CN110060252B - Method and device for processing target prompt in picture and endoscope system - Google Patents
Method and device for processing target prompt in picture and endoscope system Download PDFInfo
- Publication number
- CN110060252B CN110060252B CN201910350260.4A CN201910350260A CN110060252B CN 110060252 B CN110060252 B CN 110060252B CN 201910350260 A CN201910350260 A CN 201910350260A CN 110060252 B CN110060252 B CN 110060252B
- Authority
- CN
- China
- Prior art keywords
- target
- picture
- feature
- processed
- processing
- 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
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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
Landscapes
- Engineering & 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for processing in-picture target prompt and an endoscope system. Acquiring a picture, judging whether a target exists in the picture, and extracting target characteristics and position attributes of the picture; associating the target feature with the position attribute, and judging whether an associated feature which is the same as the associated feature exists in an associated feature library or not; and if the associated features identical to the associated features exist in the associated feature library, the target is not prompted. According to the invention, the target characteristics are associated with the position attributes, when the pictures repeatedly shot at the position are processed, the characteristics cannot be repeatedly prompted as long as the associated characteristics of the target in the pictures exist in the associated characteristic library, so that repeated work of detection personnel or subsequent image processing equipment is avoided, and the picture processing efficiency is improved. Meanwhile, the associated feature library has a memorandum effect on the inspectors and subsequent image processing equipment, and key targets are prevented from being forgotten after all pictures are checked.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method and a device for prompting and processing an in-picture target and an endoscope system.
Background
In the field of endoscopy, such as detection of the inner wall of a human organ or pipeline flaw detection through an endoscope, target identification and detection are generally required in a large number of images, and since continuous shooting cannot be performed completely according to the spatial orientation sequence during endoscope shooting, there are cases where shooting is repeated at the same position. At present, some manufacturers successively release an AI auxiliary judgment instrument, which can automatically identify a target from a picture taken by an endoscope and mark the target, or prompt a detector to pay attention to the target, and because the same position is repeatedly taken, the same target can be repeatedly marked, prompted and even repeatedly processed, so that the workload is increased and the detection efficiency of the endoscope is reduced.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and particularly provides an in-picture target prompt processing method, an in-picture target prompt processing device and an endoscope system.
In order to achieve the above object, according to a first aspect of the present invention, there is provided an in-picture object hint processing method, including:
step S1, acquiring the picture, judging whether the picture has the target,
if at least one target exists in the picture, extracting target characteristics and position attributes of the picture, wherein the position attributes represent the positions of the images in the picture, and entering step S2;
if no target exists in the picture, go to step S4;
step S2, the target characteristic is associated with the position attribute to form an associated characteristic, whether the associated characteristic same as the associated characteristic exists in the associated characteristic library or not is judged,
if the associated feature library does not have the associated feature same as the associated feature, judging whether the target is further operated and processed, if not, prompting the target, and entering the step S3; if the operation is processed, the prompt processing is not carried out on the target, the associated features are stored in an associated feature library, and the step S3 is carried out;
if the associated feature identical to the associated feature exists in the associated feature library, the target is not prompted, and the process proceeds to step S3;
step S3, judging whether all the targets are checked for associated features, if all the targets in the picture are checked for associated features, entering step S4, otherwise returning to step S2 to check for associated features of the next target in the picture;
step S4, judging whether the check of all pictures is finished, if not, returning to the step S1 to process the subsequent pictures; and if the operation is finished, exiting.
The beneficial effects of the above technical scheme are: according to the invention, the target characteristics are associated with the position attributes, the associated characteristics corresponding to the target after further operation processing are stored in the associated characteristic library, when the picture repeatedly shot at the position is processed, the characteristics cannot be repeatedly prompted as long as the associated characteristics of the target in the picture are stored in the associated characteristic library, so that repeated work of detection personnel or subsequent image processing equipment is avoided, and the picture processing efficiency is improved. Meanwhile, the associated feature library has a memorandum effect on the inspectors and subsequent image processing equipment, and key targets are prevented from being forgotten after all pictures are checked.
