WO2024002136A1 - 一种照明校正方法、装置、电子设备及存储介质 - Google Patents
一种照明校正方法、装置、电子设备及存储介质 Download PDFInfo
- Publication number
- WO2024002136A1 WO2024002136A1 PCT/CN2023/103091 CN2023103091W WO2024002136A1 WO 2024002136 A1 WO2024002136 A1 WO 2024002136A1 CN 2023103091 W CN2023103091 W CN 2023103091W WO 2024002136 A1 WO2024002136 A1 WO 2024002136A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- light source
- response
- corrected
- source part
- image
- Prior art date
Links
- 238000005286 illumination Methods 0.000 title claims abstract description 85
- 238000012937 correction Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000004044 response Effects 0.000 claims abstract description 274
- 238000005316 response function Methods 0.000 claims description 45
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 239000011521 glass Substances 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 abstract description 29
- 230000008569 process Effects 0.000 description 18
- 238000003384 imaging method Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000003086 colorant Substances 0.000 description 4
- 239000013307 optical fiber Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000001795 light effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000003679 aging effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/06—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B23/00—Telescopes, e.g. binoculars; Periscopes; Instruments for viewing the inside of hollow bodies; Viewfinders; Optical aiming or sighting devices
- G02B23/24—Instruments or systems for viewing the inside of hollow bodies, e.g. fibrescopes
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B23/00—Telescopes, e.g. binoculars; Periscopes; Instruments for viewing the inside of hollow bodies; Viewfinders; Optical aiming or sighting devices
- G02B23/24—Instruments or systems for viewing the inside of hollow bodies, e.g. fibrescopes
- G02B23/2407—Optical details
- G02B23/2461—Illumination
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
- H05B47/115—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings
- H05B47/125—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings by using cameras
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Definitions
- the present application relates to the field of endoscope illumination, and in particular to an illumination correction method, device, electronic equipment and computer-readable storage medium.
- the multi-wavelength light source illumination device in the endoscope system can use multiple wavelength light-emitting elements as the source of illumination light, and combine the light paths through the optical lens group to converge into the optical fiber bundle of the endoscope light guide part, thereby affecting the endoscope lens. Provide lighting at the end.
- endoscope systems that use multi-wavelength light source illumination usually have inconsistencies between the emitted spectrum and the actual illumination spectrum transmitted to the endoscope. question.
- the illumination spectrum emitted by each endoscope is inconsistent, which may eventually lead to many problems such as abnormal color of the endoscope image, reduced contrast, and poor special light effects.
- the purpose of this application is to provide an illumination correction method, device, electronic equipment and computer-readable storage medium that can correct the illumination light emitted by an endoscope so that the relative spectra of the illumination light emitted by different endoscopes are consistent. And it can effectively reduce the complexity of endoscope illumination correction.
- this application provides an illumination correction method, which is applied to an endoscope system.
- the endoscope system includes a multi-wavelength light source and an endoscope.
- the illumination correction method includes:
- the reference light source part is set to emit light constantly in a specified lighting mode. At the same time, the light source part to be corrected is illuminated using multiple preset driving signals, and the endoscope is acquired each time it is illuminated. Response images taken on standard subjects;
- the preset driving signal and its corresponding response image are used to generate a characteristic response proportional model; the characteristic response proportional model is used to reflect the image response characteristics corresponding to the light source part to be corrected and the image response characteristics corresponding to the reference light source part.
- the standard object is a white balance cap.
- determining the reference light source part and the light source part to be corrected in the multi-wavelength light source includes:
- the lighting correction method further includes:
- the lighting correction method also includes:
- generating a characteristic response scale model using the preset driving signal and its corresponding response image includes:
- parameters in the driving response model are used to generate a first response function corresponding to the first response characteristic and the first response function corresponding to the first response characteristic.
- the characteristic response scale model is generated using the first response function and the second response function.
- generating a driving response model using the preset driving signal and the color value of the response image includes:
- a polynomial fitting method is used to fit the correlation between the preset driving signal and the color value of the response image to obtain the driving response model.
- the first response feature and the second response feature both correspond to different color channels
- the first response function corresponding to the first response feature and the first response function corresponding to the first response feature are generated using parameters in the driving response model.
- the second response function corresponding to the second response characteristic includes:
- a first response function corresponding to the color channel of the first response feature and a second response function corresponding to the color channel of the second response feature are respectively extracted from the driving response model.
- This application also provides an illumination correction device applied to an endoscope system.
- the endoscope system includes a multi-wavelength light source and an endoscope.
- the illumination correction device includes:
- An initialization module for determining the reference light source part and the light source part to be corrected in the multi-wavelength light source
- a driving module for setting the reference light source part to emit light constantly in a specified lighting mode, and at the same time, using multiple preset driving signals to light up the light source part to be corrected, and acquiring the content each time it is turned on.
- a model generation module for generating a characteristic response proportional model using the preset driving signal and its corresponding response image; the characteristic response proportional model is used to reflect the light source part to be corrected The corresponding relationship between the ratio of the corresponding image response characteristics and the corresponding image response characteristics of the reference light source part and the driving signal of the light source part to be corrected;
- An adjustment coefficient calculation module for determining an adjustment coefficient using the characteristic response scale model, the preset scale standard value and the original driving signal of the light source part to be corrected corresponding to the specified lighting mode, so as to utilize the adjustment
- the coefficient corrects the original driving signal of the light source part to be corrected in each lighting mode.
- This application also provides an electronic device, including:
- Memory used to store computer programs
- a processor configured to implement the illumination correction method as described above when executing the computer program.
- This application also provides a computer-readable storage medium, which stores computer-executable instructions.
- the computer-executable instructions are loaded and executed by a processor, the illumination correction method as described above is implemented.
- the present application provides an illumination correction method, which is applied to an endoscope system.
- the endoscope system includes a multi-wavelength light source and an endoscope.
- the illumination correction method includes: determining a reference light source part in the multi-wavelength light source; The light source part to be corrected; the reference light source part is set to emit light constantly in a designated lighting mode, and at the same time, the light source part to be corrected is illuminated using multiple preset driving signals, and the content is obtained each time it is lit.
- the original driving signal corresponding to the specified lighting mode determines an adjustment coefficient, so as to use the adjustment coefficient to correct the original driving signal of the light source part to be corrected in each lighting mode.
- this application can first determine the reference light source part and the light source part to be corrected in the multi-wavelength light source, and adjust the reference light source part to emit constant light under the specified lighting mode to ensure that the light emission amount of the reference light source part is fixed and easy to adjust.
- this application will collect the response image data actually generated by the light source part to be corrected under different driving signal conditions and the reference light source part that fixes the light, and use the preset driving signal and its response image to generate characteristic response proportional model type, the corresponding relationship between the ratio of the unique image response characteristics of the light source part to be corrected and the unique image response characteristics of the reference light source part and the driving signal of the light source part to be corrected can be established through this characteristic response proportion model, and then, using this
- the characteristic response scale model can calculate the target drive signal that can achieve the preset scale standard value, and determine the light source to be corrected based on the target drive signal and the original drive signal of the light source part to be corrected that corresponds to the specified lighting mode.
- the light source part to be corrected can be corrected, so that the relative spectra of the illumination light emitted by different endoscopes can be consistent.
- the above-mentioned illumination correction process can be directly implemented in the existing endoscope system without the need for special fixed tooling and optical power measurement equipment. Therefore, the complexity of endoscope illumination correction can be effectively reduced.
- This application also provides an illumination correction device, electronic equipment and a computer-readable storage medium, which have the above beneficial effects.
- Figure 1 is a schematic diagram of an endoscope system provided by an embodiment of the present application.
- Figure 2 is a flow chart of an illumination correction method provided by an embodiment of the present application.
- Figure 3 is a flow chart of a lighting correction control sequence provided by an embodiment of the present application.
- Figure 4 is a structural block diagram of an illumination correction device provided by an embodiment of the present application.
- FIG. 5 is a structural block diagram of an electronic device provided by an embodiment of the present application.
- FIG. 1 is a schematic diagram of an endoscope system provided by an embodiment of the present application. It can be seen that the endoscope system includes a multi-wavelength light source 10 , an endoscope 11 and an image processor 12 .
- the multi-wavelength light source 10 in the endoscope includes two or more light source parts.
- it may include a first light source part 101, a second light source part 102, and a third light source part 103. and the fourth light source part 104.
- These light source parts can be uniformly controlled by the light source control part 105, and the latter can realize independent control of the driving signals of each light source part.
- the light source control part 105 can drive the first light source part 101 and the first light source part 101 respectively according to each original driving signal corresponding to the imaging mode and the image brightness level.
- the second light source part 102, the third light source part 103 and/or the fourth light source part 104 emit light.
- the illumination light emitted by these light source parts is combined and coupled into the light guide fiber (not shown) in the endoscope 11 by the beam combining optical lens group 106, and is transmitted to the head end of the endoscope 11 by the light guide fiber to illuminate the subject.
- the object when performing illumination correction, the object is a standard object with high consistency such as a white balance cap, gauze, etc.) and facilitates the endoscope 11 to collect image signals.
- the image signal may be transmitted from the endoscope 11 to the image processor 12 for processing.
- the image processor 12 and the light source control unit 105 are connected through a serial port, which can transmit control signals and other specific information.
