WO2022110712A1 - 图像增强方法、装置、电子设备及计算机可读存储介质 - Google Patents

图像增强方法、装置、电子设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2022110712A1
WO2022110712A1 PCT/CN2021/096528 CN2021096528W WO2022110712A1 WO 2022110712 A1 WO2022110712 A1 WO 2022110712A1 CN 2021096528 W CN2021096528 W CN 2021096528W WO 2022110712 A1 WO2022110712 A1 WO 2022110712A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
pixel
image set
processed
color space
Prior art date
Application number
PCT/CN2021/096528
Other languages
English (en)
French (fr)
Inventor
郭冰雪
初晓
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2022110712A1 publication Critical patent/WO2022110712A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/04Context-preserving transformations, e.g. by using an importance map
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10024Color image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20024Filtering details

Definitions

  • the present application relates to the technical field of image processing, and in particular, to an image enhancement method, apparatus, electronic device, and computer-readable storage medium.
  • the inventor realizes that most of the current methods for image enhancement are to use a neural network to perform feature extraction on the image, and to perform operations such as labeling the extracted features to achieve image enhancement.
  • the features extracted by the neural network are inaccurate, and the accuracy of image enhancement by using the extracted features for labeling and other operations is not high. Therefore, how to improve the accuracy of image enhancement? has become an urgent problem to be solved.
  • An image enhancement method comprising:
  • Color space conversion is performed on the updated image to obtain an enhanced image.
  • An image enhancement device includes:
  • a space conversion module for acquiring an original image, performing color space conversion on the original image to obtain an initial image
  • an image dyeing module configured to dye the initial image by using one or more preset dyeing methods to obtain a standard image set
  • a detail enhancement processing module configured to perform detail enhancement processing on the standard image set to obtain a to-be-processed image set
  • a parameter extraction module configured to perform parameter extraction on the to-be-processed image set to obtain numerical parameters of each to-be-processed image in the to-be-processed image set;
  • a parameter updating module configured to perform parameter updating on the initial image according to the numerical parameters to obtain an updated image
  • the space conversion module is used for performing color space conversion on the updated image to obtain an enhanced image.
  • An electronic device comprising:
  • a processor that executes the instructions stored in the memory to achieve the following steps:
  • Color space conversion is performed on the updated image to obtain an enhanced image.
  • a computer-readable storage medium having at least one instruction stored in the computer-readable storage medium, the at least one instruction being executed by a processor in an electronic device to implement the following steps:
  • Color space conversion is performed on the updated image to obtain an enhanced image.
  • the present application can solve the problem that the accuracy of image enhancement is not high.
  • FIG. 1 is a schematic flowchart of an image enhancement method provided by an embodiment of the present application
  • FIG. 2 is a functional block diagram of an image enhancement apparatus provided by an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of an electronic device implementing the image enhancement method according to an embodiment of the present application.
  • the embodiments of the present application provide an image enhancement method.
  • the execution subject of the image enhancement method includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal.
  • the image enhancement method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
  • the image enhancement method includes:
  • the original image may be any color image, and due to the limitation of display devices with image display functions such as a computer, the original image is generally an image in the RGB color space or an image in the CMYK color space.
  • the present application implements that the original image can be obtained from a pre-built blockchain node by using a python statement with a data capture function, and the efficiency of obtaining the original image can be improved by utilizing the high data ingestion of the blockchain node.
  • performing color space conversion on the original image to obtain an initial image includes:
  • the three components of the intermediate value are normalized to obtain the normalized three components
  • the corrected three-component is input into the target color space to obtain an initial image.
  • the original color space parameter, the absolute color parameter, and the target color parameter can be obtained from the underlying data of different color spaces by using a python statement with a data capture function.
  • the original color space parameter is a specific parameter that defines the color range in the color space where the original image is located, and the original color space includes but is not limited to the RGB color space, the CMYK color space, and the color displayed in the original color space.
  • the range will change with the change of the display device;
  • the absolute color parameter is a specific parameter that defines the color range of the absolute color space, and the absolute color space includes but is not limited to the sRGB color space, the Adobe RGB color space, and the absolute color space is a display The color range does not change with the display device.
  • the target color space includes the LAB color space, and the target color parameters are specific parameters that define the color range in the target color space.
  • the color range displayed in the target color space will not change with the change of the display device, and because the target color space
  • the color range shown in is suitable for human vision and is more conducive to displaying image details.
  • the original image It is not possible to convert directly from the original color space to the target color space. It is necessary to convert the original image in the original color space into the absolute color space first, and then convert the original image to the target color space through the absolute color space.
  • the original color space of the original image is RGB color space
  • the target color space is LAB color space.
  • the original image needs to be converted from RGB color space to sRGB color space first. (ie absolute color space), and then convert the original image to LAB color space through sRGB color space.
  • the embodiment of the present application traverses the original image, obtains the three-component color of each pixel in the original image, and uses a linear transformation function to perform intermediate value transformation on the three-color color component according to the absolute color parameter, to obtain the three-component intermediate value,
  • the linear transformation function is as follows:
  • the three intermediate value components x, y, and z are respectively used to represent the three color components of any pixel of the image in the absolute color space.
  • This embodiment of the present application converts the color space of the original image from the original color space to the absolute color space through the above steps.
  • the normalized three components are obtained by normalizing the intermediate value three components, including:
  • F x , F y , and F z are the three normalized components
  • x, y, and z are the three intermediate value components
  • ⁇ , ⁇ , and ⁇ are preset normalization coefficients.
  • the normalization coefficients ⁇ , ⁇ , and ⁇ generally take the values of
  • performing numerical correction on the normalized three-component according to the target color parameter to obtain the three-component correction for each pixel in the original image includes:
  • the normalized three components are numerically corrected using the following numerical correction algorithm:
  • L, a, b are the three normalized components of each pixel in the original image
  • F x , F y , and F z are the three normalized components
  • is a preset correction parameter
  • c is a preset constant coefficient
  • the color space conversion is performed on the original image, which realizes the conversion of the original image from the original color space to the target color space, and the use of the target color space can better display the detailed characteristics of the image, which is conducive to the subsequent accurate image analysis. Details are enhanced.
  • the initial image is dyed by using one or more preset dyeing methods to obtain a standard image set, including:
  • one or more color parameters are acquired from a pre-built database by using a python statement with a data capture function.
  • the color parameter is a parameter used to uniquely identify different colors
  • the color parameter is a dynamic floating-point value
  • the target pixel can be converted into a preset color range according to the pixel value of the target pixel.
  • the color parameter of red is r
  • the color range of red is (qp)
  • the pixel value of the target pixel is k
  • k is not within the range of (qp)
  • the color parameter r is used to linearly adjust the pixel value of the target pixel , so that the pixel value of the target pixel falls within the (qp) range.
  • various color parameters are used to linearly adjust the pixel value of each pixel in the initial image to obtain images of various colors, which are collected into a standard image set.
  • the embodiments of the present application use different dyeing methods to dye the initial image, so that the image details in the initial image can be highlighted in different colors, which is beneficial to improve the accuracy of subsequent image enhancement of the details in the image.
  • the detail enhancement processing is performed on the standard image set to obtain the to-be-processed image set, including:
  • the pixel filter includes but is not limited to a maximum value filter, a minimum value filter and a median filter, and the pixel points in the standard image set are used to perform pixel filtering processing, The filtering of noise pixels in the standard image set can be realized.
  • performing local texture deepening on the filtered image set to obtain an image set to be processed including:
  • center pixel of each said image area and the neighborhood pixel of said center pixel use a preset algorithm to calculate the binary symbol of the center pixel of each said image area;
  • Pixel enhancement is performed on the central pixel according to the binary symbol to obtain an image set to be processed.
  • a preset algorithm to calculate the binary symbol of the center pixel of each of the image areas, including:
  • P 0 is the central pixel of the image area
  • P e is the mean value of the neighboring pixels of the central pixel
  • n is the number of the neighboring pixels
  • s(P 0 ⁇ P e ) is the quantization operation.
  • the embodiment of the present application performs detail enhancement processing on the standard image set, filters the noise pixels in the standard image set, and deepens the local texture of the image details, which highlights the detail features in the image, which is beneficial to improve the accuracy of image enhancement. Spend.
  • the numerical parameters include the mean brightness, brightness variance, red channel mean, red channel variance, blue channel mean, and blue channel variance of each to-be-processed image in the to-be-processed image set.
  • performing parameter extraction on the to-be-processed image set to obtain the numerical parameters of each to-be-processed image in the to-be-processed image set includes:
  • the separately calculating the brightness mean and brightness variance of each to-be-processed image in the to-be-processed image set includes:
  • L Avg is the luminance mean value
  • L Var is the luminance variance
  • U is the number of pixels included in the U-th to-be-processed image in the to-be-processed image set
  • S v is the U-th to-be-processed image The luminance component of the vth pixel in .
  • the steps of calculating the red channel mean value, red channel variance, blue channel mean value and blue channel variance of each to-be-processed image in the to-be-processed image set respectively are the same as calculating the brightness mean and brightness variance of each to-be-processed image in the to-be-processed image set
  • the steps are the same and will not be repeated here.
  • the parameter update of the initial image according to the numerical parameter to obtain an updated image includes:
  • the pixels in the initial image are assigned values using the update parameters to obtain an updated image.
  • the update parameters include brightness update parameters, red update parameters and blue update parameters.
  • the brightness update parameter of the initial image is obtained by calculating the following numerical formula:
  • I k is the brightness update parameter of the kth pixel in the initial image
  • ⁇ target is the brightness variance in the numerical parameter
  • ⁇ source is the brightness variance in the initial image
  • Z k is the initial image
  • the pixel value of the kth pixel in , mean(source) is the mean value of brightness in the initial image
  • mean(target) is the mean value of brightness in the numerical parameter.
  • the steps of calculating the red update parameter and the blue update parameter are the same as the steps of calculating the brightness update parameter, which will not be repeated here.
  • the updated image can be obtained by assigning the three components of each pixel in the initial image by using the update parameter.
  • the performing color space conversion on the updated image includes: converting the color space of the updated image from the target color space to the original color space of the original image.
  • the step of performing color space conversion on the updated image is the same as the step of performing color space conversion on the original image in S1, and will not be repeated here.
  • the enhanced image is obtained by converting the color space of the updated image to the color space of the original image.
  • the embodiment of the present application realizes the conversion of the original image from the original color space to the target color space by performing image conversion on the acquired original image, and the use of the target color space can better display the image details, which is conducive to the subsequent accurate image details.
  • Perform enhancement use different dyeing methods to dye the initial image, and perform detail enhancement processing on the dyed image to obtain an image set to be processed, which can highlight the image details in the initial image under different colors, and highlight the details in the image.
  • feature which is beneficial to improve the accuracy of image enhancement; extract parameters from the image set to be processed, update the initial image with the results of the parameter extraction, and convert the updated image back to the original color space, which realizes the transformation of the image to be processed.
  • the detailed features in the original image are digitized, and the image details in the initial image are accurately updated according to the parameter extraction results. Therefore, the image enhancement method proposed in this application can solve the problem of low accuracy of image enhancement.
  • FIG. 2 it is a functional block diagram of an image enhancement apparatus provided by an embodiment of the present application.
  • the image enhancement apparatus 100 described in this application may be installed in an electronic device. According to the implemented functions, the image enhancement apparatus 100 may include a spatial transformation module 101 , an image coloring module 102 , a detail enhancement processing module 103 , a parameter extraction module 104 , a parameter updating module 105 and a spatial transformation module 106 .
  • the modules described in this application may also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device and can perform fixed functions, and are stored in the memory of the electronic device.
  • each module/unit is as follows:
  • the space conversion module 101 is used to obtain an original image, and perform color space conversion on the original image to obtain an initial image; in the embodiment of the present application, the original image can be any color image, and because a computer or the like has an image display Due to the limitations of the functional display device, the original image is generally an image in the RGB color space or an image in the CMYK color space.
  • the present application implements that the original image can be obtained from a pre-built blockchain node by using a python statement with a data capture function, and the efficiency of obtaining the original image can be improved by utilizing the high data ingestion of the blockchain node.
  • the space conversion module 101 is specifically used for:
  • the three components of the intermediate value are normalized to obtain the normalized three components
  • the corrected three-component is input into the target color space to obtain an initial image.
  • the original color space parameter, the absolute color parameter, and the target color parameter can be obtained from the underlying data of different color spaces by using a python statement with a data capture function.
  • the original color space parameter is a specific parameter that defines the color range in the color space where the original image is located, and the original color space includes but is not limited to the RGB color space, the CMYK color space, and the color displayed in the original color space.
  • the range will change with the change of the display device;
  • the absolute color parameter is a specific parameter that defines the color range of the absolute color space, and the absolute color space includes but is not limited to the sRGB color space, the Adobe RGB color space, and the absolute color space is a display The color range does not change with the display device.
  • the target color space includes the LAB color space, and the target color parameters are specific parameters that define the color range in the target color space.
  • the color range displayed in the target color space will not change with the change of the display device, and because the target color space
  • the color range shown in is suitable for human vision and is more conducive to displaying image details.
  • the original image It is not possible to convert directly from the original color space to the target color space. It is necessary to convert the original image in the original color space into the absolute color space first, and then convert the original image to the target color space through the absolute color space.
  • the original color space of the original image is RGB color space
  • the target color space is LAB color space.
  • the original image needs to be converted from RGB color space to sRGB color space first. (ie absolute color space), and then convert the original image to LAB color space through sRGB color space.
  • the embodiment of the present application traverses the original image, obtains the three-component color of each pixel in the original image, and uses a linear transformation function to perform intermediate value transformation on the three-color color component according to the absolute color parameter, to obtain the three-component intermediate value,
  • the linear transformation function is as follows:
  • the three intermediate value components x, y, and z are respectively used to represent the three color components of any pixel of the image in the absolute color space.
  • This embodiment of the present application converts the color space of the original image from the original color space to the absolute color space through the above steps.
  • the normalized three components are obtained by normalizing the intermediate value three components, including:
  • F x , F y , and F z are the three normalized components
  • x, y, and z are the three intermediate value components
  • ⁇ , ⁇ , and ⁇ are preset normalization coefficients.
  • the normalization coefficients ⁇ , ⁇ , and ⁇ generally take the values of
  • performing numerical correction on the normalized three-component according to the target color parameter to obtain the three-component correction for each pixel in the original image includes:
  • the normalized three components are numerically corrected using the following numerical correction algorithm:
  • L, a, and b are the three normalized components of each pixel in the original image
  • F x , F y , and F z are the three normalized components
  • is a preset correction parameter
  • C is a preset constant coefficient
