background from thyroid ultrasound images. Jianning Chi et al proposed a fine-tuning depth convolutional neural network-based ultrasound thyroid nodule image classification that only takes into account the interference of scale lines and annotations on the image while performing image preprocessing, and does not take into account irrelevant operational interfaces at the periphery of the image. Ouch et al propose a method of determining seed points using gray values, and removing background and labels by scanning a growth-forming region. The method is not ideal for processing images with uneven gray levels and similar gray levels to those of the region of interest, and particularly, the method often removes useful scale information in the images, so that the method is greatly limited in practicability and not strong in popularization. Lepengson et al filter the image background based on a threshold segmentation method by using gray level difference to enhance the image target, thereby simplifying the recognition task, reducing the amount of training data and parameters required by the convolutional neural network, and further improving the segmentation effect of the neural convolutional network on natural color images. However, further improvement is needed to meet the requirement of higher complexity ultrasound image processing. In addition, most researchers are working on thyroid ultrasound images directly based on images from which extraneous manipulation interfaces have been removed. For example, Dimitris e.maroulis et al propose a variable background active contour model to assist in delineating nodules in thyroid ultrasound images. Deepika Koundal et al propose a technique for automatically extracting the region of interest of an ultrasound image of a thyroid nodule by using an intermittent segmentation method. In summary, for a thyroid ultrasound image without an irrelevant operation interface background, nodule segmentation in the image can be better realized, and currently, an actually available thyroid ultrasound image interference interface automatic identification and removal method is not available.
Disclosure of Invention
Aiming at the problems, the invention provides a thyroid ultrasonic image interference interface automatic identification and removal method based on threshold segmentation; the method aims to automatically identify and remove irrelevant operation interfaces and character identification interference during thyroid ultrasound image segmentation, only reserve an interested area to be processed, and further improve the accuracy and efficiency of image segmentation.
The technical scheme of the invention is as follows: the thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation comprises the following specific steps:
step (1.1), selecting an input picture, and processing the input picture into a gray image;
step (1.2), carrying out binarization processing on the gray level image based on a preset initial threshold value so as to obtain an initial shade of the gray level image;
step (1.3), filling larger holes in the communicating region in the initial mask, removing the communicating region with small area,
step (1.4), marking all other connected domains in the initial shade of the gray-scale image with the small-area connected domain removed, and then judging whether the initial shade has an operation interface or not;
if so, selecting a preset central rectangular area, judging the number of connected domains, and reserving the connected domains with the largest area; thereby obtaining an initial mask capable of removing the interference interface;
if not, performing morphological processing on the gray-scale image before binarization processing, performing binarization processing on the gray-scale image, removing the character identifier and the interference interface, and performing Otus threshold segmentation to obtain an initial mask for removing the interference interface;
step (1.5), according to the integrity of the interested area of the ultrasonic image, taking an external rectangle from the obtained initial mask for removing the interference interface, and judging whether the difference between the external rectangle and the area of the mask is overlarge;
if so, reserving the initial mask for removing the interference interface, taking the initial mask as a final mask finally used for removing the interference interface, and extracting the region of interest to prevent misjudgment when the region of interest is not rectangular;
if not, indicating that the region of interest is close to the rectangular shape, and selecting the circumscribed rectangle as a final mask for removing the interference interface finally;
and finally, overlapping the obtained final mask and the gray level image to obtain the image without the interference.
Further, in step (1.1), the specific step of processing the input picture into a grayscale image is: firstly, selecting an input picture, secondly, judging whether the input picture is a gray level image, if the input picture is not the gray level image, carrying out gray level processing on the input picture so as to obtain a gray level image, and then carrying out binarization processing on the gray level image;
and if the input picture is a gray level image, directly performing binarization processing on the gray level image.
Further, the binarization processing specifically includes: and judging all pixel points with the gray value larger than or equal to the threshold value in the gray image as reserved areas, replacing the pixel points in the areas with the pixel points with the gray value of 255 for representation, otherwise judging the area as a background area, and replacing the pixel points in the area with the pixel points with the gray value of 0 for representation.
Further, in the step (1.4), all other connected domains in the binarized image from which the small-area connected domains are removed are labeled, wherein for the number of connected domains possessed by the binarized image, when the number of connected domains is greater than 1, it indicates that the binarized image has larger-area operation interface interference.
Furthermore, the thyroid ultrasound image comprises three image types including a large-area operation interface, a small-area operation interface and a non-operation interface, and different processing operations can be selected in a self-adaptive manner.