- the embodiments of the present application do not limit the specific image processor, light source control unit, light source unit, beam combining filter set, and endoscope, nor do they limit the specific number of light source units, nor do they limit the above components.
- the communication control process between them is limited.
- this application aims at the above-mentioned problem of spectral shift caused by differences in endoscopes, and provides an illumination correction method that keeps the illumination spectra emitted by different endoscopes consistent by correcting the relative spectra between the light source parts. .
- each light source unit remains consistent, which can be reflected on the image side as the image response ratio between each light source unit (specifically, it can be expressed as the color/channel response ratio) remains stable;
- the driving signals of each light source unit can directly affect the image response of each light source unit in the image collected by the endoscope connected to it;
- the main reason for the deviation of the illumination spectrum emitted from the endoscope lens is that the illumination light emitted from each light source has different attenuation in different endoscopes, and this attenuation can be considered to be fixed and does not depend on the specific lighting requirements. None to do.
- each endoscope can capture the standard object.
- the image response ratio between each light source part in the response image is the same as the image response ratio between each light source part in the response image taken by a standard endoscope on a standard object, which ensures that the relative spectra emitted by each endoscope remain consistent.
- standard objects such as white balance caps, white boards, gauze and other subjects with high imaging consistency
- the response image is a standard value of the image response ratio between each light source part that is established in advance.
- one of the light source parts can be selected as the reference light source part, and the other light source parts can be used as the light source parts to be corrected, with the reference light source part as the benchmark (that is, maintaining the image of the reference light source part) response characteristics remain unchanged), a standard value of the ratio between the image response characteristics corresponding to each light source part to be corrected and the image response characteristics corresponding to the reference light source part is established in advance.
- the selection criteria of the reference light source part can be any light source part. In practical applications, the light source part with good monochromaticity can be selected as the reference light source part to better distinguish its main image response characteristics.
- the "preset lighting requirements” specifically refer to that in order to achieve a certain imaging mode (preferably an imaging mode including light source units of various colors) and a certain image brightness level (for example, a medium brightness level), each light source unit must Emit light under the specified driving signal corresponding to the above-mentioned imaging mode and image brightness level.
- the "preset lighting requirement” can be: making the first light source part 101 in FIG.
- the designated driving signals I 1 to I 4 are mutually related driving signals, and the designated driving signals I 1 to I 4 may be different from each other.
- the illumination correction method provided by the embodiment of the present application can be used to determine the various parameters associated with the endoscope to be corrected.
- the adjustment coefficient of the light source part to be corrected can be used to determine the various parameters associated with the endoscope to be corrected.
- Figure 2 is a flow chart of an illumination correction method provided by an embodiment of the present application. The method is applied to the above-mentioned endoscope system.
- the endoscope system includes a multi-wavelength light source and an endoscope. , this method may include but is not limited to:
- the light source part to be corrected is the light source part that needs to be corrected and adjusted
- the reference light source part is the calibration standard of each light source part to be corrected.
- the reference light source part should remain fixed, that is, the reference light source part cannot be replaced, and its corresponding driving signal should remain fixed, and the light emission state should remain constant. This can ensure that each light source part to be corrected has a unified A comparison benchmark to facilitate adjustment of relative spectra between light sources.
- the embodiments of the present application do not limit the number of light source parts to be corrected that can correspond to a single correction. It can be one or multiple. In order to reduce the computational complexity and the setting complexity of related driving signals, a single correction can only process one light source part to be corrected.
- the "specified lighting mode” here corresponds to the "preset lighting requirements" above, that is, the “specified lighting mode” refers to each light source in order to achieve a certain imaging mode and a certain image brightness level.
- the part emits light under the specified driving signal corresponding to the above-mentioned imaging mode and image brightness level.
- the reference light source part should be constantly driven using the corresponding driving signal in the "specified lighting mode” to achieve constant light emission.
- the embodiments of the present application do not limit the specific types of driving signals of each light source part, such as voltage, current, control word, etc., which can be selected according to actual application requirements, where the control word is the control in serial port control word communication.
- the response image is image information obtained by photographing the standard object by the photosensitive element when a specific drive signal is used to light up the light source part and illuminate the standard object.
- this application uses image data to record the lighting conditions of the light source part.
- this application collects response images corresponding to multiple different preset driving signals. These images can not only record the specific response changes of the light source part to be corrected under different driving conditions, but also because the light source part to be corrected and the reference are different when collecting response images.
- the light source parts work at the same time, so the image can further record the change in response ratio between the light source part to be corrected and the reference light source part under different driving conditions, so as to facilitate subsequent fitting.
- the embodiments of the present application do not limit the specific value and quantity of the preset driving signals, which can be set according to actual application requirements.
- the preset driving signals can be written into a sequence in advance, and this sequence can be used to sequentially light up the light source parts to be corrected.
- the embodiments of the present application do not limit the specific type of the standard object, and may be standard objects with high consistency such as white balance caps and gauze. Since the white balance cap is a common accessory for endoscopes and can effectively ensure the consistency of imaging, this application uses the white balance cap as a standard object.
- the characteristic response proportion model is used to reflect the ratio of the image response characteristics corresponding to the light source part to be corrected and the image response characteristics corresponding to the reference light source part to the light source to be corrected. Correspondence between the driving signals of the parts.
- the characteristic response proportion model is a model obtained by fitting the above-mentioned preset driving signal and response image, and is used to reflect the ratio between the image response characteristics corresponding to the light source part to be corrected and the image response characteristics corresponding to the reference light source part. The correspondence between the driving signals of the light source parts to be corrected.
- the lighting correction effect can be achieved.
- the characteristic response ratio model it is possible to determine the specific drive required when the energy ratio between the image response characteristics corresponding to the light source part to be corrected and the image response characteristics corresponding to the reference light source part reaches the standard value.
- the signal conditions, and further, based on the determined specific driving signal conditions, the driving signal of the light source part to be corrected can be corrected, thereby achieving the lighting correction effect.
- the embodiments of the present application do not limit the method used to fit the characteristic response proportional model.
- linear fitting polynomial fitting, piecewise linear fitting, etc.
- the relationship between the preset driving signal and the response image can be first fitted to obtain an initial driving response model; then, according to the above two image response characteristics, relevant parameters are extracted from the driving response model to construct features.
- Response proportion model which can be adjusted according to actual application requirements.
- the preset ratio standard value is the standard energy ratio between the image response characteristics corresponding to the light source part to be corrected and the image response characteristics corresponding to the reference light source part under the above specified lighting mode. Since the driving signal of the light source part to be corrected is an independent variable in this model, and the proportional value between the image response characteristics corresponding to the light source part to be corrected under different driving signal conditions and the image response characteristics corresponding to the reference light source part is a dependent variable, therefore The characteristic response proportion model and the preset proportion standard value can be used to obtain the target driving signal corresponding to the light source part to be corrected, and then the adjustment coefficient can be determined by using the target driving signal and the original driving signal of the light source part to be corrected corresponding to the specified lighting mode. .
- I_fix represents the target driving signal
- Std_response represents the preset proportion standard value
- F -1 ( ⁇ ) represents the inverse function of the characteristic response proportion model
- I_now represents the original driving signal
- k represents the adjustment coefficient
- I_FIX represents the target driving signal sequence
- response i.e. F( ⁇ )
- the main reason for the deviation of the illumination spectrum emitted from the endoscope lens is that the illumination light emitted from each light source part has different attenuation in different endoscopes, and this attenuation can be considered to be fixed and has nothing to do with the specific illumination.
- the mode is independent, so after the adjustment coefficient is obtained, the coefficient can be used to correct the original driving signal corresponding to the light source part to be corrected in each lighting mode. It can be seen that since the calculation of the adjustment coefficient does not require the use of special fixed tooling and optical power measurement equipment, and the illumination correction process can also be directly implemented in the existing endoscope system, the complexity of endoscope illumination correction can be effectively reduced. .
- this coefficient can also be saved in the memory of the endoscope, so that when the endoscope is connected to the multi-wavelength light source again, the multi-wavelength light source automatically reads the adjustment coefficient and adjusts the corresponding data to be processed.
- the drive signal of the correction light source unit in each lighting mode is updated and can be set according to actual application requirements.
- step S201 is specifically: determining the reference light source part and any light source part to be corrected in the multi-wavelength light source. Then, after determining the adjustment coefficient using the characteristic response scale model, the preset scale standard value and the original drive signal of the light source part to be corrected, it may also include:
- Step 21 Determine the next light source part to be corrected in the multi-wavelength light source, and enter the step of lighting the light source part to be corrected using multiple preset driving signals until the adjustment coefficients of all light source parts to be corrected have been determined.
- a validity detection process can be set up to detect The effectiveness of the adjustment coefficient.
- the embodiments of the present application do not limit the specific process of validity detection. For example, after calibration and adjustment, the data collected by the endoscope system to be corrected and the standard endoscope system can be detected when the relevant light source parts are lit in the same lighting mode. Respond to the deviation value between images, and determine whether the adjustment coefficient is reliable based on whether the deviation value is less than a preset threshold.
- the illumination correction method may also include:
- Step 31 Determine the target illumination mode, use the original driving signal in the target illumination mode to light up all the light source parts in the multi-wavelength light source, and obtain the original response image captured by the endoscope on the standard object.