In a preferred embodiment of the present invention, the step S1 includes:
setting a plurality of standard pictures of different types, setting a first threshold value, calculating the similarity between the pictures and the different standard pictures, and obtaining a plurality of similarity values;
if the maximum similarity value is larger than the first threshold value, the position attribute of the standard picture corresponding to the maximum similarity value is used as the position attribute of the picture, the type name of the standard picture is used as the target feature, and if the maximum similarity value is smaller than the first threshold value, the picture is considered to have no target.
The beneficial effects of the above technical scheme are: a method for quickly and simultaneously obtaining whether a target exists in a picture, a picture position attribute and a target feature is disclosed.
In a preferred embodiment of the present invention, in the step S2, the further operation process is:
outputting and prompting a type name corresponding to the target feature and a first probability of the target feature;
the first probability acquiring step includes:
step S21, calculating the number of pixels equal to or close to the pixel value of the pixel corresponding to the position in the picture in the standard image with the highest similarity to the picture, and recording the number as the first pixel number;
step S22, obtaining the sum of pixel points of the standard image with the highest similarity with the picture, and recording the sum as the number of second pixel points;
in step S23, the first probability is a ratio of the number of the first pixel points to the number of the second pixel points.
The beneficial effects of the above technical scheme are: a technical scheme of further operation processing is disclosed, and the technical scheme enables a user to intuitively obtain the target feature and the first probability and facilitates subsequent decision processing.
In a preferred embodiment of the present invention, in the step S1, the target feature includes part or all of an outline, a color histogram, a size, or a pixel mean of the target area.
The beneficial effects of the above technical scheme are: several forms of target features are disclosed that can be extracted quickly.
In a preferred embodiment of the present invention, in step S2, the time interval for determining whether the target is further processed is:
a preset time period;
or before the detection personnel switch pictures;
or the detection person switches in front of the gazing area on the picture.
The beneficial effects of the above technical scheme are: the judged time interval is set, so that endless circulation is avoided, and the time interval is set to reasonably accord with habits of people.
In a preferred embodiment of the present invention, in the step S2, the method for determining whether the target is further processed is:
and judging whether the area containing the target in the picture is saved by screenshot, if so, considering that the target is further operated and processed, and otherwise, considering that the target is not further operated and processed.
The beneficial effects of the above technical scheme are: the efficiency is improved by a rapid and direct judgment mode.
In a preferred embodiment of the present invention, in the step S2, the method for determining whether the target is further processed is:
judging whether the optimized imaging step is executed or not, if so, considering that the target is further operated and processed, otherwise, considering that the target is not further operated and processed;
the step of optimizing imaging comprises:
aiming at the target feature, finding the imaging optimization parameter corresponding to the target feature from the imaging optimization adjustment table, and outputting the imaging optimization parameter to the image sensor for adjusting an optimization execution unit of the image sensor to optimize imaging;
the imaging optimization adjustment table comprises a plurality of different target characteristics and imaging optimization parameters corresponding to each target characteristic.
The beneficial effects of the above technical scheme are: and after the imaging is optimized, the specific situation of the target can be observed and judged more conveniently.
In a preferred embodiment of the present invention, in the step S2, the method for determining whether the target is further processed is:
setting a first time threshold, acquiring a watching area of eyes of a detection person on a display, and when the watching area falls in an area where a target is located and the duration reaches the first time threshold, considering that the target is further operated and processed, otherwise, considering that the target is not further operated and processed.
The beneficial effects of the above technical scheme are: by monitoring the watching area of the inspector and taking continuous observation of whether the target is detected by the inspector as a specific technical scheme for further operation and processing, the method is more intuitive and vivid.
In order to achieve the above object, according to a second aspect of the present invention, the present invention provides an in-picture target indication processing apparatus, including a processor, a picture providing unit, and a display, where the processor obtains a picture from the picture providing unit, processes the picture according to the in-picture target indication processing method of the present invention, and displays the processed picture on the display.