  • the color space conversion is performed on the original image, which realizes the conversion of the original image from the original color space to the target color space, and the use of the target color space can better display the detailed characteristics of the image, which is conducive to the subsequent accurate image analysis. Details are enhanced.
  • the image dyeing module 102 is configured to dye the initial image by using one or more preset dyeing methods to obtain a standard image set.
  • the image coloring module 102 is specifically used for:
  • one or more color parameters are acquired from a pre-built database by using a python statement with a data capture function.
  • the color parameter is a parameter used to uniquely identify different colors
  • the color parameter is a dynamic floating point value
  • the target pixel can be converted into a preset color range according to the pixel value of the target pixel.
  • the color parameter of red is r
  • the color range of red is (qp)
  • the pixel value of the target pixel is k
  • k is not in the range of (qp)
  • the color parameter r is used to linearly adjust the pixel value of the target pixel , so that the pixel value of the target pixel falls within the (qp) range.
  • various color parameters are used to linearly adjust the pixel value of each pixel in the initial image to obtain images of various colors, which are collected into a standard image set.
  • the embodiments of the present application use different dyeing methods to dye the initial image, so that the image details in the initial image can be highlighted in different colors, which is beneficial to improve the accuracy of subsequent image enhancement of the details in the image.
  • the detail enhancement processing module 103 is configured to perform detail enhancement processing on the standard image set to obtain a to-be-processed image set.
  • the detail enhancement processing module 103 is specifically used for:
  • the pixel filter includes, but is not limited to, a maximum value filter, a minimum value filter, and a median filter, and the pixel filter is used to perform pixel filtering processing on the pixels in the standard image set, The filtering of noise pixels in the standard image set can be realized.
  • performing local texture deepening on the filtered image set to obtain an image set to be processed including:
  • Pixel enhancement is performed on the central pixel according to the binary symbol to obtain an image set to be processed.
  • a preset algorithm to calculate the binary symbol of the center pixel of each of the image areas, including:
  • P 0 is the central pixel of the image area
  • P e is the mean value of the neighboring pixels of the central pixel
  • n is the number of the neighboring pixels
  • s(P 0 ⁇ P e ) is the quantization operation.
  • the embodiment of the present application performs detail enhancement processing on the standard image set, filters the noise pixels in the standard image set, and deepens the local texture of the image details, which highlights the detail features in the image, which is beneficial to improve the accuracy of image enhancement. Spend.
  • the parameter extraction module 104 is configured to perform parameter extraction on the to-be-processed image set to obtain numerical parameters of each to-be-processed image in the to-be-processed image set.
  • the numerical parameters include the mean brightness, brightness variance, red channel mean, red channel variance, blue channel mean, and blue channel variance of each to-be-processed image in the to-be-processed image set.
  • the parameter extraction module 104 is specifically used for:
  • the separately calculating the brightness mean and brightness variance of each to-be-processed image in the to-be-processed image set includes:
  • L Avg is the luminance mean value
  • L Var is the luminance variance
  • U is the number of pixels included in the U-th to-be-processed image in the to-be-processed image set
  • S v is the U-th to-be-processed image The luminance component of the vth pixel in .
  • the steps of separately calculating the red channel mean value, red channel variance, blue channel mean value and blue channel variance of each to-be-processed image in the to-be-processed image set are the same as calculating the brightness mean and brightness variance of each to-be-processed image in the to-be-processed image set
  • the steps are the same and will not be repeated here.
  • the parameter updating module 105 is configured to update the parameters of the initial image according to the numerical parameters to obtain an updated image.
  • the parameter update module 105 is specifically used for:
  • the pixels in the initial image are assigned values using the update parameters to obtain an updated image.
  • the update parameters include brightness update parameters, red update parameters and blue update parameters.
  • the brightness update parameter of the initial image is obtained by calculating the following numerical formula:
  • I k is the brightness update parameter of the kth pixel in the initial image
  • ⁇ target is the brightness variance in the numerical parameter
  • ⁇ source is the brightness variance in the initial image
  • Z k is the initial image
  • the pixel value of the kth pixel in , mean(source) is the mean value of brightness in the initial image
  • mean(target) is the mean value of brightness in the numerical parameter.
  • the steps of calculating the red update parameter and the blue update parameter are the same as the steps of calculating the brightness update parameter, which will not be repeated here.
  • the updated image can be obtained by assigning the three components of each pixel in the initial image by using the update parameter.
  • the space conversion module 106 is configured to perform color space conversion on the updated image to obtain an enhanced image.
  • the performing color space conversion on the updated image includes: converting the color space of the updated image from the target color space to the original color space of the original image.
  • the step of performing color space conversion on the updated image is consistent with the step of performing color space conversion on the original image by the space conversion module 101, and details are not described herein.
  • the enhanced image is obtained by converting the color space of the updated image to the color space of the original image.
  • the embodiment of the present application realizes the conversion of the original image from the original color space to the target color space by performing image conversion on the obtained original image, and the use of the target color space can better display the image details, which is conducive to the subsequent accurate image details.
  • Perform enhancement use different dyeing methods to dye the initial image, and perform detail enhancement processing on the dyed image to obtain a to-be-processed image set, which can highlight the image details in the initial image under different colors, and highlight the details in the image.
  • feature which is beneficial to improve the accuracy of image enhancement; extract the parameters of the image set to be processed, update the initial image with the results of the parameter extraction, and convert the updated image back to the original color space, which realizes the transformation of the image to be processed.
  • the detailed features in the original image are digitized, and the image details in the initial image are accurately updated according to the parameter extraction results. Therefore, the image enhancement device proposed in the present application can solve the problem that the accuracy of image enhancement is not high.
  • FIG. 3 it is a schematic structural diagram of an electronic device for implementing an image enhancement method provided by an embodiment of the present application.
  • the electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an image enhancement program 12.
  • the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc.
  • the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 .
  • the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash memory card (Flash Card), etc.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 can not only be used to store application software installed in the electronic device 1 and various types of data, such as the code of the image enhancement program 12, etc., but also can be used to temporarily store data that has been output or will be output.
  • the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits.
  • Central Processing Unit CPU
  • microprocessor digital processing chip
  • graphics processor and combination of various control chips, etc.
  • the processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing programs or modules (such as images) stored in the memory 11. Enhanced programs, etc.), and call data stored in the memory 11 to perform various functions of the electronic device 1 and process data.
  • the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like.
  • PCI peripheral component interconnect
  • EISA Extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.
  • FIG. 3 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 3 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the figure. components, or a combination of certain components, or a different arrangement of components.
  • the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management
  • the device implements functions such as charge management, discharge management, and power consumption management.
  • the power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
  • the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • a network interface optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
  • the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
  • the image enhancement program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, it can realize:
  • Color space conversion is performed on the updated image to obtain an enhanced image.
  • the modules/units integrated in the electronic device 1 may be stored in a computer-readable storage medium.
  • the computer-readable storage medium may be volatile or non-volatile.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only). Memory).
  • the present application also provides a computer-readable storage medium, where the readable storage medium stores a computer program, and when executed by a processor of an electronic device, the computer program can realize:
  • Color space conversion is performed on the updated image to obtain an enhanced image.
  • modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.
  • the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

一种图像增强方法,包括:获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像(S1);利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集(S2);对所述标准图像集进行细节加强处理,得到待处理图像集(S3);对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量(S4);根据所述数值参量对所述初始图像进行参数更新,得到更新图像(S5);对所述更新图像进行色彩空间转回,得到增强图像(S6)。此外,还涉及区块链技术,所述原始图像可存储于区块链的节点。一种图像增强装置、电子设备以及计算机可读存储介质。该方法可以解决对图像进行图像增强的精确度不高的问题。

Description

图像增强方法、装置、电子设备及计算机可读存储介质
本申请要求于2020年11月30日提交中国专利局、申请号为CN202011374000.X,发明名称为“图像增强方法、装置、电子设备及计算机可读存储介质”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。
技术领域
本申请涉及图像处理技术领域,尤其涉及一种图像增强方法、装置、电子设备及计算机可读存储介质。
背景技术
随着计算机视觉的发展,越来越多的场合对图像进行分析处理以实现从图像中获取需要的信息。例如,在医疗领域,人们通过图像处理模型对医疗图像进行观测、分析,从医疗图像中检测出病灶的信息。但输入至图像处理模型中的图像中往往存在着模糊的情况,导致图像处理模型无法准确地从图像中获取准确的信息,因此需要对图像进行图像增强。
发明人意识到目前对图像进行图像增强的方法多为利用神经网络对图像进行特征提取,对提取到的特征进行标注等操作以实现图像增强。但由于图像本身的模糊导致神经网络提取到的特征并不准确,进而造成利用提取到的特征进行标注等操作来实现图像增强的精确度不高,因此,如何提高对图像进行图像增强的精确度成为了亟待解决的问题。
发明内容
一种图像增强方法,包括:
获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
对所述标准图像集进行细节加强处理,得到待处理图像集;
对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
对所述更新图像进行色彩空间转回,得到增强图像。
一种图像增强装置,所述装置包括:
空间转换模块,用于获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
图像染色模块,用于利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
细节加强处理模块,用于对所述标准图像集进行细节加强处理,得到待处理图像集;
参量提取模块,用于对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
参数更新模块,用于根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
空间转回模块,用于对所述更新图像进行色彩空间转回,得到增强图像。
一种电子设备,所述电子设备包括:
存储器,存储至少一个指令;及
处理器,执行所述存储器中存储的指令以实现如下步骤:
获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
对所述标准图像集进行细节加强处理,得到待处理图像集;
对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参 量;
根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
对所述更新图像进行色彩空间转回,得到增强图像。
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至少一个指令,所述至少一个指令被电子设备中的处理器执行以实现如下步骤:
获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
对所述标准图像集进行细节加强处理,得到待处理图像集;
对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
对所述更新图像进行色彩空间转回,得到增强图像。
本申请可以解决对图像进行图像增强的精确度不高的问题。
附图说明
图1为本申请一实施例提供的图像增强方法的流程示意图;
图2为本申请一实施例提供的图像增强装置的功能模块图;
图3为本申请一实施例提供的实现所述图像增强方法的电子设备的结构示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供一种图像增强方法。所述图像增强方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述图像增强方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
参照图1所示,为本申请一实施例提供的图像增强方法的流程示意图。在本实施例中,所述图像增强方法包括:
S1、获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像。
本申请实施例中,所述原始图像可以为任何彩色图像,且由于计算机等具有图像显示功能的显示设备的限制,所述原始图像一般为RGB色彩空间的图像或为CMYK色彩空间的图像。
本申请实施了可利用具有数据抓取功能的python语句从预先构建的区块链节点中获取所述原始图像,利用区块链节点对数据的高吞天性,可提高获取原始图像的效率。
详细地,所述对所述原始图像进行色彩空间转换,得到初始图像,包括:
获取原始图像的原始色彩空间参数;
根据所述原始色彩空间参数遍历并获取所述原始图像中各像素点的颜色三分量;
根据绝对色彩空间的绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量;
将所述中间值三分量进行归一化处理,得到归一化三分量;
根据目标色彩空间的目标色彩参数对所述归一化三分量进行数值校正,得到所述原始图像中各像素点校正三分量;
将所述校正三分量输入至所述目标色彩空间,得到初始图像。
本申请实施例可利用具有数据抓取功能的python语句从不同颜色空间的底层数据中获取所述原始色彩空间参数、所述绝对色彩参数和所述目标色彩参数。
详细地,所述原始色彩空间参数是所述原始图像所在的色彩空间中定义颜色范围的特定参数,所述原始色彩空间包括但不限于RGB色彩空间、CMYK色彩空间,原始色彩空间中显示的色彩范围会随着显示设备的变动而变动;所述绝对色彩参数是绝对色彩空间定义颜色范围的特定参数,所述绝对色彩空间包括但不限于sRGB色彩空间、Adobe RGB色彩空间,绝对色彩空间是显示的色彩范围不会随着显示设备的变动而变动。
所述目标色彩空间包括LAB色彩空间,所述目标色彩参数是目标色彩空间中定义颜色范围的特定参数,目标色彩空间中显示的颜色范围不会随显示设备的变动而变动,且由于目标色彩空间中显示的颜色范围适用于人类视觉,更有利于显示图像细节特征。
由于所述原始图像所在的原始色彩空间中显示的色彩范围会随着显示设备的变动而变动,但标色彩空间中显示的颜色范围不会随显示设备的变动而变动,因此,所述原始图像无法直接从原始色彩空间转化至所述目标色彩空间,需要先将原始色彩空间中的原始图像转化至绝对色彩空间中,通过绝对色彩空间将所述原始图像转化至所述目标色彩空间。
例如,原始图像的原始色彩空间为RGB色彩空间,目标色彩空间为LAB色彩空间,在将原始图像从RGB色彩空间转换至LAB色彩空间时,需要先将原始图像从RGB色彩空间转换至sRGB色彩空间(即绝对色彩空间),再通过sRGB色彩空间将原始图像转换至LAB色彩空间。
本申请实施例遍历所述原始图像,获取所述原始图像中各像素点的颜色三分量,并利用线性变换函数根据绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量,其中,所述线性变换函数如下:
Figure PCTCN2021096528-appb-000001
y=α*R+β*G+γ*B
z=δ*R+ε*G+θ*B
其中,x、y、z为所述中间值三分量;R、G、B为原始图像中任一像素点的颜色三分量,C、
Figure PCTCN2021096528-appb-000002
∪、α、β、γ、δ、ε、θ为预设转化系数。
详细地,所述中间值三分量x、y、z分别用于表示绝对色彩空间中图像的任一像素点的颜色三分量。
本申请实施例通过上述步骤将原始图像的色彩空间由原始色彩空间转化为绝对色彩空间。
进一步地,所述将所述中间值三分量进行归一化处理得到归一化三分量,包括:
利用如下归一化算法将所述中间值三分量进行归一化处理:
F x=ρ*x
F y=σ*y
F z=τ*z
其中,F x、F y、F z为所述归一化三分量,x、y、z为所述中间值三分量,ρ、σ、τ为预设的归一化系数。
详细地,所述归一化系数ρ、σ、τ一般取值为
Figure PCTCN2021096528-appb-000003
本申请实施例中,所述根据所述目标色彩参数对所述归一化三分量进行数值校正得到所述原始图像中各像素点校正三分量,包括:
利用如下数值校正算法对所述归一化三分量进行数值校正:
Figure PCTCN2021096528-appb-000004
a=ω*(F x-F y)
Figure PCTCN2021096528-appb-000005
其中,L、a、b为所述原始图像中各像素点校正三分量,F x、F y、F z为所述归一化三分 量,
Figure PCTCN2021096528-appb-000006
ω、
Figure PCTCN2021096528-appb-000007
为预设的校正参数,c为预设常数系数。
本申请实施例中对所述原始图像进行色彩空间转换,实现了将原始图像从原始色彩空间转换至目标色彩空间,利用目标色彩空间可更好的显示图像细节特征,有利于后续精准地对图像细节进行增强。
S2、利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集。
本申请实施例中,所述利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集,包括:
获取一种或者多种颜色参数;
遍历并获取所述初始图像中各像素点的像素值;
分别根据所述一种或者多种颜色参数对所述像素值进行线性调整,得到标准图像集。
本申请实施例利用具有数据抓取功能的python语句从预先构建的数据库中获取一种或者多种颜色参数。
详细地,所述颜色参数是用于唯一标识不同色彩的参数,所述颜色参数为动态浮点数值,可根据目标像素的像素值将目标像素转化至预设的颜色范围内。
例如,红色的颜色参数为r,红色的颜色范围为(qp),存在目标像素的像素值为k,且k不在(qp)范围内,则利用颜色参数r对目标像素的像素值进行线性调整,使得所述目标像素的像素值落入(qp)范围内。
本申请实施例中,分别利用多种颜色参数对初始图像中各像素点的像素值进行线性调整,得到多种不同颜色的图像,并汇集为标准图像集。
本申请实施例利用不同染色方式对初始图像进行染色,可实现在不同颜色下突出初始图像中的图像细节,有利于提高后续对图像中细节进行图像增强的精确度。
S3、对所述标准图像集进行细节加强处理,得到待处理图像集。
本申请实施例中,所述对所述标准图像集进行细节加强处理,得到待处理图像集,包括:
遍历并获取所述标准图像集的像素点;
利用预设的像素滤波器对所述像素点进行像素滤波处理,得到滤波图像集;
对所述滤波图像集进行局部纹理加深,得到待处理图像集。
本申请实施例中,所述像素滤波器包括但不限于最大值滤波器、最小值滤波器和中值滤波器,利用所述像素滤波器将所述标准图像集中的像素点进行像素滤波处理,可实现对所述标准图像集中噪声像素点的过滤。
进一步地,所述对所述滤波图像集进行局部纹理加深,得到待处理图像集,包括:
利用n×n的图像窗口在所述滤波图像集中依次执行区域选择,得到多个图像区域;
根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元;
根据所述二进制码元对所述中心像素进行像素增强,得到待处理图像集。
可选地,所述根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元,包括:
利用如下算法计算所述图像区域的中心像素的二进制码元
Figure PCTCN2021096528-appb-000008
Figure PCTCN2021096528-appb-000009
其中,P 0为所述图像区域的中心像素,P e为所述中心像素的邻域像素的均值,n为所述邻域像素的个数,s(P 0-P e)为量化运算。
本申请实施例对标准图像集进行细节加强处理,将标准图像集中噪声像素点进行过滤,并对图像细节进行局部纹理加深,突出了图像中的细节特征,有利于提高对图像进行图像 增强的精确度。
S4、对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量。
本申请实施例中,所述数值参量包括待处理图像集中各待处理图像的亮度均值、亮度方差、红色通道均值、红色通道方差、蓝色通道均值和蓝色通道方差。
本申请实施例中,所述对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量包括:
计算所述待处理图像集中各待处理图像的亮度均值和亮度方差;
计算所述待处理图像集中各待处理图像的红色通道均值和红色通道方差;
计算所述待处理图像集中各待处理图像的蓝色通道均值和蓝色通道方差。
详细地,所述分别计算所述待处理图像集中各待处理图像的亮度均值和亮度方差,包括:
利用如下公式分别计算所述待处理图像集中各待处理图像的亮度均值和亮度方差:
Figure PCTCN2021096528-appb-000010
Figure PCTCN2021096528-appb-000011
其中,L Avg为所述亮度均值,L Var为所述亮度方差,U为所述所述待处理图像集中第U张待处理图像包含的像素数量,S v为所述第U张待处理图像中第v个像素点的亮度分量。
具体地,分别计算待处理图像集中各待处理图像的红色通道均值、红色通道方差、蓝色通道均值和蓝色通道方差的步骤,与计算待处理图像集中各待处理图像的亮度均值和亮度方差的步骤一致,在此不做赘述。
S5、根据所述数值参量对所述初始图像进行参数更新,得到更新图像。
本申请实施例中,所述根据所述数值参量对所述初始图像进行参数更新,得到更新图像,包括:
利用数值公式对所述数值参量进行计算,得到所述初始图像的更新参数;
利用所述更新参数对所述初始图像中的像素点进行赋值,得到更新图像。
详细地,所述更新参数包括亮度更新参数,红色更新参数和蓝色更新参数。
例如,利用如下数值公式计算得到所述初始图像的亮度更新参数:
Figure PCTCN2021096528-appb-000012
其中,I k为所述初始图像中第k个像素的亮度更新参数,σ target为所述数值参量中的亮度方差,σ source为所述初始图像中的亮度方差,Z k为所述初始图像中第k个像素的像素值,mean(source)为所述初始图像中的亮度均值,mean(target)为所述数值参量中的亮度均值。
具体地,计算所述红色更新参数和所述蓝色更新参数的步骤与计算所述亮度更新参数的步骤一致,在此不做赘述。
当计算完成得到初始图像中每个像素点的更新参数后,利用所述更新参数对初始图像中每个像素点的三分量进行赋值,即可得到更新图像。
S6、对所述更新图像进行色彩空间转回,得到增强图像。
本申请实施例中,所述对所述更新图像进行色彩空间转回,包括:将所述更新图像的色彩空间由所述目标色彩空间转换至原始图像的原始色彩空间。
所述对所述更新图像进行色彩空间转回的步骤与S1中对所述原始图像进行色彩空间转换的步骤一致,在此不做赘述。
将更新图像的色彩空间转换至原始图像的色彩空间后,得到增强图像。
本申请实施例通过对获取的原始图像进行图像转换,实现了将原始图像从原始色彩空间转换至目标色彩空间,利用目标色彩空间可更好的显示图像细节特征,有利于后续精准地对图像细节进行增强;利用不同染色方式对所述初始图像进行染色,对染色后的图像进行细节加强处理得到待处理图像集,可实现在不同颜色下突出初始图像中的图像细节,突出了图像中的细节特征,有利于提高对图像进行图像增强的精确度;对待处理图像集进行参量提取,利用参量提取结果对初始图像进行更新,并将更新后的图像转换回原始色彩空间,实现了将待处理图像中的细节特征数值化,并根据参量提取结果精确的对初始图像中的图像细节进行更新。因此本申请提出的图像增强方法,可以解决对图像进行图像增强的精确度不高的问题。
如图2所示,是本申请一实施例提供的图像增强装置的功能模块图。
本申请所述图像增强装置100可以安装于电子设备中。根据实现的功能,所述图像增强装置100可以包括空间转换模块101、图像染色模块102、细节加强处理模块103、参量提取模块104、参数更新模块105和空间转回模块106。本申请所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述空间转换模块101,用于获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;本申请实施例中,所述原始图像可以为任何彩色图像,且由于计算机等具有图像显示功能的显示设备的限制,所述原始图像一般为RGB色彩空间的图像或为CMYK色彩空间的图像。
本申请实施了可利用具有数据抓取功能的python语句从预先构建的区块链节点中获取所述原始图像,利用区块链节点对数据的高吞天性,可提高获取原始图像的效率。
详细地,所述空间转换模块101具体用于:
获取原始图像;
获取原始图像的原始色彩空间参数;
根据所述原始色彩空间参数遍历并获取所述原始图像中各像素点的颜色三分量;
根据绝对色彩空间的绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量;
将所述中间值三分量进行归一化处理,得到归一化三分量;
根据目标色彩空间的目标色彩参数对所述归一化三分量进行数值校正,得到所述原始图像中各像素点校正三分量;
将所述校正三分量输入至所述目标色彩空间,得到初始图像。
本申请实施例可利用具有数据抓取功能的python语句从不同颜色空间的底层数据中获取所述原始色彩空间参数、所述绝对色彩参数和所述目标色彩参数。
详细地,所述原始色彩空间参数是所述原始图像所在的色彩空间中定义颜色范围的特定参数,所述原始色彩空间包括但不限于RGB色彩空间、CMYK色彩空间,原始色彩空间中显示的色彩范围会随着显示设备的变动而变动;所述绝对色彩参数是绝对色彩空间定义颜色范围的特定参数,所述绝对色彩空间包括但不限于sRGB色彩空间、Adobe RGB色彩空间,绝对色彩空间是显示的色彩范围不会随着显示设备的变动而变动。
所述目标色彩空间包括LAB色彩空间,所述目标色彩参数是目标色彩空间中定义颜色范围的特定参数,目标色彩空间中显示的颜色范围不会随显示设备的变动而变动,且由于目标色彩空间中显示的颜色范围适用于人类视觉,更有利于显示图像细节特征。
由于所述原始图像所在的原始色彩空间中显示的色彩范围会随着显示设备的变动而变动,但标色彩空间中显示的颜色范围不会随显示设备的变动而变动,因此,所述原始图 像无法直接从原始色彩空间转化至所述目标色彩空间,需要先将原始色彩空间中的原始图像转化至绝对色彩空间中,通过绝对色彩空间将所述原始图像转化至所述目标色彩空间。
例如,原始图像的原始色彩空间为RGB色彩空间,目标色彩空间为LAB色彩空间,在将原始图像从RGB色彩空间转换至LAB色彩空间时,需要先将原始图像从RGB色彩空间转换至sRGB色彩空间(即绝对色彩空间),再通过sRGB色彩空间将原始图像转换至LAB色彩空间。
本申请实施例遍历所述原始图像,获取所述原始图像中各像素点的颜色三分量,并利用线性变换函数根据绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量,其中,所述线性变换函数如下:
Figure PCTCN2021096528-appb-000013
y=α*R+β*G+γ*B
z=δ*R+ε*G+θ*B
其中,x、y、z为所述中间值三分量;R、G、B为原始图像中任一像素点的颜色三分量,C、
Figure PCTCN2021096528-appb-000014
∪、α、β、γ、δ、ε、θ为预设转化系数。
详细地,所述中间值三分量x、y、z分别用于表示绝对色彩空间中图像的任一像素点的颜色三分量。
本申请实施例通过上述步骤将原始图像的色彩空间由原始色彩空间转化为绝对色彩空间。
进一步地,所述将所述中间值三分量进行归一化处理得到归一化三分量,包括:
利用如下归一化算法将所述中间值三分量进行归一化处理:
F x=ρ*x
F y=σ*y
F z=τ*z
其中,F x、F y、F z为所述归一化三分量,x、y、z为所述中间值三分量,ρ、σ、τ为预设的归一化系数。
详细地,所述归一化系数ρ、σ、τ一般取值为
Figure PCTCN2021096528-appb-000015
本申请实施例中,所述根据所述目标色彩参数对所述归一化三分量进行数值校正得到所述原始图像中各像素点校正三分量,包括:
利用如下数值校正算法对所述归一化三分量进行数值校正:
Figure PCTCN2021096528-appb-000016
a=ω*(F x-F y)
Figure PCTCN2021096528-appb-000017
其中,L、a、b为所述原始图像中各像素点校正三分量,F x、F y、F z为所述归一化三分量,
Figure PCTCN2021096528-appb-000018
ω、
Figure PCTCN2021096528-appb-000019
为预设的校正参数,C为预设常数系数。
本申请实施例中对所述原始图像进行色彩空间转换,实现了将原始图像从原始色彩空间转换至目标色彩空间,利用目标色彩空间可更好的显示图像细节特征,有利于后续精准地对图像细节进行增强。
所述图像染色模块102,用于利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集。
本申请实施例中,所述图像染色模块102具体用于:
获取一种或者多种颜色参数;
遍历并获取所述初始图像中各像素点的像素值;
分别根据所述一种或者多种颜色参数对所述像素值进行线性调整,得到标准图像集。
本申请实施例利用具有数据抓取功能的python语句从预先构建的数据库中获取一种或者多种颜色参数。
详细地,所述颜色参数是用于唯一标识不同色彩的参数,所述颜色参数为动态浮点数值,可根据目标像素的像素值将目标像素转化至预设的颜色范围内。
例如,红色的颜色参数为r,红色的颜色范围为(qp),存在目标像素的像素值为k,且k不在(qp)范围内,则利用颜色参数r对目标像素的像素值进行线性调整,使得所述目标像素的像素值落入(qp)范围内。
本申请实施例中,分别利用多种颜色参数对初始图像中各像素点的像素值进行线性调整,得到多种不同颜色的图像,并汇集为标准图像集。
本申请实施例利用不同染色方式对初始图像进行染色,可实现在不同颜色下突出初始图像中的图像细节,有利于提高后续对图像中细节进行图像增强的精确度。
所述细节加强处理模块103,用于对所述标准图像集进行细节加强处理,得到待处理图像集。
本申请实施例中,所述细节加强处理模块103具体用于:
遍历并获取所述标准图像集的像素点;
利用预设的像素滤波器对所述像素点进行像素滤波处理,得到滤波图像集;
对所述滤波图像集进行局部纹理加深,得到待处理图像集。
本申请实施例中,所述像素滤波器包括但不限于最大值滤波器、最小值滤波器和中值滤波器,利用所述像素滤波器将所述标准图像集中的像素点进行像素滤波处理,可实现对所述标准图像集中噪声像素点的过滤。
进一步地,所述对所述滤波图像集进行局部纹理加深,得到待处理图像集,包括:
利用n×n的图像窗口在所述滤波图像集中依次执行区域选择,得到多个图像区域;
根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元;
根据所述二进制码元对所述中心像素进行像素增强,得到待处理图像集。
可选地,所述根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元,包括:
利用如下算法计算所述图像区域的中心像素的二进制码元
Figure PCTCN2021096528-appb-000020
Figure PCTCN2021096528-appb-000021
其中,P 0为所述图像区域的中心像素,P e为所述中心像素的邻域像素的均值,n为所述邻域像素的个数,s(P 0-P e)为量化运算。
本申请实施例对标准图像集进行细节加强处理,将标准图像集中噪声像素点进行过滤,并对图像细节进行局部纹理加深,突出了图像中的细节特征,有利于提高对图像进行图像增强的精确度。
所述参量提取模块104,用于对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量。
本申请实施例中,所述数值参量包括待处理图像集中各待处理图像的亮度均值、亮度方差、红色通道均值、红色通道方差、蓝色通道均值和蓝色通道方差。
本申请实施例中,所述参量提取模块104具体用于:
计算所述待处理图像集中各待处理图像的亮度均值和亮度方差;
计算所述待处理图像集中各待处理图像的红色通道均值和红色通道方差;
计算所述待处理图像集中各待处理图像的蓝色通道均值和蓝色通道方差。
详细地,所述分别计算所述待处理图像集中各待处理图像的亮度均值和亮度方差,包括:
利用如下公式分别计算所述待处理图像集中各待处理图像的亮度均值和亮度方差:
Figure PCTCN2021096528-appb-000022
Figure PCTCN2021096528-appb-000023
其中,L Avg为所述亮度均值,L Var为所述亮度方差,U为所述所述待处理图像集中第U张待处理图像包含的像素数量,S v为所述第U张待处理图像中第v个像素点的亮度分量。
具体地,分别计算待处理图像集中各待处理图像的红色通道均值、红色通道方差、蓝色通道均值和蓝色通道方差的步骤,与计算待处理图像集中各待处理图像的亮度均值和亮度方差的步骤一致,在此不做赘述。
所述参数更新模块105,用于根据所述数值参量对所述初始图像进行参数更新,得到更新图像。
本申请实施例中,所述参数更新模块105具体用于:
利用数值公式对所述数值参量进行计算,得到所述初始图像的更新参数;
利用所述更新参数对所述初始图像中的像素点进行赋值,得到更新图像。
详细地,所述更新参数包括亮度更新参数,红色更新参数和蓝色更新参数。
例如,利用如下数值公式计算得到所述初始图像的亮度更新参数:
Figure PCTCN2021096528-appb-000024
其中,I k为所述初始图像中第k个像素的亮度更新参数,σ target为所述数值参量中的亮度方差,σ source为所述初始图像中的亮度方差,Z k为所述初始图像中第k个像素的像素值,mean(source)为所述初始图像中的亮度均值,mean(target)为所述数值参量中的亮度均值。
具体地,计算所述红色更新参数和所述蓝色更新参数的步骤与计算所述亮度更新参数的步骤一致,在此不做赘述。
当计算完成得到初始图像中每个像素点的更新参数后,利用所述更新参数对初始图像中每个像素点的三分量进行赋值,即可得到更新图像。
所述空间转回模块106,用于对所述更新图像进行色彩空间转回,得到增强图像。
本申请实施例中,所述对所述更新图像进行色彩空间转回,包括:将所述更新图像的色彩空间由所述目标色彩空间转换至原始图像的原始色彩空间。
所述对所述更新图像进行色彩空间转回的步骤与所述空间转换模块101对所述原始图像进行色彩空间转换的步骤一致,在此不做赘述。
将更新图像的色彩空间转换至原始图像的色彩空间后,得到增强图像。
本申请实施例通过对获取的原始图像进行图像转换,实现了将原始图像从原始色彩空间转换至目标色彩空间,利用目标色彩空间可更好的显示图像细节特征,有利于后续精准地对图像细节进行增强;利用不同染色方式对所述初始图像进行染色,对染色后的图像进行细节加强处理得到待处理图像集,可实现在不同颜色下突出初始图像中的图像细节,突出了图像中的细节特征,有利于提高对图像进行图像增强的精确度;对待处理图像集进行参量提取,利用参量提取结果对初始图像进行更新,并将更新后的图像转换回原始色彩空间,实现了将待处理图像中的细节特征数值化,并根据参量提取结果精确的对初始图像中的图像细节进行更新。因此本申请提出的图像增强装置,可以解决对图像进行图像增强的精确度不高的问题。
如图3所示,是本申请一实施例提供的实现图像增强方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如图像增强程序12。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(Smart Media Card,SMC)、安全数字(Secure Digital,SD)卡、闪存卡(Flash Card)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如图像增强程序12的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(Central Processing unit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(Control Unit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如图像增强程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图3仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图3示出的结构并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的图像增强程序12是多个指令的组合,在所述处理器10中运行时,可以实现:
获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
对所述标准图像集进行细节加强处理,得到待处理图像集;
对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参 量;
根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
对所述更新图像进行色彩空间转回,得到增强图像。
具体地,所述处理器10对上述指令的具体实现方法可参考图1对应实施例中相关步骤的描述,在此不赘述。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读存储介质中。所述计算机可读存储介质可以是易失性的,也可以是非易失性的。例如,所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)。
本申请还提供一种计算机可读存储介质,所述可读存储介质存储有计算机程序,所述计算机程序在被电子设备的处理器所执行时,可以实现:
获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
对所述标准图像集进行细节加强处理,得到待处理图像集;
对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
对所述更新图像进行色彩空间转回,得到增强图像。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图标记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种图像增强方法,其中,所述方法包括:
    获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
    利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
    对所述标准图像集进行细节加强处理,得到待处理图像集;
    对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