- Step 32 Obtain the standard response image captured by the standard endoscope system on the standard object in the target illumination mode, and determine the first deviation value between the original response image and the standard response image.
- the target illumination mode is preferably an illumination mode that can simultaneously light up all the light source portions of the multi-wavelength light source.
- the embodiments of the present application do not limit the driving signals corresponding to each light source part in the target lighting mode, and can be set according to actual application requirements.
- the multi-wavelength light source does not have an illumination mode that can light up all the light source parts, the multiple illumination modes it has can also be combined, as long as it can ensure that the combined illumination mode can cover all the light sources in the multi-wavelength light source. Just do it.
- Step 33 Use all adjustment coefficients to correct the original driving signals of the corresponding light source parts to be corrected, and obtain the corrected driving signals in the target lighting mode;
- Step 34 Use the correction drive signal in the target illumination mode to light up all the light source parts in the multi-wavelength light source, and simultaneously obtain the correction response image captured by the endoscope on the standard object;
- Step 35 Determine the second deviation value between the correction response image and the standard response image, and determine whether the second deviation value is smaller than the first deviation value; if so, proceed to step 36; if not, determine that the correction has failed and prompt a failure.
- Step 36 If yes, save all adjustment coefficients.
- the standard endoscope system is an endoscope system that has been calibrated, which can be used as a benchmark for evaluating the correction of this endoscope.
- This application does not limit the index selected when calculating the deviation value.
- the index may include single or multiple indexes such as channel response ratio, color evaluation coefficient of each color space, etc. If the adjustment coefficients are all verified to be valid, save all adjustment coefficients in the endoscope's memory. memory for automatic reading of multi-wavelength light sources.
- FIG. 3 is a flow chart of an illumination correction control sequence provided by an embodiment of the present application.
- the present application can first determine the reference light source part and the light source part to be corrected in the multi-wavelength light source, and adjust the reference light source part to emit constant light under the specified lighting mode to ensure that the light emission amount of the reference light source part is fixed. , to facilitate the adjustment of the relative spectrum between each light source part; then, this application will collect the response image data actually generated by the light source part to be corrected under different driving signal conditions and the reference light source part with fixed light output, and use the preset driving signal and its The response image generates a characteristic response proportion model.
- the ratio of the unique image response characteristics of the light source part to be corrected and the unique image response characteristics of the reference light source part and the “driving signal of the light source part to be corrected” can be established.
- the target drive signal that can achieve the preset proportion standard value can be calculated, and based on the target drive signal and the drive signal of the light source part to be corrected, it corresponds to the reference light source
- the original driving signal determines the adjustment coefficient of the light source part to be corrected.
- the correction of the light source part to be corrected can be realized, so that the relative spectra of the illumination light emitted by different endoscopes can be consistent.
- the above-mentioned illumination correction process can be directly implemented in the existing endoscope system without the need for special fixed tooling and optical power measurement equipment. Therefore, the complexity of endoscope illumination correction can be effectively reduced.
- the specific construction process of the characteristic response proportional model is introduced in detail below.
- using the preset driving signal and its corresponding response image to generate the characteristic response proportional model may include:
- the driving response model is used to reflect the correspondence between the driving signal of the light source to be corrected and the image response value.
- the model can be fitted using linear fitting, polynomial fitting, piecewise linear fitting, etc. Since the polynomial fitting method is commonly used, embodiments of the present application can use the polynomial fitting method to fit the correlation between the preset driving signal and the color value of the response image to obtain a driving response model.
- the embodiments of the present application do not limit the color space corresponding to the response image.
- it can be RGB color space (Red, Green, Blue), or other color spaces such as YUV (Y represents brightness, U represents color, and V represents saturation) color space, and the above color value can be RGB colors can also be YUV colors or other types of colors.
- RGB color space Red, Green, Blue
- YUV Y represents brightness, U represents color, and V represents saturation
- RGB colors can also be YUV colors or other types of colors.
- Multiple preset driving signals can be represented by the following sequence: [I 1 I 2 I 3 ...I m ];
- I i ,i ⁇ [1,m] represents the i-th driving signal.
- the RGB response value of the driving signal corresponding to the response image can be represented by the image response sequence matrix:
- R i , G i and B i represent the RGB values corresponding to the i-th response image.
- the driving response model obtained by polynomial fitting of the above preset driving signal and response sequence matrix can be expressed as:
- f R (I), f G (I), and f B (I) represent the response functions of the three channels R, G, and B
- P refers to the series of the polynomial
- kr p , kg p , and kb p are the respective
- the coefficients of the term are determined by fitting the above-mentioned actual measured values, where kr 0 , kg 0 , and kb 0 are the channel values sensed by the image when only the reference light source is used for illumination.
- the first response characteristic is an image response characteristic unique to the reference light source part
- the second response characteristic is an image response characteristic unique to the light source part to be corrected.
- the response signals generated by the reference light source part and the light source part to be corrected can be significantly distinguished according to the first response characteristic and the second response characteristic.
- the embodiments of the present application do not limit the types of the first response feature and the second response feature. For example, they may be color channel features or color features, where the color channels are R, G, and B in the RGB color space. color channels, and the color is the result of mixing these channels.
- each channel has an independent response function in the driving response model
- the response function of the corresponding channel can be directly extracted from the above model as the corresponding response feature. specific response function.
- the embodiments of the present application do not limit the specific manner of selecting the first response feature and the second response feature. For example, when the above response feature is a color channel feature, the main response of the reference light source part and the light source part to be corrected can be selected. channel; when two primary response channels overlap, the channel with the second highest response can be selected, and so on.
- the first response feature and the second response feature both correspond to different color channels, and parameters in the driving response model are used to generate a first response function corresponding to the first response feature and a third response function corresponding to the second response feature.
- Two response functions can include:
- a first response function corresponding to the color channel of the first response feature and a second response function corresponding to the color channel of the second response feature are respectively extracted from the driving response model.
- BG_RATIO that is, the characteristic response scale model
- the above feature response proportion model can also have other forms, and can be based on Adjust according to actual application requirements.
- embodiments of the present application can use a fitting method to determine the correlation between the preset driving signal and the response image, and then use the parameters in the corresponding driving response model to construct a first response function corresponding to the first response feature and The second response function corresponding to the second response characteristic, and finally the first response function and the second response function can be used to construct a characteristic response proportion model to effectively fit the actual characteristics of the light source part to be corrected and the reference light source part under different driving signal conditions.
- Feature response proportion changes can be used to construct a characteristic response proportion model to effectively fit the actual characteristics of the light source part to be corrected and the reference light source part under different driving signal conditions.
- the lighting correction device, electronic equipment, and computer-readable storage medium provided by the embodiments of the present application are introduced below.
- the lighting correction device, electronic equipment, and computer-readable storage medium described below and the lighting correction method described above may be mutually referenced.
- Figure 4 is a structural block diagram of an illumination correction device provided by an embodiment of the present application.
- the device is applied to an endoscope system.
- the endoscope system includes a multi-wavelength light source and an endoscope.
- the device may include :
- Initialization module 401 is used to determine the reference light source part and the light source part to be corrected in the multi-wavelength light source;
- the driving module 402 is used to set the reference light source part to emit light constantly in a specified lighting mode, and at the same time, use multiple preset driving signals to light up the light source part to be corrected, and collect the endoscope's reference to the standard object each time it is turned on. captured response images;
- the model generation module 403 is used to generate a characteristic response proportion model using the preset driving signal and its corresponding response image; the characteristic response proportion model is used to reflect the image response characteristics corresponding to the light source part to be corrected and the image response characteristics corresponding to the reference light source part. The corresponding relationship between the ratio and the driving signal of the light source part to be corrected;
- the adjustment coefficient calculation module 404 is used to determine the adjustment coefficient using the characteristic response scale model, the preset scale standard value and the original driving signal of the light source part to be corrected corresponding to the designated lighting mode, so as to use the adjustment coefficient to correct the light source part to be corrected.
- the standard object is a white balance cap.
- the initialization module 401 is specifically used to determine the reference light source part and any light source part to be corrected in the multi-wavelength light source; the device may also include:
- Traversal module used in the adjustment coefficient calculation module 404 to use the characteristic response scale model, preset After the adjustment coefficient is determined by the proportional standard value and the original driving signal of the light source part to be corrected corresponding to the designated lighting mode, the next light source part to be corrected in the multi-wavelength light source is determined to enter the driving module 402 and the adjustment coefficient calculation module 404. Process until all adjustment coefficients of the light source parts to be corrected have been determined.
- the device may also include:
- the original response image acquisition module is used to determine the target lighting mode, use the original driving signal in the target lighting mode to illuminate all light source parts in the multi-wavelength light source, and obtain the original response image captured by the endoscope on the standard object;
- the first deviation value calculation module is used to obtain the standard response image captured by the standard endoscope system on the standard object in the target lighting mode, and determine the first deviation value between the original response image and the standard response image;
- a correction module used to use all adjustment coefficients to correct the original driving signal of the corresponding light source part to be corrected to obtain the corrected driving signal in the target lighting mode
- the correction response image acquisition module is used to light up all the light source parts of the endoscope using the correction drive signal in the target lighting mode, and at the same time acquire the correction response image captured by the endoscope on the standard object;
- the second deviation value calculation and validity judgment module is used to determine the second deviation value between the correction response image and the standard response image, and determine whether the second deviation value is smaller than the first deviation value; if so, save all adjustment coefficients.