The beneficial effects of the above technical scheme are: the method for processing the target prompt in the picture has the beneficial effect.
In order to achieve the above object, according to a third aspect of the present invention, there is provided an endoscope system comprising the in-picture object cue processing device of the present invention, the picture providing unit being an image sensor;
or the system also comprises a camera for shooting the face image of the detection person, the video input end of the processor is connected with the output end of the camera, and the image output end of the processor is connected with the input end of the display.
The beneficial effects of the above technical scheme are: the device for processing the target prompt in the picture has the beneficial effect.
Drawings
FIG. 1 is a flowchart illustrating a method for processing an in-picture target hint in accordance with an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram illustrating a first application scenario of the method for processing an in-picture target hint of the present invention;
FIG. 3 is a schematic diagram of a target prompt in a process of processing a picture with the same location attribute in a second application scenario of the method for processing a target prompt in a picture according to the present invention;
fig. 4 is a schematic diagram of a hint after a target in a picture has been further processed in a second application scenario of the method for processing a hint of a target in a picture according to the present invention.
Reference numerals:
1a first target; 2 second target.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
The invention provides a method for processing target prompts in pictures, a flow chart of which is shown in figure 1, and in a preferred embodiment, the method comprises the following steps:
step S1, acquiring the picture, judging whether the picture has the target,
if at least one target exists in the picture, extracting the target characteristics and the position attribute of the picture, wherein the position attribute represents the position of the image in the picture, and entering the step S2;
if no target exists in the picture, go to step S4;
step S2, the target characteristic is associated with the position attribute to form an associated characteristic, whether the associated characteristic same as the associated characteristic exists in the associated characteristic library or not is judged,
if the associated feature library does not have the associated feature same as the associated feature, determining whether the target is further operated, if not, performing a prompt process on the target, and entering step S3; if the operation is processed, the prompt processing is not performed on the target, the associated feature is stored in the associated feature library, and the process goes to step S3;
if the associated feature identical to the associated feature exists in the associated feature library, the target is not prompted, and the process proceeds to step S3;
step S3, judging whether all the targets are checked for associated features, if all the targets in the picture are checked for associated features, entering step S4, otherwise returning to step S2 to check for associated features of the next target in the picture;
step S4, judging whether the check of all pictures is finished, if not, returning to the step S1 to process the subsequent pictures; and if the operation is finished, exiting.
In the present embodiment, the presentation in the presentation process of the target is preferably, but not limited to, a sound presentation, a presentation frame provided on the periphery of the target, and an interface shake.
In the present embodiment, the determination of whether the target exists in the picture may be performed by observing the target with human eyes of the inspector, the target area may be drawn manually, and the size of the target may be measured manually.
In the embodiment, in the whole picture inspection process, the type of the target to be detected can be preset, for example, when an industrial endoscope is used for pipeline flaw detection, the target to be detected can be preset to be corroded, cracked, protruded and the like, and for example, when a medical endoscope is used for detecting the inner wall of a stomach body, the target to be detected can be preset to be bleeding, tumor, ulcer and the like. Therefore, we can set the target feature as the target category name.
Further, whether a target exists in the picture is judged, and the specific process may be as follows:
the method comprises the steps of setting a plurality of standard pictures of different target types, setting a second threshold and a third threshold, wherein the third threshold is larger than the second threshold, calculating the similarity between the obtained pictures and the different standard pictures, obtaining a plurality of similarity values, if the maximum similarity value is smaller than the second threshold, determining that the pictures do not contain targets, if at least one similarity value is larger than the third threshold, determining that the obtained pictures contain the targets, the number of the targets is the same as the number of the similarity values larger than the third threshold, and the target characteristics of each target are the target type names of the corresponding standard pictures.
In this embodiment, preferably, the second threshold is 10% to 20% of the similarity value between two identical pictures, and the third threshold is 60% to 100% of the similarity value between two identical pictures. The similarity calculation method of the two images may use an existing algorithm, such as the SIFT algorithm, or may use the similarity calculation method disclosed in chinese patent publication No. CN107689041A or CN 103870828A.