The invention has the beneficial effects that: the invention aims to provide a processing method for automatically identifying and removing a thyroid ultrasound image, which is innovative mainly in automatic judgment of operation interface interference and can meet the requirement of removing the operation interface interference of various sizes and positions; compared with the prior art, the method can quickly and automatically identify and remove the edge interference of the ultrasonic thyroid image, extract the region of interest and provide convenience for subsequent segmentation, feature extraction and classification.
Drawings
FIG. 1 is a flow chart of the architecture of the present invention.
Detailed Description
In order to more clearly illustrate the technical solution of the present invention, the following detailed description is made with reference to the accompanying drawings:
as shown in the figure; the thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation comprises the following specific steps:
step (1.1), selecting an input picture, and processing the input picture into a gray image;
step (1.2), carrying out binarization processing on the gray level image based on a preset initial threshold value so as to obtain an initial shade of the gray level image;
step (1.3), filling larger holes in the communicating region in the initial mask, removing the communicating region with small area,
step (1.4), marking all other connected domains in the initial shade of the gray-scale image with the small-area connected domain removed, and then judging whether the initial shade has an operation interface or not;
if so, selecting a preset central rectangular area, judging the number of connected domains, and reserving the connected domains with the largest area; thereby obtaining an initial mask capable of removing the interference interface;
if not, performing morphological processing on the gray-scale image before binarization processing, performing binarization processing on the gray-scale image, removing the character identifier and the interference interface, and performing Otus threshold segmentation to obtain an initial mask for removing the interference interface;
step (1.5), according to the integrity of the interested area of the ultrasonic image, taking an external rectangle from the obtained initial mask for removing the interference interface, and judging whether the difference between the external rectangle and the area of the mask is overlarge;
if so, reserving the initial mask for removing the interference interface, taking the initial mask as a final mask finally used for removing the interference interface, and extracting the region of interest to prevent misjudgment when the region of interest is not rectangular;
if not, indicating that the region of interest is close to the rectangular shape, and selecting the circumscribed rectangle as a final mask for removing the interference interface finally;
and finally, overlapping the obtained final mask and the gray level image to obtain the image without the interference.
Further, in step (1.1), the specific step of processing the input picture into a grayscale image is: firstly, selecting an input picture, secondly, judging whether the input picture is a gray level image, if the input picture is not the gray level image, carrying out gray level processing on the input picture so as to obtain a gray level image, and then carrying out binarization processing on the gray level image;
and if the input picture is a gray level image, directly performing binarization processing on the gray level image.
Further, the binarization processing specifically includes: and judging all pixel points with the gray value larger than or equal to the threshold value in the gray image as reserved areas, replacing the pixel points in the areas with the pixel points with the gray value of 255 for representation, otherwise judging the area as a background area, and replacing the pixel points in the area with the pixel points with the gray value of 0 for representation.
Further, in the step (1.4), all other connected domains in the binarized image from which the small-area connected domains are removed are labeled, wherein for the number of connected domains possessed by the binarized image, when the number of connected domains is greater than 1, it indicates that the binarized image has larger-area operation interface interference.
Furthermore, the thyroid ultrasound image comprises three image types including a large-area operation interface, a small-area operation interface and a non-operation interface, and different processing operations can be selected in a self-adaptive manner.
Specifically, the invention provides a method for automatically extracting a region of interest based on threshold segmentation, which specifically comprises the following characteristics:
the method can identify a plurality of ultrasonic thyroid images, comprises three image types including a large-area operation interface, a small-area operation interface and an operation interface which is not contained, and can adaptively select different processing operations.
The invention can carry out binarization processing on the image on the basis of the initial set threshold value so as to obtain the most initial mask. Regardless of the size difference between the interested area and the operation interface, the extraction can be completed as long as most of the interested area is positioned in the middle of the whole image.
For the character identification interference outside the image interested region, morphological operation can be used to reduce the influence of the character identification interference so as to acquire the interested region; the method comprises the following specific steps:
selecting a picture for inputting, judging whether the picture is a gray image or not, and if the original picture is not the gray image, performing gray processing on the image; and carrying out binarization on the image based on a preset initial threshold value, and adjusting the threshold value in a circulating mode until a segmentation effect occurs on the ultrasonic image with higher overall image brightness.
Filling larger holes existing in the region of interest of the ultrasonic image, and removing small-area connected regions so as to remove interference such as small character marks outside the region of interest.
And marking the number of connected domains of the binary image with the small-area connected domain removed, wherein when the number of the connected domains is more than 1, the image has larger-area operation interface interference, selecting a central rectangular area with a preset size for the binary image, judging the number of the connected domains again, and reserving the connected domain with the largest area to obtain the initial mask with the interference interface removed.
And for the binary image only having a single connected domain, if the interference interface area of the original image is smaller, returning to the binary image mask before the binarization step, performing morphological processing on the gray image, removing the character identifier and the interference interface, and performing Otus threshold segmentation to obtain the binary image mask.
In order to reserve the integrity of the interested area of the ultrasonic image as much as possible so as to extract the characteristics and segment subsequently, an external rectangle is firstly taken from the interested area of the mask, the difference between the area of the external rectangle and the area of the original area is judged, when the difference is larger, the original mask is reserved to extract the interested area, the misjudgment when the interested area is not the rectangle is prevented, and when the difference is smaller, the original image is close to the rectangle, so that the external rectangle is selected as the final mask. And overlapping the obtained shade with the gray level image to obtain the image without the interference.
Example (b):
the embodiment is a method for automatically extracting a region of interest based on threshold segmentation, and in practical application, the method comprises the following steps:
1. inputting a thyroid ultrasound image to be processed, processing a picture into a gray-scale image, wherein the initial threshold value is 15/255, binarizing the picture, removing a 4-neighborhood connected domain with the area smaller than 10000 after inverting the picture, preventing the dark color part of the interest area in the gray-scale image from being lost, preventing gaps between the picture interface and a surrounding type operation interface from being filled, inverting again and removing a small-area connected domain, and deleting character marks independent of the operation interface and the interest area;
2. judging the number of connected domains in the obtained binary image, in this example, only the surrounding operation interface region and the region of interest exist after the processing, the number of connected domains is greater than 1, and the size of the detected picture is 1080 × 1024, then selecting an image center rectangular region, taking the upper left corner of the image as the origin of coordinates, and the horizontal and vertical coordinates of the four vertices of the rectangle are x: round (1080/8) ═ 135, round (1080 × 13/16) ═ 878, y: round (1024/8) ═ 128, and round (1024 × 7/8) ═ 896;
in the example, the area of the interference of the operation interface is reduced after the frame selection, namely, the maximum connected domain can be reserved, so that the region of interest is extracted;
3. and taking a circumscribed rectangle for the obtained region of interest, and comparing the difference of the area of the region of interest before and after processing, wherein the difference of the area of the region of interest before and after processing is less than 20000, and taking the circumscribed rectangle as the region of interest. And overlapping the obtained shade with the gray scale image to obtain the ultrasonic image without interference.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of embodiments of the present invention; other variations are possible within the scope of the invention; thus, by way of example, and not limitation, alternative configurations of embodiments of the invention may be considered consistent with the teachings of the present invention; accordingly, the embodiments of the invention are not limited to the embodiments explicitly described and depicted.
Claims (5)
1. The thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation is characterized by comprising the following specific steps:
step (1.1), selecting an input picture, and processing the input picture into a gray image;
step (1.2), carrying out binarization processing on the gray level image based on a preset initial threshold value so as to obtain an initial shade of the gray level image;
step (1.3), filling larger holes in the communicating region in the initial mask, removing the communicating region with small area,
step (1.4), marking all other connected domains in the initial mask of the gray level image with the small-area connected domain removed, and then judging whether the mask has an operation interface or not;
if so, selecting a preset central rectangular area, judging the number of connected domains, and reserving the connected domains with the largest area; thereby obtaining an initial mask capable of removing the interference interface;
if not, performing morphological processing on the gray-scale image before binarization processing, performing binarization processing on the gray-scale image, removing the character identifier and the interference interface, and performing Otus threshold segmentation to obtain an initial mask for removing the interference interface;
step (1.5), according to the integrity of the interested area of the ultrasonic image, taking an external rectangle from the obtained initial mask for removing the interference interface, and judging whether the difference between the external rectangle and the area of the mask is overlarge;
if so, reserving the initial mask for removing the interference interface, taking the initial mask as a final mask finally used for removing the interference interface, and extracting the region of interest to prevent misjudgment when the region of interest is not rectangular;
if not, indicating that the region of interest is close to the rectangular shape, and selecting the circumscribed rectangle as a final mask for removing the interference interface finally;
and finally, overlapping the obtained final mask and the gray level image to obtain the image without the interference.
2. The thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation as claimed in claim 1, wherein in step (1.1), the specific step of processing the input image into a gray image is: firstly, selecting an input picture, secondly, judging whether the input picture is a gray level image, if the input picture is not the gray level image, carrying out gray level processing on the input picture so as to obtain a gray level image, and then carrying out binarization processing on the gray level image;
and if the input picture is a gray level image, directly performing binarization processing on the gray level image.
3. The method for automatically identifying and removing the thyroid ultrasound image interference interface based on threshold segmentation as claimed in claim 1, wherein in step (1.2), the binarization processing specifically means:
and judging all pixel points with the gray value larger than or equal to the threshold value in the gray image as reserved areas, replacing the pixel points in the areas with the pixel points with the gray value of 255 for representation, otherwise judging the area as a background area, and replacing the pixel points in the area with the pixel points with the gray value of 0 for representation.
4. The thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation as claimed in claim 1, wherein in step (1.4), all other connected domains in the image after the binarization processing after removing the small-area connected domain are labeled, wherein for the number of connected domains possessed by the image after the binarization processing, when the number of connected domains is greater than 1, it indicates that the image after the binarization processing has a larger area of operation interface interference.
5. The method for automatically identifying and removing the thyroid ultrasound image interference interface based on the threshold segmentation according to claims 1-4, wherein the thyroid ultrasound image comprises three image types including a large-area operation interface, a small-area operation interface and no operation interface, and different processing operations can be adaptively selected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561899.6A CN112634240B (en) | 2020-12-25 | 2020-12-25 | Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561899.6A CN112634240B (en) | 2020-12-25 | 2020-12-25 | Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112634240A true CN112634240A (en) | 2021-04-09 |
| CN112634240B CN112634240B (en) | 2022-09-23 |
Family
ID=75325396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011561899.6A Active CN112634240B (en) | 2020-12-25 | 2020-12-25 | Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112634240B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113362345A (en) * | 2021-06-30 | 2021-09-07 | 武汉中科医疗科技工业技术研究院有限公司 | Image segmentation method and device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241973A (en) * | 2018-08-21 | 2019-01-18 | 南京工程学院 | A kind of full-automatic soft dividing method of character under grain background |
| CN110060235A (en) * | 2019-03-27 | 2019-07-26 | 天津大学 | A kind of thyroid nodule ultrasonic image division method based on deep learning |
-
2020
- 2020-12-25 CN CN202011561899.6A patent/CN112634240B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241973A (en) * | 2018-08-21 | 2019-01-18 | 南京工程学院 | A kind of full-automatic soft dividing method of character under grain background |
| CN110060235A (en) * | 2019-03-27 | 2019-07-26 | 天津大学 | A kind of thyroid nodule ultrasonic image division method based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113362345A (en) * | 2021-06-30 | 2021-09-07 | 武汉中科医疗科技工业技术研究院有限公司 | Image segmentation method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112634240B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
| CN111724402B (en) | Medical image labeling method, system and device | |
| JP6733983B2 (en) | Image analysis device | |
| CN107038704B (en) | Retina image exudation area segmentation method and device and computing equipment | |
| CN110110667B (en) | Processing method and system of diatom image and related components | |
| CN110766017A (en) | Mobile terminal character recognition method and system based on deep learning | |
| CN110751619A (en) | Insulator defect detection method | |
| CN112507911B (en) | Real-time recognition method of pecan fruits in image based on machine vision | |
| WO2021147866A1 (en) | Ecg signal acquisition method and device, storage medium, and electronic device | |
| CN110807775A (en) | Traditional Chinese medicine tongue image segmentation device and method based on artificial intelligence and storage medium | |
| CN113160153A (en) | Lung nodule screening method and system based on deep learning technology | |
| CN110992384A (en) | Semi-automatic image data labeling method, electronic device and storage medium | |
| CN110060246B (en) | Image processing method, device and storage medium | |
| CN112634240B (en) | Thyroid ultrasound image interference interface automatic identification and removal method based on threshold segmentation | |
| CN110363103B (en) | Insect pest identification method and device, computer equipment and storage medium | |
| CN111105427A (en) | Lung image segmentation method and system based on connected region analysis | |
| CN110136139B (en) | Dental nerve segmentation method in facial CT image based on shape feature | |
| CN110889374A (en) | Seal image processing method and device, computer and storage medium | |
| CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
| Chen et al. | Image segmentation based on mathematical morphological operator | |
| CN111612749A (en) | Lung image-based focus detection method and device | |
| Tabatabaei et al. | A novel method for binarization of badly illuminated document images | |
| CN110264463A (en) | A kind of material counting method based on matlab image procossing | |
| CN114972209A (en) | Cervical pathology image processing method and device | |
| Khan et al. | Segmentation of single and overlapping leaves by extracting appropriate contours |
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 |