- model generation module 403 may include:
- a driving response model generation unit used to generate a driving response model using the preset driving signal and the color value of its corresponding response image
- a response function generation unit configured to generate a first response function corresponding to the first response feature and a second response function corresponding to the second response feature using parameters in the driving response model
- the characteristic response proportional model generating unit is configured to generate a characteristic response proportional model using the first response function and the second response function according to the first response characteristic corresponding to the reference light source part and the second response characteristic corresponding to the light source part to be corrected.
- the driver response model generation unit may include:
- the driving response model generation subunit is used to use a polynomial fitting method to fit the correlation between the preset driving signal and the color value of the response image to obtain a driving response model.
- the response function generation unit may include:
- the extraction subunit is used to respectively extract the first response function corresponding to the color channel of the first response feature and the second response function corresponding to the color channel of the second response feature from the driving response model.
- the embodiment of the present application discloses an electronic device 20, including a processor 21 and a memory 22; wherein the memory 22 is used to save a computer program; the processor 21 is used to execute the The computer program executes the illumination correction method disclosed in the foregoing embodiments.
- the memory 22, as a carrier for resource storage may be a read-only memory, a random access memory, a magnetic disk or an optical disk, and the storage method may be short-term storage or permanent storage.
- the electronic device 20 also includes a power supply 23, a communication interface 24, an input and output interface 25 and a communication bus 26; wherein the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20;
- the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, which is not specifically limited here;
- the input and output interface 25 is used to obtain external input data or output data to the external world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.
- embodiments of the present application also disclose a computer-readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, the illumination correction method disclosed in the foregoing embodiments is implemented.
- RAM random access memory
- ROM read-only memory
- electrically programmable ROM electrically erasable programmable ROM
- registers hard disks, removable disks, CD-ROMs, or anywhere in the field of technology. any other known form of storage media.
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Optics & Photonics (AREA)
- Surgery (AREA)
- General Physics & Mathematics (AREA)
- Astronomy & Astrophysics (AREA)
- Biomedical Technology (AREA)
- Animal Behavior & Ethology (AREA)
- Engineering & Computer Science (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Radiology & Medical Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biophysics (AREA)
- Endoscopes (AREA)
Abstract
一种照明校正方法、装置、电子设备及存储介质，涉及内窥镜照明领域，方法应用于内窥镜***，内窥镜***包括多波长光源和内窥镜，该方法可首先确定多波长光源中的参考光源部及待校正光源部，并将参考光源部调整为恒定出光，以便于调整各光源部之间的相对光谱；随后，可采集待校正光源部在不同驱动信号条件下与固定出光的参考光源部实际产生的响应图像数据，并利用预设驱动信号及其响应图像生成特征响应比例模型，其中该模型可反映待校正光源部独有的图像响应特征和参考光源部独有的图像响应特征的比例与待校正光源部的驱动信号之间的对应关系，进而可基于该模型对待校正光源部进行相对光谱校正，以使不同内窥镜出射的照明光的相对光谱达到一致。
Description
本申请要求于2022年06月30日提交中国专利局、申请号为202210762851.4、发明名称为“一种照明校正方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请涉及内窥镜照明领域，特别涉及一种照明校正方法、装置、电子设备及计算机可读存储介质。
内窥镜***中的多波长光源照明装置可采用多种波长发光元件作为照明光来源，并通过光学透镜组进行光路合束，共同汇聚至内窥镜导光部光纤束，从而对内窥镜头端提供照明。然而，受结构位置公差与装配工艺限制，以及受光纤束等导光材料的老化影响，采用多波长光源照明的内窥镜***通常存在出射光谱与传导至内窥镜中的实际照明光谱不一致的问题。而各内窥镜出射的照明光谱不一致，最终可能会导致内窥镜图像颜色异常、对比度下降、特殊光效果不佳等诸多问题。
因此，如何提升内窥镜***从头端出射至被摄体的照明光谱的一致性，是目前亟需解决的技术问题。
发明内容
本申请的目的是提供一种照明校正方法、装置、电子设备及计算机可读存储介质，能够对内窥镜出射的照明光进行校正，使不同内窥镜出射的照明光的相对光谱达到一致，且可有效降低内窥镜照明校正的复杂度。
为解决上述技术问题，本申请提供一种照明校正方法，应用于内窥镜***，所述内窥镜***包括多波长光源和内窥镜，所述照明校正方法包括：
确定所述多波长光源中的参考光源部以及待校正光源部；
将所述参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮所述待校正光源部，并在每次点亮时获取所述内窥镜
对标准对象拍摄的响应图像；
利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型；所述特征响应比例模型用于反映所述待校正光源部对应的图像响应特征和所述参考光源部对应的图像响应特征之比与所述待校正光源部的驱动信号之间的对应关系；
利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数，以利用所述调节系数校正所述待校正光源部在各照明模式下的原始驱动信号。
可选地，所述标准对象为白平衡帽。
可选地，所述确定所述多波长光源中的参考光源部以及待校正光源部，包括：
确定所述多波长光源中的参考光源部以及任一待校正光源部；
则，在利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数之后，所述照明校正方法还包括：