In the present embodiment, the position attribute of the picture is the position of the imaging object corresponding to the picture image; when the industrial endoscope performs pipeline flaw detection, if the pipeline is formed by connecting a plurality of pipeline units in series, the position attribute of the picture is a serial number mark respectively positioned on the inner wall of each pipeline unit, and the number is identified as the prior art, for example, refer to the technical schemes disclosed in the patents with publication numbers CN103413152B and CN 105975958B. When the medical endoscope detects the inner wall of the stomach body, the position attributes of the picture can be different parts of the stomach body, such as the fundus, the cardia, the stomach body, the antrum and the pylorus, and in this application scenario, the identification of the position attributes of the picture can refer to the technical scheme in the chinese patent with the publication number CN109035339A, and is not described herein again.
In a preferred embodiment, step S1 includes:
setting a plurality of standard pictures of different types, setting a first threshold value, calculating the similarity between the obtained picture and the different standard pictures, and obtaining a plurality of similarity values;
if the maximum similarity value is greater than the first threshold value, the position attribute of the standard picture corresponding to the maximum similarity value is used as the position attribute of the obtained picture, the type name of the standard picture is used as the target feature, and if the maximum similarity value is smaller than the first threshold value, the obtained picture is considered to have no target.
In this embodiment, the plurality of different types of standard pictures include standard pictures with different position attributes, and the standard picture with the same position attribute includes a plurality of standard pictures with different targets, so that the method can simultaneously obtain the position attribute of the picture, whether the target exists in the picture, and the target feature. The similarity calculation method for two pictures can adopt the prior art, such as SIFT algorithm, or use the similarity calculation method disclosed in Chinese patent with publication number CN107689041A or CN 103870828A. Preferably, the first threshold is 10% -20% of the similarity value of two identical pictures.
In a preferred embodiment, in step S2, the further operation processing steps are specifically:
outputting and prompting a type name corresponding to the target feature and a first probability of the target feature;
the first probability acquiring step includes:
step S21, calculating the number of pixels equal to or close to the pixel value of the pixel corresponding to the position in the picture in the standard image with the highest similarity to the picture, and recording the number as the first pixel number;
step S22, obtaining the sum of pixel points of the standard image with the highest similarity with the picture, and recording the sum as the number of second pixel points;
in step S23, the first probability is a ratio of the number of the first pixel points to the number of the second pixel points.
In a preferred embodiment, in step S1, the target feature includes part or all of the contour, color histogram, size, or pixel mean of the target region.
In the embodiment, the contour of the target region can be obtained by using the existing image segmentation method, such as an edge segmentation method based on Canny operator, a segmentation method based on a threshold value after gray processing, a segmentation method based on an active contour, and the like; after the contour of the target area is obtained, the color histogram of the color image in the contour is obtained, and the color histogram is the target feature; the size can be determined by the number of pixels contained in the target region, or the number of horizontally continuous longest pixels and/or the number of vertically continuous longest pixels in the target region.
In a preferred embodiment, in step S2, the time interval for determining whether the target is further processed is:
a preset time period;
or before the detection personnel switch pictures;
or the detection person switches in front of the gazing area on the picture.
In this embodiment, it is preferable that the preset time period is 0.5 to 2 minutes to meet the habit of people. Before the detection personnel switches the pictures, if the detection personnel starts the detection of the next picture. And (4) before the detection personnel switches the watching area on the picture, if the detection personnel drags the picture and the previous target is no longer in the display area of the display, the detection personnel is considered to switch the watching area. The gazing area can also be obtained according to the technical scheme of obtaining the gazing area of human eyes provided in the prior art with the publication number of CN107103293B in the prior art, whether the gazing area at the current moment is consistent with that at the previous moment or not is compared, and if the gazing area is not consistent, the detection personnel are considered to switch the gazing area.
In a preferred embodiment of the present invention, in step S2, the method for determining whether the target is further processed is:
and judging whether the area containing the target in the picture is saved by screenshot, if so, considering that the target is further operated and processed, and otherwise, considering that the target is not further operated and processed.