    根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
    对所述更新图像进行色彩空间转回,得到增强图像。
  2. 如权利要求1所述的图像增强方法,其中,所述对所述原始图像进行色彩空间转换,得到初始图像,包括:
    获取原始图像的原始色彩空间参数;
    根据所述原始色彩空间参数遍历并获取所述原始图像中各像素点的颜色三分量;
    根据绝对色彩空间的绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量;
    将所述中间值三分量进行归一化处理,得到归一化三分量;
    根据目标色彩空间的目标色彩参数对所述归一化三分量进行数值校正,得到所述原始图像中各像素点校正三分量;
    将所述校正三分量输入至所述目标色彩空间,得到初始图像。
  3. 如权利要求1所述的图像增强方法,其中,所述利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集,包括:
    获取一种或者多种颜色参数;
    遍历并获取所述初始图像中各像素点的像素值;
    分别根据所述一种或者多种颜色参数对所述像素值进行线性调整,得到标准图像集。
  4. 如权利要求1所述的图像增强方法,其中,所述对所述标准图像集进行细节加强处理,得到待处理图像集,包括:
    遍历并获取所述标准图像集的像素点;
    利用预设的像素滤波器对所述像素点进行像素滤波处理,得到滤波图像集;
    对所述滤波图像集进行局部纹理加深,得到待处理图像集。
  5. 如权利要求4所述的图像增强方法,其中,所述对所述滤波图像集进行局部纹理加深,得到待处理图像集,包括:
    利用n×n的图像窗口在所述滤波图像集中依次执行区域选择,得到多个图像区域;
    根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元;
    根据所述二进制码元对所述中心像素进行像素增强,得到待处理图像集。
  6. 如权利要求5所述的图像增强方法,其中,所述根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元,包括:
    利用如下算法计算所述图像区域的中心像素的二进制码元
    Figure PCTCN2021096528-appb-100001
    Figure PCTCN2021096528-appb-100002
    其中,P 0为所述图像区域的中心像素,P e为所述中心像素的邻域像素的均值,n为所述邻域像素的个数,s(P 0-P e)为量化运算。
  7. 如权利要求1至6中任一项所述的图像增强方法,其中,所述对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量包括:
    计算所述待处理图像集中各待处理图像的亮度均值和亮度方差;
    计算所述待处理图像集中各待处理图像的红色通道均值和红色通道方差;
    计算所述待处理图像集中各待处理图像的蓝色通道均值和蓝色通道方差。
  8. 一种图像增强装置,其中,所述装置包括:
    空间转换模块,用于获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
    图像染色模块,用于利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
    细节加强处理模块,用于对所述标准图像集进行细节加强处理,得到待处理图像集;
    参量提取模块,用于对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
    参数更新模块,用于根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
    空间转回模块,用于对所述更新图像进行色彩空间转回,得到增强图像。
  9. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下步骤:
    获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
    利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
    对所述标准图像集进行细节加强处理,得到待处理图像集;
    对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
    根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
    对所述更新图像进行色彩空间转回,得到增强图像。
  10. 如权利要求9所述的电子设备,其中,所述对所述原始图像进行色彩空间转换,得到初始图像,包括:
    获取原始图像的原始色彩空间参数;
    根据所述原始色彩空间参数遍历并获取所述原始图像中各像素点的颜色三分量;
    根据绝对色彩空间的绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量;
    将所述中间值三分量进行归一化处理,得到归一化三分量;
    根据目标色彩空间的目标色彩参数对所述归一化三分量进行数值校正,得到所述原始图像中各像素点校正三分量;
    将所述校正三分量输入至所述目标色彩空间,得到初始图像。
  11. 如权利要求9所述的电子设备,其中,所述利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集,包括:
    获取一种或者多种颜色参数;
    遍历并获取所述初始图像中各像素点的像素值;
    分别根据所述一种或者多种颜色参数对所述像素值进行线性调整,得到标准图像集。
  12. 如权利要求9所述的电子设备,其中,所述对所述标准图像集进行细节加强处理,得到待处理图像集,包括:
    遍历并获取所述标准图像集的像素点;
    利用预设的像素滤波器对所述像素点进行像素滤波处理,得到滤波图像集;
    对所述滤波图像集进行局部纹理加深,得到待处理图像集。
  13. 如权利要求12所述的电子设备,其中,所述对所述滤波图像集进行局部纹理加深,得到待处理图像集,包括:
    利用n×n的图像窗口在所述滤波图像集中依次执行区域选择,得到多个图像区域;
    根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元;
    根据所述二进制码元对所述中心像素进行像素增强,得到待处理图像集。
  14. 如权利要求13所述的电子设备,其中,所述根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元,包括:
    利用如下算法计算所述图像区域的中心像素的二进制码元
    Figure PCTCN2021096528-appb-100003
    Figure PCTCN2021096528-appb-100004
    其中,P 0为所述图像区域的中心像素,P e为所述中心像素的邻域像素的均值,n为所述邻域像素的个数,s(P 0-P e)为量化运算。
  15. 如权利要求9至14中任一项所述的电子设备,其中,所述对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量包括:
    计算所述待处理图像集中各待处理图像的亮度均值和亮度方差;
    计算所述待处理图像集中各待处理图像的红色通道均值和红色通道方差;
    计算所述待处理图像集中各待处理图像的蓝色通道均值和蓝色通道方差。
  16. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:
    获取原始图像,对所述原始图像进行色彩空间转换,得到初始图像;
    利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集;
    对所述标准图像集进行细节加强处理,得到待处理图像集;
    对所述待处理图像集进行参量提取,得到所述待处理图像集中各待处理图像的数值参量;
    根据所述数值参量对所述初始图像进行参数更新,得到更新图像;
    对所述更新图像进行色彩空间转回,得到增强图像。
  17. 如权利要求16所述的计算机可读存储介质,其中,所述对所述原始图像进行色彩空间转换,得到初始图像,包括:
    获取原始图像的原始色彩空间参数;
    根据所述原始色彩空间参数遍历并获取所述原始图像中各像素点的颜色三分量;
    根据绝对色彩空间的绝对色彩参数对所述颜色三分量进行中间值转化,得到中间值三分量;
    将所述中间值三分量进行归一化处理,得到归一化三分量;
    根据目标色彩空间的目标色彩参数对所述归一化三分量进行数值校正,得到所述原始图像中各像素点校正三分量;
    将所述校正三分量输入至所述目标色彩空间,得到初始图像。
  18. 如权利要求16所述的计算机可读存储介质,其中,所述利用预设的一种或者多种染色方式对所述初始图像进行染色,得到标准图像集,包括:
    获取一种或者多种颜色参数;
    遍历并获取所述初始图像中各像素点的像素值;
    分别根据所述一种或者多种颜色参数对所述像素值进行线性调整,得到标准图像集。
  19. 如权利要求16所述的计算机可读存储介质,其中,所述对所述标准图像集进行细节加强处理,得到待处理图像集,包括:
    遍历并获取所述标准图像集的像素点;
    利用预设的像素滤波器对所述像素点进行像素滤波处理,得到滤波图像集;
    对所述滤波图像集进行局部纹理加深,得到待处理图像集。
  20. 如权利要求19所述的计算机可读存储介质,其中,所述对所述滤波图像集进行局部纹理加深,得到待处理图像集,包括:
    利用n×n的图像窗口在所述滤波图像集中依次执行区域选择,得到多个图像区域;
    根据每个所述图像区域的中心像素以及所述中心像素的邻域像素,利用预设算法计算每个所述图像区域的中心像素的二进制码元;
    根据所述二进制码元对所述中心像素进行像素增强,得到待处理图像集。
PCT/CN2021/096528 2020-11-30 2021-05-27 图像增强方法、装置、电子设备及计算机可读存储介质 WO2022110712A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011374000.XA CN112446839B (zh) 2020-11-30 2020-11-30 图像增强方法、装置、电子设备及计算机可读存储介质
CN202011374000.X 2020-11-30

Publications (1)

Publication Number Publication Date
WO2022110712A1 true WO2022110712A1 (zh) 2022-06-02

Family

ID=74738273

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/096528 WO2022110712A1 (zh) 2020-11-30 2021-05-27 图像增强方法、装置、电子设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN112446839B (zh)
WO (1) WO2022110712A1 (zh)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115423724A (zh) * 2022-11-03 2022-12-02 中国石油大学(华东) 强化学习参数优化的水下图像增强方法、装置及介质
CN115423716A (zh) * 2022-09-05 2022-12-02 深圳市新弘途科技有限公司 基于多维滤波的图像增强方法、装置、设备及存储介质
CN115861321A (zh) * 2023-02-28 2023-03-28 深圳市玄羽科技有限公司 应用于工业互联网的生产环境检测方法及系统
CN115937145A (zh) * 2022-12-09 2023-04-07 深圳市禾葡兰信息科技有限公司 基于大数据分析的肌肤健康可视化方法、装置及设备
CN117152182A (zh) * 2023-10-31 2023-12-01 深圳市巨龙创视科技有限公司 一种超低照度网络相机图像处理方法、装置及电子设备
CN117315053A (zh) * 2023-11-28 2023-12-29 国网山东省电力公司淄博供电公司 一种老旧设备拍摄图像视觉效果改进方法
CN117495742A (zh) * 2023-08-01 2024-02-02 西交利物浦大学 图像的染色转移方法、装置、设备及介质
CN117853346A (zh) * 2024-03-08 2024-04-09 杭州湘亭科技有限公司 基于洗消机器人的放射源三维辐射图像智能增强方法
CN117495742B (zh) * 2023-08-01 2024-05-31 西交利物浦大学 图像的染色转移方法、装置、设备及介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112446839B (zh) * 2020-11-30 2023-11-07 平安科技(深圳)有限公司 图像增强方法、装置、电子设备及计算机可读存储介质
CN113744167B (zh) * 2021-09-02 2024-04-30 厦门美图之家科技有限公司 一种图像数据转换方法及装置
CN113870454A (zh) * 2021-09-29 2021-12-31 平安银行股份有限公司 基于人脸识别的考勤方法、装置、电子设备及存储介质
CN113923474B (zh) * 2021-09-29 2023-06-23 北京百度网讯科技有限公司 视频帧处理方法、装置、电子设备以及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101493892A (zh) * 2009-02-27 2009-07-29 中国农业大学 图像特征提取方法及装置
US20170112216A1 (en) * 2015-10-22 2017-04-27 Gerber Technology, Inc. Color management for fabrication systems
CN111970432A (zh) * 2019-05-20 2020-11-20 华为技术有限公司 一种图像处理方法及图像处理装置
CN112446839A (zh) * 2020-11-30 2021-03-05 平安科技(深圳)有限公司 图像增强方法、装置、电子设备及计算机可读存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4824660B2 (ja) * 2007-11-21 2011-11-30 日本電信電話株式会社 デザイン配色変換方法、デザイン配色変換装置およびデザイン配色変換プログラム
JP5975213B2 (ja) * 2012-10-02 2016-08-23 富士ゼロックス株式会社 画像処理装置及び画像処理プログラム
US9979942B2 (en) * 2016-06-30 2018-05-22 Apple Inc. Per pixel color correction filtering
CN107424134B (zh) * 2017-07-27 2020-01-24 Oppo广东移动通信有限公司 图像处理方法、装置、计算机可读存储介质和计算机设备
CN108648143B (zh) * 2018-04-17 2022-03-29 中国科学院光电技术研究所 一种利用序列图像的图像分辨率增强方法
CN111310862B (zh) * 2020-03-27 2024-02-09 西安电子科技大学 复杂环境下基于图像增强的深度神经网络车牌定位方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101493892A (zh) * 2009-02-27 2009-07-29 中国农业大学 图像特征提取方法及装置
US20170112216A1 (en) * 2015-10-22 2017-04-27 Gerber Technology, Inc. Color management for fabrication systems
CN111970432A (zh) * 2019-05-20 2020-11-20 华为技术有限公司 一种图像处理方法及图像处理装置
CN112446839A (zh) * 2020-11-30 2021-03-05 平安科技(深圳)有限公司 图像增强方法、装置、电子设备及计算机可读存储介质

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115423716A (zh) * 2022-09-05 2022-12-02 深圳市新弘途科技有限公司 基于多维滤波的图像增强方法、装置、设备及存储介质
CN115423716B (zh) * 2022-09-05 2024-04-26 深圳市新弘途科技有限公司 基于多维滤波的图像增强方法、装置、设备及存储介质
CN115423724A (zh) * 2022-11-03 2022-12-02 中国石油大学(华东) 强化学习参数优化的水下图像增强方法、装置及介质
CN115423724B (zh) * 2022-11-03 2023-03-21 中国石油大学(华东) 强化学习参数优化的水下图像增强方法、装置及介质
CN115937145A (zh) * 2022-12-09 2023-04-07 深圳市禾葡兰信息科技有限公司 基于大数据分析的肌肤健康可视化方法、装置及设备
CN115937145B (zh) * 2022-12-09 2024-03-19 深圳市禾葡兰信息科技有限公司 基于大数据分析的肌肤健康可视化方法、装置及设备
CN115861321A (zh) * 2023-02-28 2023-03-28 深圳市玄羽科技有限公司 应用于工业互联网的生产环境检测方法及系统
CN115861321B (zh) * 2023-02-28 2023-09-05 深圳市玄羽科技有限公司 应用于工业互联网的生产环境检测方法及系统
CN117495742A (zh) * 2023-08-01 2024-02-02 西交利物浦大学 图像的染色转移方法、装置、设备及介质
CN117495742B (zh) * 2023-08-01 2024-05-31 西交利物浦大学 图像的染色转移方法、装置、设备及介质
CN117152182B (zh) * 2023-10-31 2024-02-20 深圳市巨龙创视科技有限公司 一种超低照度网络相机图像处理方法、装置及电子设备
CN117152182A (zh) * 2023-10-31 2023-12-01 深圳市巨龙创视科技有限公司 一种超低照度网络相机图像处理方法、装置及电子设备
CN117315053A (zh) * 2023-11-28 2023-12-29 国网山东省电力公司淄博供电公司 一种老旧设备拍摄图像视觉效果改进方法
CN117315053B (zh) * 2023-11-28 2024-03-22 国网山东省电力公司淄博供电公司 一种老旧设备拍摄图像视觉效果改进方法
CN117853346A (zh) * 2024-03-08 2024-04-09 杭州湘亭科技有限公司 基于洗消机器人的放射源三维辐射图像智能增强方法
CN117853346B (zh) * 2024-03-08 2024-05-14 杭州湘亭科技有限公司 基于洗消机器人的放射源三维辐射图像智能增强方法

Also Published As

Publication number Publication date
CN112446839B (zh) 2023-11-07
CN112446839A (zh) 2021-03-05

Similar Documents

Publication Publication Date Title
WO2022110712A1 (zh) 图像增强方法、装置、电子设备及计算机可读存储介质
AU2018102232A4 (en) Bone marrow cell marking method and system
WO2022121156A1 (zh) 图像中目标物检测方法、装置、电子设备及可读存储介质
WO2022247005A1 (zh) 图像中目标物识别方法、装置、电子设备及存储介质
CN111932534B (zh) 医学影像图片分析方法、装置、电子设备及可读存储介质
WO2020248848A1 (zh) 智能化异常细胞判断方法、装置及计算机可读存储介质
CN106845545B (zh) 数字式电测仪表自动检定装置中的图像识别方法及装置
WO2021151307A1 (zh) 基于病理切片扫描和分析一体化方法、装置、设备及介质
CN111476760B (zh) 医学图像的生成方法、装置、电子设备及介质
KR102634812B1 (ko) 스크린 광 누설량을 추정하는 방법, 장치 및 전자기기
WO2022178994A1 (zh) 表格结构识别方法、装置、电子设备及存储介质
WO2021168703A1 (zh) 字符处理及字符识别方法、存储介质和终端设备
CN114512085A (zh) 一种tft显示屏的视觉色彩校准方法
CN115278186B (zh) 基于物联网的可控制均匀投影方法、装置、设备及介质
US10963988B2 (en) Image processing device, image processing system, image processing method, and program
CN111985471A (zh) 一种车牌定位方法、装置及存储介质
CN113610934B (zh) 图像亮度调整方法、装置、设备及存储介质
CN115908175A (zh) 低照度图像多级增强方法、装置、电子设备以及存储介质
CN112862707A (zh) 一种基于图像处理的风电叶磨损分析方法及装置
WO2022227191A1 (zh) 非主动活体检测方法、装置、电子设备及存储介质
CN113989137A (zh) 一种脸部肌肤图像色素沉着提取并形成棕区光谱的方法
CN112802088A (zh) 一种基于图像处理技术的传输控制方法及装置
CN111899239A (zh) 图像处理方法和装置
CN117495742B (zh) 图像的染色转移方法、装置、设备及介质
CN115578370B (zh) 一种基于脑影像的代谢区域异常检测方法及装置

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: 21896222

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21896222

Country of ref document: EP

Kind code of ref document: A1