确定所述多波长光源中的下一待校正光源部，并进入所述利用多个预设驱动信号点亮所述待校正光源部的步骤，直至所有所述待校正光源部的调节系数均已确定。
可选地，所述照明校正方法还包括：
确定目标照明模式，同时利用所述目标照明模式下的原始驱动信号点亮所述多波长光源中的所有光源部，并获取所述内窥镜对所述标准对象拍摄的原始响应图像；
获取标准内窥镜***在所述目标照明模式下对所述标准对象拍摄的标准响应图像，并确定所述原始响应图像与所述标准响应图像间的第一偏差值；
利用所有所述调节系数校正其对应的待校正光源部的原始驱动信号，得到目标照明模式下的校正驱动信号；
利用所述目标照明模式下的校正驱动信号点亮所述多波长光源中的所有光源部，同时获取所述内窥镜对所述标准对象拍摄的校正响应图像；
确定所述校正响应图像与所述标准响应图像间的第二偏差值，并判断所述第二偏差值是否小于第一偏差值；
若是，则保存所有所述调节系数。
可选地，所述利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型，包括：
利用所述预设驱动信号及所述响应图像的色彩值生成驱动响应模型；
根据所述参考光源部对应的第一响应特征和所述待校正光源部对应的第二响应特征，利用所述驱动响应模型中的参数生成所述第一响应特征对应的第一响应函数以及所述第二响应特征对应的第二响应函数；
利用所述第一响应函数及所述第二响应函数生成所述特征响应比例模型。
可选地，所述利用所述预设驱动信号及所述响应图像的色彩值生成驱动响应模型，包括：
利用多项式拟合方法对所述预设驱动信号及所述响应图像的色彩值间的关联关系进行拟合，得到所述驱动响应模型。
可选地，所述第一响应特征及所述第二响应特征均对应不同的颜色通道，所述利用所述驱动响应模型中的参数生成所述第一响应特征对应的第一响应函数以及所述第二响应特征对应的第二响应函数，包括：
从所述驱动响应模型中分别提取所述第一响应特征的颜色通道对应的第一响应函数，以及所述第二响应特征的颜色通道对应的第二响应函数。
本申请还提供一种照明校正装置，应用于内窥镜***，所述内窥镜***包括多波长光源和内窥镜，所述照明校正装置包括：
初始化模块，用于确定所述多波长光源中的参考光源部以及待校正光源部；
驱动模块，用于将所述参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮所述待校正光源部，并在每次点亮时获取所述内窥镜对标准对象拍摄的响应图像；
模型生成模块，用于利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型；所述特征响应比例模型用于反映所述待校正光源部对
应的图像响应特征和所述参考光源部对应的图像响应特征之比与所述待校正光源部的驱动信号之间的对应关系；
调节系数计算模块，用于利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数，以利用所述调节系数校正所述待校正光源部在各照明模式下的原始驱动信号。
本申请还提供一种电子设备，包括：
存储器，用于存储计算机程序；
处理器，用于执行所述计算机程序时实现如上所述的照明校正方法。
本申请还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机可执行指令，所述计算机可执行指令被处理器加载并执行时，实现如上所述的照明校正方法。
本申请提供一种照明校正方法，应用于内窥镜***，所述内窥镜***包括多波长光源和内窥镜，所述照明校正方法包括：确定所述多波长光源中的参考光源部以及待校正光源部；将所述参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮所述待校正光源部，并在每次点亮时获取所述内窥镜对标准对象拍摄的响应图像；利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型；所述特征响应比例模型用于反映所述待校正光源部对应的图像响应特征和所述参考光源部对应的图像响应特征之比与所述待校正光源部的驱动信号之间的对应关系；利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数，以利用所述调节系数校正所述待校正光源部在各照明模式下的原始驱动信号。
可见，本申请可首先确定多波长光源中的参考光源部及待校正光源部，并将参考光源部调整为在指定照明模式下恒定出光，以保证参考光源部的出光量固定不变，便于调整各光源部之间的相对光谱；随后，本申请将采集待校正光源部在不同驱动信号条件下与固定出光的参考光源部实际产生的响应图像数据，并利用预设驱动信号及其响应图像生成特征响应比例模
型，通过该特征响应比例模型可建立待校正光源部独有的图像响应特征和参考光源部独有的图像响应特征的比例与待校正光源部的驱动信号之间的对应关系，进而，利用该特征响应比例模型，可推算出可达成预设比例标准值的目标驱动信号，并基于该目标驱动信号和待校正光源部的、与所述指定照明模式相对应的原始驱动信号，确定待校正光源部的调节系数，最终，基于该调节系数即可实现对待校正光源部的校正，能够使不同内窥镜出射的照明光的相对光谱达到一致。并且，上述照明校正过程可直接在现有内窥镜***中实现，无需借助特殊的固定工装和光功率测量设备，因此，可有效降低内窥镜照明校正的复杂度。本申请还提供一种照明校正装置、电子设备及计算机可读存储介质，具有上述有益效果。
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。
图1为本申请实施例所提供的一种内窥镜***的示意图；
图2为本申请实施例所提供的一种照明校正方法的流程图；
图3为本申请实施例所提供的一种照明校正控制时序的流程图；
图4为本申请实施例所提供的一种照明校正装置的结构框图；
图5为本申请实施例所提供的一种电子设备的结构框图。
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
为便于理解，首先将对本申请所适用的内窥镜***进行简单描述。请参考图1，图1为本申请实施例所提供的一种内窥镜***的示意图。可见，该内窥镜***包括多波长光源10、内窥镜11和图像处理器12。
具体地，内窥镜中的多波长光源10包括两个或两个以上光源部，例如，作为其中一种示例，其可以包括第一光源部101、第二光源部102、第三光源部103和第四光源部104，这些光源部可由光源控制部105统一控制，且后者可实现对各光源部驱动信号的单独控制。比如，当选定某种成像模式和某个图像亮度档位时，光源控制部105可按照与该成像模式和该图像亮度档位对应的各个原始驱动信号，分别驱动第一光源部101、第二光源部102、第三光源部103和/或第四光源部104发光。这些光源部所发出照明光由合束光学透镜组106合束耦合入内窥镜11中的导光光纤(图未示)，由导光光纤传输至内窥镜11的头端以照亮被摄物体(在进行照明校正时，被摄物体为如白平衡帽、纱布等一致性较高的标准对象)并方便内窥镜11采集图像信号。图像信号可由内窥镜11传输至图像处理器12进行处理。此外，图像处理器12与光源控制部105间由串口连接，可进行控制信号及其他特定信息的传递。
需要说明的是，本申请实施例并不限定具体的图像处理器、光源控制部、光源部、合束滤光片组及内窥镜，也不限定光源部的具体数量，也不对上述各部件间的通信控制过程进行限定，具体可参考内窥镜***的相关技术。
在实际应用中，可以默认多波长光源在出厂前已完成光谱调试，所以即便是不同的多波长光源在相同的照明模式下也能出射相同的照明光谱，从而，可以认为所有多波长光源都具有一致的出射光谱。然而，在使用过程中不可控的是，当不同内窥镜连接至多波长光源时，受结构位置公差与装配工艺限制，多波长光源中各光源部实际耦合到各内窥镜中的光谱有可能会出现偏移，进而导致各内窥镜所出射的照明光谱与多波长光源实际出射的照明光谱不一致。另外，受光纤束本身对不同波段的照明光的传导特
性差异以及光纤束的老化影响，即便同一内窥镜连接同一多波长光源也会出现镜体出射的光谱与传导至内窥镜中的实际照明光谱不一致的问题。而内窥镜出射的照明光谱不一致，最终可能会导致内窥镜图像颜色异常、对比度下降、特殊光效果不佳等诸多问题。
鉴于此，本申请针对上述由内窥镜差异引起的光谱偏移的问题，提供了一种通过校正各光源部之间的相对光谱，使得不同内窥镜出射的照明光谱保持一致的照明校正方法。
其中，经本申请发明人研究发现：
1、各光源部之间的相对光谱保持一致，在图像端可体现为各光源部间的图像响应比例(具体可表现为颜色/通道响应比例)保持稳定；
2、各光源部的驱动信号可直接影响与其连接的内窥镜采集到的图像中各光源部的图像响应；
3、内窥镜头端出射的照明光谱产生偏移的原因主要在于各光源部出射的照明光在不同内窥镜中具有不一样的衰减，而该衰减可以认为是固定的，与具体的照明要求无关。
因此，只要在任意相同的照明要求下(比如，在同一成像模式、同一图像亮度档位下)，通过使用合适的调节系数校正各光源的原始驱动信号，使各内窥镜对标准对象拍摄的响应图像中各光源部间的图像响应比例均与标准内窥镜对标准对象拍摄的响应图像中各光源部间的图像响应比例相同，即可保证各内窥镜出射的相对光谱保持一致。
基于上述发明构思，在本申请实施例中，可以首先根据标准内窥镜在预设照明要求下对标准对象(比如，白平衡帽、白板、纱布等成像一致性较高的被摄对象)拍摄的响应图像，预先建立各光源部间图像响应比例的标准值。
其中，为了便于建立各光源部间图像响应的相对关系，可以选择其中一个光源部作为参考光源部，其他光源部作为待校正光源部，以参考光源部为基准(即，保持参考光源部的图像响应特征不变)，预先建立各待校正光源部对应的图像响应特征与参考光源部对应的图像响应特征之间的比例标准值。可以理解的是，在预设比例标准值阶段，本申请实施例并不限定
参考光源部的选择标准，其可以为任意光源部，在实际应用中，可以选择单色性好的光源部作为参考光源部，以更好地区分其主要的图像响应特征。
其中，所述“预设照明要求”具体是指，为了实现某一成像模式(优选包括各色光源部的成像模式)和某一图像亮度档位(比如，中等亮度档位)，各光源部均在与上述成像模式和图像亮度档位对应的指定驱动信号下出光。例如，所述“预设照明要求”可以为：使图1中的第一光源部101(设为参考光源部)在指定驱动信号I1下发光，第二光源部102(设为待校正光源部)在指定驱动信号I2下发光，第三光源部103(设为待校正光源部)在指定驱动信号I3下发光，第四光源部104(设为待校正光源部)在指定驱动信号I4下发光，指定驱动信号I1～I4互为关联驱动信号，并且，指定驱动信号I1～I4可以互不相等。
进一步地，在实际应用中，当需要针对某一待校正的内窥镜进行照明校正时，可以采用本申请实施例所提供的照明校正方法来确定与该待校正的内窥镜关联的、各待校正光源部的调节系数。
具体地，请参考图2，图2为本申请实施例所提供的一种照明校正方法的流程图，该方法应用于上述内窥镜***，该内窥镜***包括多波长光源和内窥镜，该方法可以包括但不限于：
S201、确定多波长光源中的参考光源部以及待校正光源部。
如上所述，待校正光源部为需要被校正调整的光源部，而参考光源部为各待校正光源部的校正基准。在完成所有光源部的校正之前，参考光源部应当保持固定，即参考光源部不能更换，且其对应的驱动信号应当保持固定，出光状态应当保持恒定，这样可以保证各个待校正光源部有统一的比较基准，便于调整各光源之间的相对光谱。
需要说明的是，本申请实施例并不限定单次校正可对应的待校正光源部数量，可以为一个也可以为多个。为降低计算复杂度及相关驱动信号的设置复杂度，单次校正可仅对一个待校正光源部进行处理。
S202、将参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮待校正光源部，并在每次点亮时获取内窥镜对标准对象拍摄的响应图像。
应当指出的是，此处的“指定照明模式”与上文中的“预设照明要求”相互对应，即“指定照明模式”是指为了实现某一成像模式和某一图像亮度档位，各光源部在与上述成像模式和图像亮度档位对应的指定驱动信号下发光。换句话说，参考光源部应当采用在“指定照明模式”中对应的驱动信号进行恒定驱动，以实现恒定出光。需要说明的是，本申请实施例并不限定各光源部的驱动信号的具体类型，例如电压、电流、控制字等，可根据实际应用需求进行选择，其中控制字为串口控制字通信中的控制量，用于控制自带控制板的发光元件。进一步，在本申请实施例中，响应图像为在利用特定驱动信号点亮光源部并照明标准对象的情况下，感光元件对标准对象拍摄得到的图像信息。换而言之，本申请采用图像数据来记录光源部的照明情况。进一步，本申请采集了多个不同预设驱动信号对应的响应图像，这些图像不仅能够记录待校正光源部在不同驱动条件下具体的响应变化情况，同时由于采集响应图像时待校正光源部和参考光源部同时工作，因此该图像还能够进一步记录不同驱动条件下待校正光源部与参考光源部间的响应比例变化情况，以便后续进行拟合。需要说明的是，本申请实施例并不限定预设驱动信号的具体数值及数量，可根据实际应用需求进行设定。为便于控制，可预先将预设驱动信号写入序列，并利用这一序列顺序点亮待校正光源部。
进一步，本申请实施例并不限定标准对象的具体类型，可以为白平衡帽、纱布等一致性较高的标准对象。由于白平衡帽为内窥镜常规配附件，且可有效保证成像的一致性，因此本申请采用白平衡帽作为标准对象。
S203、利用预设驱动信号及其对应的响应图像生成特征响应比例模型；特征响应比例模型用于反映待校正光源部对应的图像响应特征和参考光源部对应的图像响应特征之比与待校正光源部的驱动信号之间的对应关系。
本申请实施例中，特征响应比例模型是利用上述预设驱动信号及响应图像拟合得到的模型，用于反映待校正光源部对应的图像响应特征和参考光源部对应的图像响应特征之比与待校正光源部的驱动信号之间的对应关系。
其中，可以理解的是，由于照明光谱一致性在图像端可体现为各光源
部间的图像响应比例保持稳定，因此，当各光源部件的图像响应比例达到标准值时，即可实现照明校正效果。在本申请实施例中，通过建立该特征响应比例模型，可以确定待校正光源部对应的图像响应特征与参考光源部对应的图像响应特征之间的能量比例达到该标准值时所需的特定驱动信号条件，进而，可基于所确定的特定驱动信号条件，对待校正光源部的驱动信号进行校正，由此实现照明校正效果。
需要说明的是，本申请实施例并不限定拟合特征响应比例模型所使用的方法，例如可采用线性拟合、多项式拟合、分段线性拟合等方式。进一步，拟合过程中可首先拟合预设驱动信号及响应图像之间的关系，得到一个初始的驱动响应模型；随后依照上述两种图像响应特征，从驱动响应模型中提取相关参数来构造特征响应比例模型，具体可根据实际应用需求进行调整。
S204、利用特征响应比例模型、预设比例标准值及待校正光源部的、与指定照明模式相对应的原始驱动信号确定调节系数，以利用调节系数校正待校正光源部在各照明模式下的原始驱动信号。
需要说明的是，预设比例标准值即为在上述指定照明模式下待校正光源部对应的图像响应特征和参考光源部对应的图像响应特征间的标准能量比例。由于待校正光源部的驱动信号在该模型中属于自变量，而待校正光源部对应的图像响应特征在不同驱动信号条件与参考光源部对应的图像响应特征之间的比例值属于因变量，因此可利用特征响应比例模型及预设比例标准值，反求待校正光源部对应的目标驱动信号，进而利用目标驱动信号和待校正光源部的、与指定照明模式相对应的原始驱动信号确定调节系数。
具体的，调节系数的确定过程可表示为：
I_fix＝F-1(Std_response)
k＝I_fix/I_now
I_fix＝F-1(Std_response)
k＝I_fix/I_now
其中，I_fix表示目标驱动信号，Std_response表示预设比例标准值，F-1(·)表示特征响应比例模型的反函数，I_now表示原始驱动信号，k表示调节系数。需要说明的是，本申请实施例并不限定逆函数的确定方式，可
参考相关技术内容。
当然，假若单次校正可同时校正多个待校正光源部，则上述调节系数的确定过程可表示为：
response＝F(I1，I2，I3...Im)
I_FIX＝[I_fix1，I_fix2，I_fix3I_fixm]＝F-1(Std_response)
K＝I_FIX/I_now
response＝F(I1，I2，I3...Im)
I_FIX＝[I_fix1，I_fix2，I_fix3I_fixm]＝F-1(Std_response)
K＝I_FIX/I_now
其中，I_FIX表示目标驱动信号序列，response(即F(·))表示特征响应比例模型。
进一步，由于内窥镜头端出射的照明光谱产生偏移的原因主要在于各光源部出射的照明光在不同内窥镜中具有不一样的衰减，而该衰减可以认为是固定的，与具体的照明模式无关，因此在得到调节系数后，可利用该系数对待校正光源部在各照明模式下对应的原始驱动信号进行校正。可见，由于调节系数的计算并不需要借助特殊的固定工装和光功率测量设备，且照明校正过程也可直接在现有内窥镜***中实现，因此，可有效降低内窥镜照明校正的复杂度。当然，在得到调节系数后，也可以将这一系数保存在内窥镜的存储器中，以使内窥镜与多波长光源再次连接时，由多波长光源自动读取调节系数并对对应的待校正光源部在各照明模式下的驱动信号进行更新，可根据实际应用需求进行设定。
此外，还可以理解的是，在本实施例中，为了简化计算量，在单次校正仅对一个待校正光源部进行处理，而为实现对内窥镜各光源部的校正，在确定当前待校正光源部的调节系数后，可继续在多波长光源中选择下一光源部进入校正处理，直至完成对除参考光源部外的其它光源部的调节系数的计算处理。
在一种可能的情况中，步骤S201具体为：确定多波长光源中的参考光源部以及任一待校正光源部。那么，在利用特征响应比例模型、预设比例标准值及待校正光源部的原始驱动信号确定调节系数之后，还可以包括：
步骤21：确定多波长光源中的下一待校正光源部，并进入利用多个预设驱动信号点亮待校正光源部的步骤，直至所有待校正光源部的调节系数均已确定。
进一步，为确保调节系数可靠有效，可设置有效性检测过程，以检测
调节系数的有效性。本申请实施例并不限定有效性检测的具体过程，例如可在校正调整后，检测待校正内窥镜***与标准内窥镜***在通过相同照明模式点亮相关光源部的情况下所采集的响应图像间的偏差值，并根据该偏差值是否小于预设阈值来确定调节系数是否可靠。
或者，为避免预设阈值设置不当对有效性检测的影响，在本实施例中，所述照明校正方法还可以包括：
步骤31：确定目标照明模式，同时利用目标照明模式下的原始驱动信号点亮多波长光源中的所有光源部，并获取内窥镜对标准对象拍摄的原始响应图像。
步骤32：获取标准内窥镜***在目标照明模式下对标准对象拍摄的标准响应图像，并确定原始响应图像与标准响应图像间的第一偏差值。
应当指出的是，目标照明模式优选为可以同时点亮多波长光源中所有光源部的照明模式。本申请实施例并不限定目标照明模式下各光源部所对应的驱动信号，可根据实际应用需求进行设定。另外，假若多波长光源不具有能够点亮所有光源部的照明模式，则也可利用其所拥有的多个照明模式进行组合，只要能够确保组合后的照明模式可覆盖多波长光源中的所有光源部即可。
步骤33：利用所有调节系数校正其对应的待校正光源部的原始驱动信号，得到目标照明模式下的校正驱动信号；
步骤34：利用目标照明模式下的校正驱动信号点亮多波长光源中的所有光源部，同时获取内窥镜对标准对象拍摄的校正响应图像；
步骤35：确定校正响应图像与标准响应图像间的第二偏差值，并判断第二偏差值是否小于第一偏差值；若是，则进入步骤36；若否，则判定校正失败，并提示失败。
步骤36：若是，则保存所有调节系数。
需要说明的是，标准内窥镜***即为已完成校正的内窥镜***，其可作为评价本内窥镜校正情况的基准。本申请并不限定偏差值计算时所选用的指标，该指标可以包括通道响应比、各色彩空间色彩评估系数等单个或多个指标。若调节系数均验证有效，则将所有调节系数保存在内窥镜的存
储器中，以便多波长光源自动读取。
为便于理解，请参考图3，图3为本申请实施例所提供的一种照明校正控制时序的流程图。
基于上述实施例，本申请可首先确定多波长光源中的参考光源部及待校正光源部，并将参考光源部调整为在指定照明模式下恒定出光，以保证参考光源部的出光量固定不变，便于调整各光源部之间的相对光谱；随后，本申请将采集待校正光源部在不同驱动信号条件下与固定出光的参考光源部实际产生的响应图像数据，并利用预设驱动信号及其响应图像生成特征响应比例模型，通过该特征响应比例模型可建立“待校正光源部独有的图像响应特征和参考光源部独有的图像响应特征的比例”与“待校正光源部的驱动信号”之间的对应关系，进而，利用该特征响应比例模型，可推算出可达成预设比例标准值的目标驱动信号，并基于该目标驱动信号和待校正光源部的、与参考光源的驱动信号对应的原始驱动信号，确定待校正光源部的调节系数，最终，基于该调节系数即可实现对待校正光源部的校正，能够使不同内窥镜出射的照明光的相对光谱达到一致。并且，上述照明校正过程可直接在现有内窥镜***中实现，无需借助特殊的固定工装和光功率测量设备，因此，可有效降低内窥镜照明校正的复杂度。
基于上述实施例，下面对特征响应比例模型的具体构造过程进行详细介绍，在一种可能的情况中，利用预设驱动信号及其对应的响应图像生成特征响应比例模型，可以包括：
S301、利用预设驱动信号及其对应的响应图像的色彩值生成驱动响应模型。
在本申请实施例中，驱动响应模型用于反映待校正光源的驱动信号与图像响应值之间的对应关系。该模型可采用线性拟合、多项式拟合、分段线性拟合等方式进行拟合。由于多项式拟合方法较为常用，因此本申请实施例可利用多项式拟合方法对预设驱动信号及响应图像的色彩值间的关联关系进行拟合，得到驱动响应模型。
需要说明的是，本申请实施例并不限定响应图像所对应的色彩空间，
例如可以为RGB色彩空间(Red红色、Green绿色、Blue蓝色)，也可以为YUV(Y表示明亮度、U表示色彩及V表示饱和度)色彩空间等其他色彩空间，进而上述色彩值可以为RGB色彩，也可以为YUV色彩或其他类型的色彩。下面以具体的例子介绍上述拟合过程。多个预设驱动信号可利用如下序列表示：
[I1 I2 I3…Im]；
[I1 I2 I3…Im]；
其中Ii,i∈[1,m]表示第i个驱动信号。驱动信号对应响应图像的RGB响应值可利用图像响应序列矩阵表示：
其中，Ri、Gi和Bi表示第i幅响应图像对应的RGB值。上述预设驱动信号和响应序列矩阵进行多项式拟合得到的驱动响应模型可表示为：
其中，fR(I)、fG(I)、fB(I)表示R、G、B三个通道的响应函数，P是指多项式的级数、krp、kgp、kbp是各项式的系数，其值通过上述实际测量值拟合确定，其中，kr0、kg0、kb0即为仅采用参考光源部照明时图像感应到的各通道值。
S302、根据参考光源部对应的第一响应特征和待校正光源部对应的第
二响应特征，利用驱动响应模型中的参数生成第一响应特征对应的第一响应函数以及第二响应特征对应的第二响应函数。
在本申请实施例中，第一响应特征为参考光源部所特有的图像响应特征，第二响应特征为待校正光源部所特有的图像响应特征。换句话说，可依照第一响应特征和第二响应特征，显著地区分参考光源部和待校正光源部所产生的响应信号。需要说明的是，本申请实施例并不限定第一响应特征和第二响应特征的类型，例如可以为颜色通道特征或颜色特征，其中颜色通道在RGB色彩空间中即为R、G、B三个颜色通道，颜色则为这些通道混合的结果。由于各通道在驱动响应模型中具有独立的响应函数，因此当第一响应特征和第二响应特征分别对应不同的颜色通道时，可直接从上述模型中抽取对应通道的响应函数作为响应特征对应的特定响应函数。需要说明的是，本申请实施例并不限定选择第一响应特征和第二响应特征的具体方式，例如当上述响应特征为颜色通道特征时，可选择参考光源部和待校正光源部的主要响应通道；当两种主要响应通道相互重叠时，可选择响应次高的通道，以此类推。
在一种可能的情况中，第一响应特征及第二响应特征均对应不同的颜色通道，利用驱动响应模型中的参数生成第一响应特征对应的第一响应函数以及第二响应特征对应的第二响应函数，可以包括：
从驱动响应模型中分别提取第一响应特征的颜色通道对应的第一响应函数，以及第二响应特征的颜色通道对应的第二响应函数。
S303、利用第一响应函数及第二响应函数生成特征响应比例模型。
以参考光源部发出绿光、待校正光源部发出蓝光的情景为例，此时需选择图像蓝绿两通道响应函数相除，得到驱动序列-图像蓝绿通道响应比模型(BG_RATIO，即特征响应比例模型)可表示为：
当然，假若第一响应特征和第二响应特征分别对应其他颜色通道，或是第一响应特征和第二响应特征分别对应不同的颜色特征，则上述特征响应比例模型还可具有其他形式，可根据实际应用需求进行调整。
基于上述实施例，本申请实施例可采用拟合方式确定预设驱动信号及响应图像间的关联关系，进而可利用对应驱动响应模型中的参数构造与第一响应特征对应的第一响应函数以及第二响应特征对应的第二响应函数，并最终可利用第一响应函数和第二响应函数构造特征响应比例模型，以有效拟合待校正光源部在不同驱动信号条件下与参考光源部的实际特征响应比例变化情况。
下面对本申请实施例提供的照明校正装置、电子设备及计算机可读存储介质进行介绍，下文描述的照明校正装置、电子设备及计算机可读存储介质与上文描述的照明校正方法可相互对应参照。
请参考图4，图4为本申请实施例所提供的一种照明校正装置的结构框图，该装置应用于内窥镜***，内窥镜***包括多波长光源和内窥镜，该装置可以包括：
初始化模块401，用于确定多波长光源中的参考光源部以及待校正光源部；
驱动模块402，用于将参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮待校正光源部，并在每次点亮时采集内窥镜对标准对象拍摄的响应图像；
模型生成模块403，用于利用预设驱动信号及其对应的响应图像生成特征响应比例模型；特征响应比例模型用于反映待校正光源部对应的图像响应特征和参考光源部对应的图像响应特征之比与待校正光源部的驱动信号之间的对应关系；
调节系数计算模块404，用于利用特征响应比例模型、预设比例标准值及待校正光源部的、与指定照明模式相对应的原始驱动信号确定调节系数，以利用调节系数校正待校正光源部在各照明模式下的原始驱动信号。
可选地，标准对象为白平衡帽。
可选地，初始化模块401具体用于确定所述多波长光源中的参考光源部以及任一待校正光源部；该装置还可以包括：
遍历模块，用于在调节系数计算模块404利用特征响应比例模型、预设
比例标准值及待校正光源部的、与指定照明模式相对应的原始驱动信号确定调节系数之后，确定多波长光源中的下一待校正光源部，以进入驱动模块402和调节系数计算模块404进行处理，直至所有待校正光源部的调节系数均已确定。
可选地，该装置还可以包括：
原始响应图像采集模块，用于确定目标照明模式，同时利用目标照明模式下的原始驱动信号点亮多波长光源中的所有光源部，并获取内窥镜对标准对象拍摄的原始响应图像；
第一偏差值计算模块，用于获取标准内窥镜***在目标照明模式下对标准对象拍摄的标准响应图像，并确定原始响应图像与标准响应图像间的第一偏差值；
校正模块，用于利用所有调节系数校正其对应的待校正光源部的原始驱动信号，得到目标照明模式下的校正驱动信号；
校正响应图像采集模块，用于利用目标照明模式下的校正驱动信号点亮内窥镜的所有光源部，同时获取内窥镜对标准对象拍摄的校正响应图像；
第二偏差值计算和有效性判断模块，用于确定校正响应图像与标准响应图像间的第二偏差值，并判断第二偏差值是否小于第一偏差值；若是，则保存所有调节系数。
可选地，模型生成模块403，可以包括：
驱动响应模型生成单元，用于利用预设驱动信号及其对应的响应图像的色彩值生成驱动响应模型；
响应函数生成单元，用于利用驱动响应模型中的参数生成第一响应特征对应的第一响应函数以及第二响应特征对应的第二响应函数；
特征响应比例模生成单元，用于根据参考光源部对应的第一响应特征和待校正光源部对应的第二响应特征，利用第一响应函数及第二响应函数生成特征响应比例模型。
可选地，驱动响应模型生成单元，可以包括：
驱动响应模型生成子单元，用于利用多项式拟合方法对预设驱动信号及响应图像的色彩值间的关联关系进行拟合，得到驱动响应模型。
可选地，响应函数生成单元，可以包括：
提取子单元，用于从驱动响应模型中分别提取第一响应特征的颜色通道对应的第一响应函数，以及第二响应特征的颜色通道对应的第二响应函数。
参见图5所示，本申请实施例公开了一种电子设备20，包括处理器21和存储器22；其中，所述存储器22，用于保存计算机程序；所述处理器21，用于在执行所述计算机程序时执行前述实施例公开的照明校正方法。
关于上述照明校正方法的具体过程可以参考前述实施例中公开的相应内容，在此不再进行赘述。
并且，所述存储器22作为资源存储的载体，可以是只读存储器、随机存储器、磁盘或者光盘等，存储方式可以是短暂存储或者永久存储。
另外，所述电子设备20还包括电源23、通信接口24、输入输出接口25和通信总线26；其中，所述电源23用于为所述电子设备20上的各硬件设备提供工作电压；所述通信接口24能够为所述电子设备20创建与外界设备之间的数据传输通道，其所遵循的通信协议是能够适用于本申请技术方案的任意通信协议，在此不对其进行具体限定；所述输入输出接口25，用于获取外界输入数据或向外界输出数据，其具体的接口类型可以根据具体应用需要进行选取，在此不进行具体限定。
进一步的，本申请实施例还公开了一种计算机可读存储介质，用于保存计算机程序，其中，所述计算机程序被处理器执行时实现前述实施例公开的照明校正方法。
关于上述照明校正方法的具体过程可以参考前述实施例中公开的相应内容，在此不再进行赘述。
说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似部分互相参见即可。对于实施例公开的装置而言，由于其与实施例公开的方法相对应，所以描
述的比较简单，相关之处参见方法部分说明即可。
专业人员还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。
以上对本申请所提供的一种照明校正方法、装置、电子设备及计算机可读存储介质进行了详细介绍。本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想。应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以对本申请进行若干改进和修饰，这些改进和修饰也落入本申请权利要求的保护范围内。
Claims (10)
- 一种照明校正方法，应用于内窥镜***，所述内窥镜***包括多波长光源和内窥镜，其特征在于，所述照明校正方法包括：确定所述多波长光源中的参考光源部以及待校正光源部；将所述参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮所述待校正光源部，并在每次点亮时获取所述内窥镜对标准对象拍摄的响应图像；利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型；所述特征响应比例模型用于反映所述待校正光源部对应的图像响应特征和所述参考光源部对应的图像响应特征之比与所述待校正光源部的驱动信号之间的对应关系；利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数，以利用所述调节系数校正所述待校正光源部在各照明模式下的原始驱动信号。
- 根据权利要求1所述的照明校正方法，其特征在于，所述标准对象为白平衡帽。
- 根据权利要求1所述的照明校正方法，其特征在于，所述确定所述多波长光源中的参考光源部以及待校正光源部，包括：确定所述多波长光源中的参考光源部以及任一待校正光源部；则，在利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数之后，所述照明校正方法还包括：确定所述多波长光源中的下一待校正光源部，并进入所述利用多个预设驱动信号点亮所述待校正光源部的步骤，直至所有所述待校正光源部的调节系数均已确定。
- 根据权利要求3所述的照明校正方法，其特征在于，所述照明校正方法还包括：确定目标照明模式，同时利用所述目标照明模式下的原始驱动信号点亮所述多波长光源中的所有光源部，并获取所述内窥镜对所述标准对象拍 摄的原始响应图像；获取标准内窥镜***在所述目标照明模式下对所述标准对象拍摄的标准响应图像，并确定所述原始响应图像与所述标准响应图像间的第一偏差值；利用所有所述调节系数校正其对应的待校正光源部的原始驱动信号，得到目标照明模式下的校正驱动信号；利用所述目标照明模式下的校正驱动信号点亮所述多波长光源中的所有光源部，同时获取所述内窥镜对所述标准对象拍摄的校正响应图像；确定所述校正响应图像与所述标准响应图像间的第二偏差值，并判断所述第二偏差值是否小于第一偏差值；若是，则保存所有所述调节系数。
- 根据权利要求1至4任一项所述的照明校正方法，其特征在于，所述利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型，包括：利用所述预设驱动信号及所述响应图像的色彩值生成驱动响应模型；根据所述参考光源部对应的第一响应特征和所述待校正光源部对应的第二响应特征，利用所述驱动响应模型中的参数生成所述第一响应特征对应的第一响应函数以及所述第二响应特征对应的第二响应函数；利用所述第一响应函数及所述第二响应函数生成所述特征响应比例模型。
- 根据权利要求5所述的照明校正方法，其特征在于，所述利用所述预设驱动信号及所述响应图像的色彩值生成驱动响应模型，包括：利用多项式拟合方法对所述预设驱动信号及所述响应图像的色彩值间的关联关系进行拟合，得到所述驱动响应模型。
- 根据权利要求5所述的照明校正方法，其特征在于，所述第一响应特征及所述第二响应特征均对应不同的颜色通道，所述利用所述驱动响应模型中的参数生成所述第一响应特征对应的第一响应函数以及所述第二响应特征对应的第二响应函数，包括：从所述驱动响应模型中分别提取所述第一响应特征的颜色通道对应的 第一响应函数，以及所述第二响应特征的颜色通道对应的第二响应函数。
- 一种照明校正装置，应用于内窥镜***，所述内窥镜***包括多波长光源和内窥镜，其特征在于，所述照明校正装置包括：初始化模块，用于确定所述多波长光源中的参考光源部以及待校正光源部；驱动模块，用于将所述参考光源部设置为在指定照明模式下恒定出光，同时，利用多个预设驱动信号点亮所述待校正光源部，并在每次点亮时获取所述内窥镜对标准对象拍摄的响应图像；模型生成模块，用于利用所述预设驱动信号及其对应的响应图像生成特征响应比例模型；所述特征响应比例模型用于反映所述待校正光源部对应的图像响应特征和所述参考光源部对应的图像响应特征之比与所述待校正光源部的驱动信号之间的对应关系；调节系数计算模块，用于利用所述特征响应比例模型、预设比例标准值及所述待校正光源部的、与所述指定照明模式相对应的原始驱动信号确定调节系数，以利用所述调节系数校正所述待校正光源部在各照明模式下的原始驱动信号。
- 一种电子设备，其特征在于，包括：存储器，用于存储计算机程序；处理器，用于执行所述计算机程序时实现如权利要求1至7任一项所述的照明校正方法。
- 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机可执行指令，所述计算机可执行指令被处理器加载并执行时，实现如权利要求1至7任一项所述的照明校正方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210762851.4A CN117377173A (zh) | 2022-06-30 | 2022-06-30 | 一种照明校正方法、装置、电子设备及存储介质 |
| CN202210762851.4 | 2022-06-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024002136A1 true WO2024002136A1 (zh) | 2024-01-04 |
Family
ID=89383086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/103091 WO2024002136A1 (zh) | 2022-06-30 | 2023-06-28 | 一种照明校正方法、装置、电子设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117377173A (zh) |
| WO (1) | WO2024002136A1 (zh) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130345517A1 (en) * | 2012-06-20 | 2013-12-26 | Fujifilm Corporation | Light source apparatus and endoscope system |
| WO2018003241A1 (ja) * | 2016-06-27 | 2018-01-04 | ソニー株式会社 | 照明装置、照明装置の制御方法、および撮像システム |
| WO2019003489A1 (ja) * | 2017-06-26 | 2019-01-03 | オリンパス株式会社 | 光源制御装置及び内視鏡システム |
| CN109330547A (zh) * | 2018-09-06 | 2019-02-15 | 苏州新光维医疗科技有限公司 | 光源的调节方法、装置、设备及内窥镜 |
| CN111568352A (zh) * | 2020-04-14 | 2020-08-25 | 广东欧谱曼迪科技有限公司 | 一种光源光谱自动调节的内窥镜***及其光谱调节方法 |
-
2022
- 2022-06-30 CN CN202210762851.4A patent/CN117377173A/zh active Pending
-
2023
- 2023-06-28 WO PCT/CN2023/103091 patent/WO2024002136A1/zh unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130345517A1 (en) * | 2012-06-20 | 2013-12-26 | Fujifilm Corporation | Light source apparatus and endoscope system |
| WO2018003241A1 (ja) * | 2016-06-27 | 2018-01-04 | ソニー株式会社 | 照明装置、照明装置の制御方法、および撮像システム |
| WO2019003489A1 (ja) * | 2017-06-26 | 2019-01-03 | オリンパス株式会社 | 光源制御装置及び内視鏡システム |
| CN109330547A (zh) * | 2018-09-06 | 2019-02-15 | 苏州新光维医疗科技有限公司 | 光源的调节方法、装置、设备及内窥镜 |
| CN111568352A (zh) * | 2020-04-14 | 2020-08-25 | 广东欧谱曼迪科技有限公司 | 一种光源光谱自动调节的内窥镜***及其光谱调节方法 |
Non-Patent Citations (1)
| Title |
|---|
| ERJIANG YE, LIMU HA, KEZERBEK GULIMILA, YIBO ZHANG, XIUBIN ZHANG: "An Intelligent Regulation Algorithm of Endoscopic Illumination", MICROCOMPUTER APPLICATIONS, vol. 28, no. 12, 20 December 2012 (2012-12-20), pages 39 - 41, XP093119332 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117377173A (zh) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4434976B2 (ja) | 画像処理装置、プログラム及び画像処理方法 | |
| US10918270B2 (en) | Endoscope system and evaluation value calculation device | |
| JP2002027491A (ja) | 画像入力装置、ホワイトバランス調整方法、およびその方法を実行するためのプログラムを格納したコンピュータが読取可能な記録媒体 | |
| CN103997945A (zh) | 内窥镜装置和内窥镜的偏光元件的劣化检测方法 | |
| CN114071110B (zh) | 内窥镜色温实时矫正方法、装置、电子设备及摄像*** | |
| US10027874B2 (en) | Imaging device, client device, imaging system, control method of imaging device, control method of client device, and control method of imaging system | |
| JP2013121132A (ja) | 撮像装置及び撮像方法 | |
| US20150062350A1 (en) | Light parameter measurement method and device, screen adjustment method and electronic device | |
| CN111901520B (zh) | 一种基于图像处理的场景自适应***、方法及终端 | |
| CN111110175B (zh) | 一种内窥镜光源及其调光方法、装置和内窥镜*** | |
| CN113920037B (zh) | 一种内窥镜画面矫正方法、装置、矫正***及存储介质 | |
| WO2024002136A1 (zh) | 一种照明校正方法、装置、电子设备及存储介质 | |
| EP1189458A2 (en) | Correction curve generating method, image display unit and storage medium | |
| CN107948619B (zh) | 图像处理方法、装置、计算机可读存储介质和移动终端 | |
| JPH06222287A (ja) | 内視鏡用光源装置 | |
| JP4475874B2 (ja) | 電子内視鏡装置のプロセッサ | |
| KR20090092363A (ko) | 영상 획득 장치 및 방법 | |
| KR100919867B1 (ko) | 영상 처리 방법 및 장치 | |
| US20050030411A1 (en) | Digital still camera and image processing program | |
| JP2005198097A (ja) | 撮像装置及び発光装置及び当該撮像装置における撮像方法と撮像システム、及びそのプログラム | |
| US7728884B2 (en) | Method for white balance adjustment and digital image capturing device using the same | |
| CN109976070A (zh) | 图像投影装置、图像投影装置的控制方法和存储介质 | |
| US10559072B2 (en) | Image detection device and image detection system | |
| KR20120012632A (ko) | 카메라 모듈, 그의 렌즈 쉐이딩 보정 방법 및 그를 포함하는 장치 | |
| JP2003102019A (ja) | ホワイトバランス調整装置およびカメラシステム |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23830311 Country of ref document: EP Kind code of ref document: A1 |