In a preferred embodiment of the present invention, in step S2, the method for determining whether the target is further processed is:
judging whether the optimized imaging step is executed or not, if so, considering that the target is further operated and processed, otherwise, considering that the target is not further operated and processed;
the step of optimizing the imaging comprises:
aiming at the target feature, finding the imaging optimization parameter corresponding to the target feature from the imaging optimization adjustment table, and outputting the imaging optimization parameter to the image sensor for adjusting an optimization execution unit of the image sensor to optimize imaging;
the imaging optimization adjustment table includes a plurality of different target features and imaging optimization parameters corresponding to each target feature.
In the present embodiment, the imaging optimization adjustment table is preferably, but not limited to, in the form of:
| |
First focal length, first intensity of light source, first color of light source, … … |
| |
Second focal length, second intensity of light source, second color of light source, … … |
| Target feature 3 | Third focal length, third intensity of light source, third color of light source, … … |
| Target feature 4 | Fourth focal length, fourth intensity of light source, fourth color of light source, … … |
| …… | …… |
Preferably, the imaging optimization parameters include a set of parameters such as focal length, light source intensity or light source color. Preferably, a set of initial imaging parameters is set, the initial imaging parameters are used when the image sensor starts to work, and meanwhile, when the target features do not exist in the imaging optimization adjustment table, the initial imaging parameters can be used for imaging.
In the present embodiment, different target features correspond to different imaging optimization parameters. When the target feature is a crack, the irradiation treatment needs to be amplified and enhanced so as to observe the size of the crack, and when the target feature is corroded, the irradiation treatment needs to be enhanced so as to observe whether the hollow is corroded. As in medical endoscopes, when the target feature is a tumor, a staining magnification process is required; when the target feature is bleeding, magnification processing is required for observation; when the target feature is an ulcer, enhanced light treatment is required.
In a preferred embodiment, in step S2, the method for determining whether the target is further processed is as follows:
setting a first time threshold, acquiring a watching area of eyes of a detection person on a display, and when the watching area falls in an area where the target is located and the duration reaches the first time threshold, considering that the target is further operated and processed, otherwise, considering that the target is not further operated and processed.
In the present embodiment, the acquisition of the gaze area of the eyes of the detecting person on the display is a conventional technique, and the technical solution of acquiring the gaze area of the eyes provided in the conventional technique with publication number CN107103293B may be adopted. Or in an application scenario, a camera for shooting facing the face of the detected person is arranged on a display for displaying pictures, the camera outputs a face image, the watching region can be obtained by referring to the technical scheme disclosed in the publication number CN108615159A, and whether the watching region falls within the region where the target of the picture is located is determined (for example, the watching region can be determined according to whether the two are overlapped or whether the central points of the two are close to each other).
In an application scenario of the method for processing an in-picture target prompt of the present invention, a target prompt diagram is shown in fig. 3. Fig. 3 shows three pictures including the same position attribute a, where the first picture from left to right is used as the initial detection of the position, and when no associated feature of the first target 1 and the second target 2 exists in the associated feature library, the first picture is subjected to box prompt on the first target 1 and the second target 2.
When the detection personnel switches the inspection visual angle to obtain the second picture, the detection personnel further operates and processes the second target 2, the prompt box of the second target 2 is not displayed any more, and after the inspection is finished, the second target 2 is listed as the inspected target, namely the associated features of the second target are stored in the associated feature library.
When the detection personnel switches the inspection visual angle to obtain a third picture and further operates and processes the first target 1, the prompt box of the first target 1 is not displayed any more. Since the second object 2 is an inspected object, it is not prompted again.
When the inspector obtains the duplicate picture containing the position attribute a, the first object 1 and the second object 2 are not prompted any more since the first object 1 and the second object 2 have been inspected in the above-mentioned inspection process, as shown in fig. 4.
The invention also discloses an in-picture target prompt processing device which comprises a processor, a picture providing unit and a display, wherein the processor acquires the picture from the picture providing unit, processes the picture according to the in-picture target prompt processing method and displays the processed picture on the display.
In an application scenario of the device for prompting the target in the picture, a schematic flow diagram of the device is shown in fig. 2, the device is a judging instrument, after the judging instrument acquires the picture, whether the target exists is judged, when the target exists, whether the target is checked is judged, if the target is checked, prompting is not performed, if the target is not checked, the target feature is extracted, and a corresponding first probability is calculated, and the target feature and the first probability are output and displayed.
The invention also provides an endoscope system, which comprises the in-picture target prompt processing device, wherein the picture providing unit is an image sensor;
or the system also comprises a camera for shooting the face image of the detected person, the video input end of the processor is connected with the output end of the camera, and the image output end of the processor is connected with the input end of the display.
In this embodiment, the camera may be disposed on the display panel and directly faces the human face.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. An in-picture target prompt processing method is characterized by comprising the following steps:
step S1, acquiring the picture, judging whether the picture has the target,
if at least one target exists in the picture, extracting target characteristics and position attributes of the picture, wherein the position attributes represent the positions of the images in the picture, and entering step S2;
if no target exists in the picture, go to step S4;
step S2, the target characteristic is associated with the position attribute to form an associated characteristic, whether the associated characteristic same as the associated characteristic exists in the associated characteristic library or not is judged,
if the associated feature library does not have the associated feature same as the associated feature, judging whether the target is further operated and processed, if not, prompting the target, and entering the step S3; if the operation is processed, the prompt processing is not carried out on the target, the associated features are stored in an associated feature library, and the step S3 is carried out;
if the associated feature identical to the associated feature exists in the associated feature library, the target is not prompted, and the process proceeds to step S3;
step S3, judging whether all the targets are checked for associated features, if all the targets in the picture are checked for associated features, entering step S4, otherwise returning to step S2 to check for associated features of the next target in the picture;
step S4, judging whether the check of all pictures is finished, if not, returning to the step S1 to process the subsequent pictures; and if the operation is finished, exiting.
2. The method for processing the prompt for the target in the picture according to claim 1, wherein the step S1 comprises:
setting a plurality of standard pictures of different types, setting a first threshold value, calculating the similarity between the pictures and the different standard pictures, and obtaining a plurality of similarity values;
if the maximum similarity value is larger than the first threshold value, the position attribute of the standard picture corresponding to the maximum similarity value is used as the position attribute of the picture, the type name of the standard picture is used as the target feature, and if the maximum similarity value is smaller than the first threshold value, the picture is considered to have no target.
3. The method for processing an in-picture object hint as recited in claim 2, wherein in said step S2, said further operational process is:
outputting and prompting a type name corresponding to the target feature and a first probability of the target feature;
the first probability acquiring step includes:
step S21, calculating the number of pixels equal to or close to the pixel value of the pixel corresponding to the position in the picture in the standard image with the highest similarity to the picture, and recording the number as the first pixel number;
step S22, obtaining the sum of pixel points of the standard image with the highest similarity with the picture, and recording the sum as the number of second pixel points;
in step S23, the first probability is a ratio of the number of the first pixel points to the number of the second pixel points.
4. The in-picture target cue processing method according to claim 1, wherein in the step S1, the target feature comprises part or all of an outline, a color histogram, a size, or a pixel mean of a target region.
5. The method for processing an in-picture object hint as recited in claim 1, wherein in said step S2, the time interval for determining whether the object is further manipulated is:
a preset time period;
or before the detection personnel switch pictures;
or the detection person switches in front of the gazing area on the picture.
6. The method for processing the prompt of the target in the picture according to claim 1, wherein in the step S2, the method for determining whether the target is further processed is:
and judging whether the area containing the target in the picture is saved by screenshot, if so, considering that the target is further operated and processed, and otherwise, considering that the target is not further operated and processed.
7. The method for processing the prompt of the target in the picture according to claim 1, wherein in the step S2, the method for determining whether the target is further processed is:
judging whether the optimized imaging step is executed or not, if so, considering that the target is further operated and processed, otherwise, considering that the target is not further operated and processed;
the step of optimizing imaging comprises:
aiming at the target feature, finding the imaging optimization parameter corresponding to the target feature from the imaging optimization adjustment table, and outputting the imaging optimization parameter to the image sensor for adjusting an optimization execution unit of the image sensor to optimize imaging;
the imaging optimization adjustment table comprises a plurality of different target characteristics and imaging optimization parameters corresponding to each target characteristic.
8. The method for processing the prompt of the target in the picture according to claim 1, wherein in the step S2, the method for determining whether the target is further processed is:
setting a first time threshold, acquiring a watching area of eyes of a detection person on a display, and when the watching area falls in an area where a target is located and the duration reaches the first time threshold, considering that the target is further operated and processed, otherwise, considering that the target is not further operated and processed.
9. An in-picture object hint processing apparatus, comprising a processor, a picture providing unit, and a display, wherein the processor obtains a picture from the picture providing unit and processes the picture according to the in-picture object hint processing method of any one of claims 1 to 8, and then displays the processed picture on the display.
10. An endoscope system comprising the in-picture object cue processing device as defined in claim 9, the picture providing unit being an image sensor;
or the system also comprises a camera for shooting the face image of the detection person, the video input end of the processor is connected with the output end of the camera, and the image output end of the processor is connected with the input end of the display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910350260.4A CN110060252B (en) | 2019-04-28 | 2019-04-28 | Method and device for processing target prompt in picture and endoscope system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910350260.4A CN110060252B (en) | 2019-04-28 | 2019-04-28 | Method and device for processing target prompt in picture and endoscope system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110060252A CN110060252A (en) | 2019-07-26 |
| CN110060252B true CN110060252B (en) | 2021-11-05 |
Family
ID=67321352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910350260.4A Active CN110060252B (en) | 2019-04-28 | 2019-04-28 | Method and device for processing target prompt in picture and endoscope system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110060252B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110367913B (en) * | 2019-07-29 | 2021-09-28 | 杭州电子科技大学 | Wireless capsule endoscope image pylorus and ileocecal valve positioning method |
| CN111177449B (en) * | 2019-12-30 | 2021-11-05 | 深圳市商汤科技有限公司 | Multi-dimensional information integration method based on picture and related equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102753078A (en) * | 2010-09-24 | 2012-10-24 | 奥林巴斯医疗株式会社 | Image-display device and capsule-type endoscope system |
| CN106442569A (en) * | 2015-08-12 | 2017-02-22 | 业纳工业计量德国公司 | Borehole inspection device |
| CN106455947A (en) * | 2014-09-22 | 2017-02-22 | 奥林巴斯株式会社 | Image display device, image display method, and image display program |
| CN107808502A (en) * | 2017-10-27 | 2018-03-16 | 深圳极视角科技有限公司 | A kind of image detection alarm method and device |
| CN108378865A (en) * | 2012-11-23 | 2018-08-10 | 卡丹医学成像股份有限公司 | Display for a user the method and system of the transition between projection |
| CN109508189A (en) * | 2018-10-18 | 2019-03-22 | 北京奇艺世纪科技有限公司 | A kind of layout templates processing method, device and computer readable storage medium |
| CN110678878A (en) * | 2017-03-20 | 2020-01-10 | 华为技术有限公司 | Apparent feature description attribute identification method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015035229A2 (en) * | 2013-09-05 | 2015-03-12 | Cellscope, Inc. | Apparatuses and methods for mobile imaging and analysis |
| CN106664349B (en) * | 2014-03-25 | 2020-03-13 | 6115187加拿大公司暨伊美景象公司 | System for automatically defining user experience or system behavior related to scene image content |
| JP6876914B2 (en) * | 2017-03-21 | 2021-05-26 | 富士フイルムビジネスイノベーション株式会社 | Information processing device |
-
2019
- 2019-04-28 CN CN201910350260.4A patent/CN110060252B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102753078A (en) * | 2010-09-24 | 2012-10-24 | 奥林巴斯医疗株式会社 | Image-display device and capsule-type endoscope system |
| CN108378865A (en) * | 2012-11-23 | 2018-08-10 | 卡丹医学成像股份有限公司 | Display for a user the method and system of the transition between projection |
| CN106455947A (en) * | 2014-09-22 | 2017-02-22 | 奥林巴斯株式会社 | Image display device, image display method, and image display program |
| CN106442569A (en) * | 2015-08-12 | 2017-02-22 | 业纳工业计量德国公司 | Borehole inspection device |
| CN110678878A (en) * | 2017-03-20 | 2020-01-10 | 华为技术有限公司 | Apparent feature description attribute identification method and device |
| CN107808502A (en) * | 2017-10-27 | 2018-03-16 | 深圳极视角科技有限公司 | A kind of image detection alarm method and device |
| CN109508189A (en) * | 2018-10-18 | 2019-03-22 | 北京奇艺世纪科技有限公司 | A kind of layout templates processing method, device and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| "Localization of Wireless Capsule Endoscope: A Systematic Review";Haris Mateen et al.;《Journals & Magazines》;20170301;全文 * |
| "无线胶囊内窥镜图像检索及视频摘要方法研究与系统实现";詹昌飞;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20180715;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110060252A (en) | 2019-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018216617A1 (en) | Information processing device, control method, and program | |
| US20070195165A1 (en) | Image display apparatus | |
| US20110299748A1 (en) | Medical image processing apparatus, luminal image processing apparatus, luminal image processing method, and programs for the same | |
| US20210274999A1 (en) | Endoscope system, endoscope image processing method, and storage medium | |
| CN110060252B (en) | Method and device for processing target prompt in picture and endoscope system | |
| WO2007119297A1 (en) | Image processing device for medical use and image processing method for medical use | |
| EP2767215A1 (en) | Endoscope apparatus and control method thereof | |
| JP7289296B2 (en) | Image processing device, endoscope system, and method of operating image processing device | |
| CN112770662A (en) | Medical image processing device, medical image processing method, program, diagnosis support device, and endoscope system | |
| US10736499B2 (en) | Image analysis apparatus, image analysis system, and method for operating image analysis apparatus | |
| US20210338042A1 (en) | Image processing apparatus, diagnosis supporting method, and recording medium recording image processing program | |
| US11503982B2 (en) | Image processing apparatus, image processing method, and computer-readable recording medium for detecting a defective pixel in an image frame | |
| KR20160118037A (en) | Apparatus and method for detecting lesion from medical image automatically | |
| JP5581122B2 (en) | Electronic endoscope device | |
| JP6058240B1 (en) | Image analysis apparatus, image analysis system, and operation method of image analysis apparatus | |
| JP2009006089A (en) | Face imaging apparatus | |
| JP2012020028A (en) | Processor for electronic endoscope | |
| JP6414386B2 (en) | Image processing apparatus and image processing program | |
| JP2000197608A (en) | Ophthalmologic photographic apparatus | |
| JPWO2020071086A1 (en) | Information processing equipment, control methods, and programs | |
| CN114390276B (en) | Automatic testing method and system | |
| WO2023144936A1 (en) | Image-determining device, image-determining method, and recording medium | |
| JP2003310587A (en) | Display device for abnormal shadow detected result | |
| JP2023011303A (en) | Medical image processing apparatus and operating method of the same | |
| CN117158886A (en) | Visual field defect detection system and detection method based on eye movement tracking |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210927 Address after: 401120 1-1, 2-1, 3-1, building 5, No. 18, Cuiping Lane 2, Huixing street, Yubei District, Chongqing Applicant after: Chongqing Jinshan Medical Technology Research Institute Co.,Ltd. Address before: 401120 1 office buildings, Jinshan International Industrial City, 18 of Nei sang Road, Hui Xing street, Yubei District, Chongqing. Applicant before: CHONGQING JINSHAN MEDICAL APPLIANCE Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |