Image evaluation method and system
By building simulated backlight scenes, using light sources and portrait models to evaluate the shooting effect of electronic devices under backlight, the problem of inefficient evaluation in the existing technology is solved, and efficient and scientific evaluation results are achieved.
Patent Information
- Application Number
- CN202311094584.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-25
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2043-08-25
AI Technical Summary
The existing technology cannot objectively and efficiently evaluate the effect of electronic devices on face shooting in backlight scenarios, resulting in inefficiency and unscientific evaluation.
By building scenes including different types of light sources, portrait models and standard color cards, simulate backlight scenes, collect face images, and perform unified standard data analysis based on parameters such as face area brightness, contrast and background exposure to evaluate shooting effects.
It realizes objective and efficient evaluation of different models in backlight scenarios, saves time for professional reviewers, improves evaluation efficiency, and provides scientific evaluation results.
Smart Images

Figure CN117714666B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to a method and system for image evaluation. Background Art
[0002] In recent years, as users' demand for photography has increased, major mobile phone manufacturers have paid more attention to the presentation of mobile phone images, and the focus of portrait photography has shifted from basic indoor and outdoor scenes to challenging backlit portrait scenes. In backlit scenes, "highlights are not exposed, and shadows have details" is the direction pursued by major manufacturers.
[0003] At present, the face shooting effect of electronic devices such as mobile phones and tablets in backlit scenes is usually evaluated by professionals, which consumes a lot of manpower and time. Therefore, it is necessary to introduce an evaluation method to objectively and efficiently evaluate the face shooting effect of electronic device cameras in backlit scenes. Summary of the invention
[0004] The embodiment of the present application provides a method for image evaluation, which solves the problem of being unable to objectively and efficiently evaluate the portrait shooting effect of the camera in backlighting by setting up a scene for portrait evaluation in a backlighting scene.
[0005] In the image evaluation method provided in the present application, a scene for simulating backlighting is first built. The scene may include a portrait model, a standard color card (such as a 24-color standard color card), a flat panel light, a light box, etc. The portrait model can be placed on a horizontal desktop, and a standard color card can be placed close to the front side of the portrait model. The placement position of the standard color card will not block the face area (or face area) of the portrait model, or will not block the face area and neck area of the portrait model (that is, the standard color card can be placed on the front side of the chest of the portrait model). The standard color card includes at least a pure black block and a pure white block. A flat panel light can be placed in front of the portrait model, and the projection of the light-emitting plane of the flat panel light in the vertical direction can cover the portrait model, or the projection of the light-emitting plane of the flat panel light in the vertical direction can at least cover the face area of the portrait model, so that the face area can obtain more uniform lighting as much as possible. In one possible implementation, there may be two flat panel lights, which are respectively arranged on the left and right sides in front of the portrait model, so as to illuminate the face area from the left front and the right front, so that the illumination of the face area is more uniform. The light box may be arranged behind the portrait model, and the portrait model may be located near the left side of the light box (or near the right side of the light box) so that a sufficient area of the light box can be displayed as a background. The light box may be in a rectangular shape. The eyes of the portrait model may be located, for example, at a fixed distance from the upper edge of the light box (such as one-third of the height of the light box). The brightness of the flat panel light and the light box, and / or the color temperature of the flat panel light and the light box may be adjusted. The light-emitting surface of the light box may display an image including a plurality of different grayscale bars, and the grayscale information may be used for subsequent analysis of the background exposure.
[0006] During data collection, the electronic device to be evaluated can be placed in front of the portrait model (facing the portrait model or not facing the portrait model), and the position of the electronic device can be adjusted so that the preview interface is composed of the portrait model near the left side of the screen (such as near the left third) or near the right side of the screen (such as near the right third). The eyes of the portrait model are at a fixed distance from the upper edge of the screen (such as one third of the height of the screen). The screen must also present the background light box area, leaving at least an area to display the grayscale bar image in the light box, so as to facilitate subsequent analysis of the background exposure.
[0007] Different backlighting scenes can correspond to different face area brightness, and different light ratios between the face area brightness and the background light box brightness. Therefore, when simulating different backlighting scenes, the brightness of the flat panel light can be adjusted so that the brightness of the face area reaches the brightness corresponding to the backlighting scene, and then the light box brightness is determined according to the face area brightness and light ratio, and the light box brightness is adjusted to an appropriate brightness.
[0008] When performing data analysis, the average brightness of the face area can be obtained based on the average brightness of each pixel in the face area. The contrast can be obtained based on the grayscale of the pure black block and the pure white block in the standard color palette. The corresponding information entropy can be obtained based on the grayscale bar information displayed in the light box to characterize the background exposure. Then, the portrait shooting performance of the electronic device in the backlit scene is evaluated based on the brightness, contrast and background exposure (or information entropy) of the face area.
[0009] According to the image evaluation method provided in the embodiment of the present application, by building a scene including different types of light sources, portrait models, standard color cards, etc., an actual indoor or outdoor backlit scene is simulated, and in this scene, an image including a face is collected by using different models and / or different shooting parameters, and then the brightness, background exposure, and contrast of the face area in the image are calculated according to a unified standard to characterize the shooting effect of the face under backlighting. This method collects data in a standardized backlit simulation scene, and then uses a unified standard for data analysis to finally obtain the face shooting effect, which can solve the current problem of being unable to objectively and efficiently evaluate the portrait shooting effects of different models of cameras in backlighting.
[0010] In a first aspect, a method for image evaluation is provided, comprising: under a first shooting parameter of a first shooting mode, acquiring an image including a portrait model, the image also including a color card placed in front of the portrait model, and a first light source placed behind the portrait model, the light-emitting screen of the first light source displaying a plurality of grayscale bars; acquiring an average brightness of a face area in the portrait model according to the image; acquiring a contrast corresponding to the image according to the color card; and acquiring information entropy according to information of the grayscale bars displayed in the image, the information entropy being used to indicate an exposure condition of the image.
[0011] In a possible implementation, the portrait model and the color card can be located in the same focal plane, that is, the color card can be close to the front side of the portrait model. The color card here can be a standard color card, such as a 24-color standard color card, which includes pure black blocks and pure white blocks.
[0012] According to the image evaluation method provided in the embodiment of the present application, by building a scene including different types of light sources, portrait models, standard color cards, etc., an actual indoor or outdoor backlit scene is simulated, and in this scene, an image including a face is collected by using different models and / or different shooting parameters, and then the brightness, background exposure, and contrast of the face area in the image are calculated according to a unified standard to characterize the shooting effect of the face under backlighting. This method collects data in a standardized backlit simulation scene, and then uses a unified standard for data analysis to finally obtain the face shooting effect, which can solve the current problem of being unable to objectively and efficiently evaluate the portrait shooting effects of different models of cameras in backlighting.
[0013] In combination with the first aspect, in certain implementations of the first aspect, the method also includes: adjusting the horizontal position of the portrait model, or adjusting the horizontal position of the first light source, so that the portrait model is located at a first distance from the left edge of the first light source or the right edge of the first light source; and adjusting the height of the portrait model, or adjusting the height of the first light source, so that the eye part of the portrait model is located at a second distance from the upper edge of the first light source.
[0014] In combination with the first aspect, in some implementations of the first aspect, the method further includes: setting at least one second light source in front of the portrait model; adjusting the second light source so that the brightness of the face area of the portrait model reaches a preset brightness.
[0015] In combination with the first aspect, in certain implementations of the first aspect, when there are two second light sources, the method further includes: respectively arranging the two second light sources on the left and right sides in front of the portrait model, and the angles between the lines connecting each of the second light sources and the portrait model and the vertical line on the front of the portrait model are the same.
[0016] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: setting a bracket in front of the portrait model and fixing the device to be tested in the bracket; turning on the photo taking or video recording function of the device to be tested; adjusting the position of the device to be tested so that the portrait model is located at a third distance from the left edge of the shooting screen or the right edge of the shooting screen, and so that the eye part of the portrait model is located at a fourth distance from the upper edge of the shooting screen.
[0017] In combination with the first aspect, in some implementations of the first aspect, the method further includes: starting a first shooting mode of the device under test and adjusting to a first shooting parameter; and shooting a preset number of the images under the first shooting mode and the first shooting parameter.
[0018] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: adjusting the brightness of the second light source so that the brightness of the facial area in the portrait model meets a first preset brightness; obtaining the brightness corresponding to the first light source based on the brightness of the facial area and a preset light ratio; and adjusting the first light source based on the brightness corresponding to the first light source.
[0019] In combination with the first aspect, in some implementations of the first aspect, the first light source is a light box, and the second light source is a flat panel light.
[0020] In combination with the first aspect, in some implementations of the first aspect, the method further includes: identifying a face area in the image, a background area corresponding to the first light source, and an area corresponding to the color card.
[0021] In combination with the first aspect, in some implementations of the first aspect, obtaining the average brightness of the face area in the portrait model according to the image specifically includes: calculating the average brightness of each pixel included in the face area in each image under the same shooting mode and the same shooting parameters, and obtaining the average brightness of the face area in each image;
[0022] According to the average of the average brightness of the face area in each image, the average of the brightness of the face area in the preset number of images is calculated to obtain the average brightness of the face area.
[0023] In combination with the first aspect, in some implementations of the first aspect, the contrast is calculated according to the following formula:
[0024]
[0025] Wherein, C is the contrast, L black is the grayscale average value of the pure black block in the color card, L white is the average grayscale value of the pure white blocks in the color card.
[0026] In combination with the first aspect, in some implementations of the first aspect, the information entropy is calculated according to the following formula: Among them, H is information entropy, hist gs (K) is the histogram of the grayscale value of the image, and K is the grayscale.
[0027] In a second aspect, an image evaluation system is provided, comprising a portrait model, a first light source located behind the portrait model, a second light source located in front of the portrait model, a color card located in front of the portrait model and on the same focal plane as the portrait model, and a device to be tested, wherein the image evaluation system is used to simulate a backlit scene.
[0028] In a third aspect, an image evaluation device is provided, comprising: one or more processors; one or more memories; the one or more memories storing one or more computer programs, the one or more computer programs comprising instructions, which, when executed by the one or more processors, enable the image evaluation device to obtain the average brightness of the face area in the portrait model based on the image; obtain the contrast corresponding to the image based on the color card; and obtain information entropy based on the information of the grayscale bars displayed in the image, wherein the information entropy is used to indicate the exposure condition of the image.
[0029] In a fourth aspect, a computer-readable storage medium is provided, which stores computer-executable program instructions. When the computer-executable program instructions are executed on a computer, the computer obtains the average brightness of the facial area in the portrait model based on the image; obtains the contrast corresponding to the image based on a color card; and obtains information entropy based on information of grayscale bars displayed in the image, wherein the information entropy is used to indicate the exposure condition of the image.
[0030] In a fifth aspect, a computer program product is provided, the computer program product comprising a computer program code, and when the computer program code is run on a computer, the computer is caused to execute the method as described in any implementation manner of the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 Schematic diagram of the structure of an electronic device 100 provided in each embodiment of the present application.
[0032] Figure 2 A software structure block diagram of an electronic device 100 provided in an embodiment of the present application.
[0033] Figure 3 A schematic diagram of the architecture of a backlight simulation system involved in an image evaluation method provided in an embodiment of the present application.
[0034] Figure 4 A schematic diagram of the architecture of a backlight simulation system involved in another image evaluation method provided in an embodiment of the present application.
[0035] Figure 5 A schematic flowchart of data collection involved in an image evaluation method provided in an embodiment of the present application.
[0036] Figure 6 A schematic diagram of a shooting interface of a device under test provided in an embodiment of the present application.
[0037] Figure 7 A schematic diagram of image composition during image acquisition provided in an embodiment of the present application.
[0038] Figure 8 A schematic diagram of a light box provided in an embodiment of the present application.
[0039] Fig.9A and Fig. 9B A schematic diagram of portrait shooting effects of different models in the same backlit scene provided in an embodiment of the present application.
[0040] Fig.10 A schematic flowchart of an image evaluation method provided in an embodiment of the present application. DETAILED DESCRIPTION
[0041] It should be noted that the terms used in the implementation method part of the embodiments of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated obstacles, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two, "at least one" and "one or more" mean one, two or more than two.
[0042] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, it is defined that the "first" and "second" features may explicitly or implicitly include one or more of the features.
[0043] References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing at different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in another way.
[0044] In order to better understand the image evaluation method provided in the embodiment of the present application, the following first introduces the terms or definitions that may be involved below.
[0045] 1. Light ratio (light radio)
[0046] Light ratio is one of the most important parameters in photography. It refers to the ratio of the light received by the dark side and the bright side of the object in the lighting environment. For example, if the picture is evenly illuminated, the light ratio is 1:1; if the light received by the bright side is twice that of the dark side, the light ratio is 1:4, and so on.
[0047] 2. Lab Mode
[0048] The Lab mode is a color mode announced by the International Commission on Illumination (CIE) in 1976. It is a color mode determined by the CIE organization that theoretically includes all colors visible to the human eye. The Lab mode represents color with a brightness component L and two color components a and b. The value range of L is 0-100%, the a component represents the spectrum change from green to red, and the b component represents the spectrum change from blue to yellow. The value range of a and b is -128 to 127.
[0049] Combined with the introduction in the background technology, when an electronic device is shooting in a backlit scene, if the illuminated surface of the subject is smaller than the backlit surface, it is easy to make the light ratio between the illuminated surface and the backlit surface of the subject large, and the brightness contrast is strong. When the subject includes a portrait, if the backlit surface of the face area is larger, the face will be darker than the surrounding objects, giving the effect of a black face.
[0050] At present, relevant technologies provide some methods to improve the brightness of faces and solve the problem of dark faces. For example, the overall exposure of backlit faces is increased to increase the brightness of the face area, or high dynamic range imaging (HDR) mode is used to shoot, and the brightness of the face area is increased by synthesizing images with different exposures, etc. However, the method of increasing the overall exposure of backlit portraits to brighten the face area will cause the image outside the face area to be overexposed and the image details to be seriously lost; and for images shot in HDR mode, since some of the image exposures used in the synthesized images are calculated based on the normal exposure of the entire image, when the calculated exposure is not suitable, the final portrait will also be dark.
[0051] In summary, when different models are used to shoot portraits in different ways, the shooting effects will be different. At present, when evaluating the portrait effects of different models shot in backlight, most of them are drawn by professional evaluators based on their subjective evaluation. This evaluation method not only consumes a lot of manpower, but also takes a lot of time and is inefficient. In addition, based on subjective evaluation standards, there will inevitably be inconsistencies, which lacks scientificity in the evaluation.
[0052] In view of this, the embodiment of the present application provides a method for image evaluation, which simulates an actual indoor or outdoor backlit scene by building a scene including different types of light sources, portrait models, standard color cards, etc., and collects images including faces in the scene through different models and / or different shooting parameters, and then calculates parameters such as the brightness, background exposure, and contrast of the face area in the image according to a unified standard to characterize the shooting effect of the face under backlighting. The method collects data in a standardized backlit simulation scene, and then uses a unified standard for data analysis to finally obtain the face shooting effect, which can solve the current problem of being unable to objectively and efficiently evaluate the portrait shooting effects of different models of cameras in backlighting.
[0053] The image evaluation method provided in the embodiment of the present application can be used to test the portrait (especially face) shooting effect of various types of electronic devices. Among them, the electronic devices may include, for example: smart phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. Exemplary embodiments of electronic devices include but are not limited to those equipped with Or a portable terminal with other operating systems. The electronic device may also be a desktop computer with a touch-sensitive surface (such as a touch panel). The specific type of the electronic device is not limited in the embodiments of the present application.
[0054] For example, Figure 1 , which is a schematic structural diagram of an electronic device 100 provided in an embodiment of the present application.
[0055] The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.
[0056] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.
[0057] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.
[0058] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.
[0059] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.
[0060] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.
[0061] The modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 170A, a receiver 170B, etc.), or displays an image or video through a display screen 194. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.
[0062] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.
[0063] In some embodiments, the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and / or a satellite based augmentation system (SBAS).
[0064] The electronic device 100 implements a display function through a GPU, a display screen 194, and an application processor, etc. The display screen 194 is used to display images, videos, and the like.
[0065] The electronic device 100 can realize the shooting function through ISP, camera 193, video codec, GPU, display screen 194 and application processor.
[0066] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy. The video codec is used to compress or decompress digital video. The NPU is a neural network (NN) computing processor that quickly processes input information by drawing on the structure of biological neural networks, such as the transmission mode between neurons in the human brain, and can also continuously self-learn.
[0067] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function. For example, files such as music and videos are stored in the external memory card. The internal memory 121 can be used to store computer executable program codes, which include instructions.
[0068] The electronic device 100 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.
[0069] Exemplarily, the software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The present application embodiment takes the Android system of the layered architecture as an example to exemplify the software structure of the electronic device 100. Figure 2 It is a software structure block diagram of the electronic device 100 according to an embodiment of the present application.
[0070] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom: application layer, application framework layer, Android runtime, system library, kernel layer, hardware abstraction layer (HAL), and hardware layer.
[0071] The application layer can include a series of application packages. Figure 2 As shown, the application package may include applications such as camera, calendar, map, WLAN, music, short message, gallery, call, navigation, Bluetooth, video, etc.
[0072] The application framework layer provides application programming interface (API) and programming framework for the applications in the application layer. The application framework layer includes some predefined functions. Figure 2 As shown, the application framework layer may include a window manager, a content provider, a phone manager, a resource manager, a notification manager, a view system, and the like.
[0073] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.
[0074] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.
[0075] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.
[0076] The phone manager is used to provide communication functions of the electronic device 100, such as management of call status (including connecting, hanging up, etc.).
[0077] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.
[0078] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, the terminal vibrates, the indicator light flashes, etc.
[0079] Android Runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.
[0080] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.
[0081] The application layer and the application framework layer run in the virtual machine. The virtual machine executes the java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as obstacle life cycle management, stack management, thread management, security and exception management, and garbage collection.
[0082] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.
[0083] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.
[0084] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.
[0085] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.
[0086] A 2D graphics engine is a drawing engine for 2D drawings.
[0087] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera sensor driver, audio driver, and sensor driver.
[0088] In order to better understand the image evaluation method provided by the embodiment of the present application, the following first introduces an exemplary backlight simulation system provided by the embodiment of the present application in conjunction with the accompanying drawings. It should be noted that the backlight simulation scene here is used to simulate the outdoor or indoor backlight environment when actually taking pictures or recording videos.
[0089] For example, Figure 3 , which is a schematic diagram of the architecture of a backlight simulation system involved in an image evaluation method provided in an embodiment of the present application.
[0090] In some embodiments, the backlight simulation system may include a flat panel light 10, a light box 20, a portrait model 30, and a standard color card 40. There may be one or more flat panel lights 10. For example, when there are two flat panel lights 10, the two flat panel lights may be respectively arranged on the left and right sides in front of the portrait model. Figure 4As shown, each flat panel light 10 can be at an angle of 45° to the portrait model 30, and in order to ensure that the face area of the portrait model has uniform and sufficient brightness, the distance between each flat panel light 10 and the portrait model 30 can be maintained within a range of 2m to 3m. The size of the flat panel light is usually set to be larger than the portrait model, so that the projection range of the flat panel light 10 in the vertical direction can cover the portrait model or at least the head (or face) area of the portrait head, for example, it can be a rectangular flat panel light of 1.5m×50cm.
[0091] In addition, the flat panel light 10 can be connected to the flat panel light control system ( Figure 3 The flat panel light 10 may be connected to a light source (not shown), or the flat panel light 10 may be integrated with a flat panel light control system. The flat panel light control system may include a brightness adjustment button and a color temperature adjustment button. The brightness adjustment button may be used to adjust the brightness of the flat panel light 10 so that the brightness on the face reaches a preset value; the color temperature adjustment button may be used to adjust the color temperature of the flat panel so that the illumination of the flat panel light can simulate the indoor lighting environment and / or the lighting environment under the night scene light sign (such as the color temperature tends to be warm tones) or the color temperature of outdoor lighting (such as the color temperature tends to be cool tones).
[0092] In some embodiments, in order to better simulate outdoor backlighting scenes, indoor backlighting scenes, or night scene light sign backlighting scenes, in actual applications, the brightness of the flat panel light can be adjusted through the brightness adjustment button so that the brightness of the face area reaches a preset brightness value. Exemplarily, the brightness of the face area corresponding to different backlighting scenes (or front brightness) can be shown in the following Table 1:
[0093] Table 1
[0094] Simulation scenario Face area brightness Outdoor backlit scene 1000lux Indoor backlit scene 100lux Night scene light sign backlight scene 20lux
[0095] It should be noted that the brightness of the face area under different simulated scenes in Table 1 above is only an example. In actual applications, in order to make the brightness of the face area closer to the brightness under different simulated scenes, the preset brightness corresponding to the brightness of the face area can also be adjusted. The embodiments of the present application are not limited to this.
[0096] In some embodiments, in order to ensure that the brightness of the face more accurately reaches the corresponding preset brightness value in different backlighting scenes, a illuminance meter can be used to detect the brightness of the face, and the brightness of the flat panel light can be adaptively adjusted according to the detection result of the illuminance meter, so that the brightness of the face area finally reaches the preset brightness value. For example, taking the preset brightness value corresponding to the face area shown in Table 1 above as an example, in an outdoor backlighting scene, the brightness of the flat panel light is adjusted so that the brightness of the face area is 1000 lux; in an indoor backlighting scene, the brightness of the flat panel light is adjusted so that the brightness of the face area reaches 100 lux; in a night scene with a backlight sign, the brightness of the flat panel light is adjusted so that the brightness of the face area reaches 20 lux).
[0097] by Figure 3 Taking the two flat panel lights shown as an example, in some embodiments, the specific process of debugging the brightness of the flat panel lights may include: first, turning on the two flat panel lights so that the flat panel lights are at the default brightness; then using a illuminance meter to detect the brightness of the face area, if the brightness of the face area is lower than a preset brightness value, then the brightness of the two flat panel lights can be adjusted synchronously (for example, the brightness of the two flat panel lights can be increased synchronously), and after one adjustment, continue to use the illuminance meter to detect the brightness of the face area, if the brightness of the face area still does not reach the preset brightness value, then the flat panel lights can be adjusted a second time; and so on, until the brightness of the face area reaches the corresponding preset brightness value; or, if the brightness of the face area is higher than the preset brightness value, then the brightness of the two flat panel lights can be adjusted synchronously (for example, the brightness of the two flat panel lights can be reduced synchronously), and after one adjustment, continue to use the illuminance meter to detect the brightness of the face area, if the brightness of the face area still does not reach the preset brightness value, then the flat panel lights can be adjusted a second time, and so on, until the brightness of the face area reaches the corresponding preset brightness value.
[0098] It should be noted that in the embodiment of the present application, the brightness of the two flat panel lights can be kept synchronized, that is, at the same time, the brightness of the two flat panel lights is consistent. When the brightness of the two flat panel lights is consistent, both sides of the portrait model located between the two flat panel lights can be evenly illuminated. However, the embodiment of the present application is not limited to this. For example, when there are more than two flat panel lights, different flat panel lights may be set in different positions, and each flat panel light may be adjusted to a different brightness.
[0099] In some embodiments, the light box 20 can be placed on a platform (such as a table) behind the portrait model 30, and the light box 20 can account for more than 2 / 3 of the image, so that enough light-emitting surface of the light box is left as the background, which is convenient for subsequent background exposure analysis. Specifically, the distance between the light box 20 and the portrait model 30 can be maintained in the range of 30 cm to 50 cm, for example; the center line (or center axis) of the portrait model 30 can be aligned with the vertical line at 1 / 3 of the left side of the light box 20, or the center line (or center axis) of the portrait model 30 can also be aligned with the vertical line at 1 / 3 of the right side of the light box 20, so that 2 / 3 of the light-emitting surface of the light box can be presented in the background; the eyes of the portrait model 30 can be aligned with the vertical line at 1 / 3 of the upper side of the light box 20. The light box 20 has a brightness adjustment button, which can be used to adjust the brightness of the light box.
[0100] As an example, Figure 3 As shown, three light boxes with the same size specifications can be placed side by side behind the portrait model, the midline (or central axis) of the portrait model can be aligned with the vertical contact line between the first light box on the left and the middle light box, and the right light box can be unobstructed by the portrait model and can be fully presented in the image.
[0101] In some embodiments, the brightness of the light box can be obtained based on the brightness of the face and a preset light ratio (or background light ratio). For example, a method for calculating the brightness of the light box can be shown in the following formula (1-1):
[0102] L=2 ev+1 ×L0 / 1000(1-1)
[0103] Wherein, L is the brightness of the light box, L0 is the brightness of the foreground or the brightness of the face area, and ev is the light ratio between the face area and the background light box.
[0104] It should be noted that the above formula (1-1) is only an exemplary calculation method for obtaining the light box brightness based on the ratio of face brightness to background light. In actual applications, the light box brightness can also be obtained by other methods, and the embodiments of the present application are not limited to this.
[0105] For example, in different simulation scenarios, the brightness of the face area and its corresponding background light ratio (that is, the light ratio between the brightness of the face area and the brightness of the background light box) can be shown in the following Table 2:
[0106] Table 2
[0107]
[0108] It should be noted that the values of the brightness of the face area and its corresponding background light ratio under different backlighting scenes in Table 2 above are only examples. In actual applications, the brightness of the face area and / or the background light ratio can also be set to other values, which are not limited in the embodiments of the present application. In addition, the embodiments of the present application only introduce the backlighting scenes as indoor backlighting scenes, outdoor backlighting scenes, and night scene light sign backlighting portrait scenes as examples, but the image evaluation method provided by the present application is not limited to application in simulating these three backlighting scenes.
[0109] In some embodiments, the portrait model 30 can select a color (corresponding to the skin color of a real portrait) as required.
[0110] In some embodiments, a standard color card may be placed in close contact with the front side of the portrait model 30. The standard color card may be located on the same focal plane as the portrait model, below the face area of the portrait model and without covering the neck. The standard color card may include a pure black block and a pure white block, for example, Figure 3 The 24-color standard color card shown.
[0111] It should be noted that the system architecture applicable to the image evaluation introduced above is only an example. In actual applications, the system architecture may also include other numbers of devices, such as more flat panel lights, or the system architecture may also include more other devices, or the relative positions of the various devices in the system architecture may also be maintained at other distances or angles, etc. The embodiments of the present application are not limited to this.
[0112] After the backlight simulation system is built, images can be collected through the electronic device being tested, that is, the data collection process is carried out. The following takes the electronic device being tested as a mobile phone as an example to introduce the data collection process. Figure 5 FIG. 1 is a schematic flow chart of data collection involved in an image evaluation method provided in an embodiment of the present application. The flow may specifically include the following steps:
[0113] S501, placing a bracket, fixing the mobile phone to be tested on the bracket, and adjusting the distance between the mobile phone and the portrait model.
[0114] In some embodiments, the bracket can be placed in front of the portrait model, and the bracket can be adjusted in height. The fixed position of the mobile phone in the bracket can be at the same height as the portrait model, for example, the camera of the mobile phone and the center point of the portrait model (or the midpoint of the line connecting the two eyes, etc.) are at the same height.
[0115] In some implementations, the distance between the mobile phone and the portrait model can be close to the distance for taking photos or videos. For example, the distance between the mobile phone and the portrait model can be kept within the range of 1m to 1.5m, but this embodiment of the application is not limited to this.
[0116] S502, turning on the mobile phone under test, adjusting to a preset shooting mode, and setting parameters and / or adjusting the composition.
[0117] The preset shooting modes here may include multiple modes, such as: photo mode, portrait mode, movie mode, etc. The parameters here refer to shooting parameters, such as magnification, image size ratio, etc.
[0118] In some embodiments, adjusting the shooting mode may include, for example, adjusting the shooting mode to one of aperture mode, night mode, portrait mode, video mode, and professional mode; setting parameters may include, for example, adjusting the shooting magnification, adjusting the image size ratio (such as 4:3, or 16:9, etc.), turning on or off the flash, turning on or off the AI control, etc.; adjusting the composition may include, for example, adjusting the relative position of the camera, the portrait model, and the light box in the background.
[0119] In some embodiments, assuming that the preset shooting mode is the photo mode and the shooting parameter is 2×, the tested mobile phone is turned on and adjusted to the preset shooting mode, for example, it may include: the user clicks on the camera application (application, App) on the main interface of the mobile phone; when the mobile phone receives the user's click operation input for the camera App, the camera shooting interface may be displayed in response to the click operation; for example, please refer to Figure 6 The shooting interface may include multiple controls, such as setting controls, artificial intelligence (AI) mode controls, flash controls, camera flip controls, album controls, and zoom controls. In addition, the shooting interface may also include different shooting modes, such as aperture mode, night scene mode, portrait mode, video mode, professional mode, and more modes, wherein more modes may include more controls for setting shooting modes ( Figure 6 (not shown). Afterwards, when the mobile phone receives a click operation on the camera mode control from the user, the camera mode can be switched from the default mode (e.g., video mode) to the camera mode. Afterwards, when the mobile phone receives an adjustment operation on the camera magnification from the user, the camera magnification can be changed in response to the user's adjustment operation until it reaches 2×.
[0120] In some embodiments, the purpose of adjusting the composition is to make the image present both the complete face area and sufficient background (light box), so as to facilitate the subsequent analysis of the background exposure (such as whether it is overexposed). Figure 7As shown, the adjusted composition may include, for example: the face area of the portrait model is located at 1 / 3 of the image, specifically, the distance between the midline (or central axis) of the face area and the left side of the image may be 1 / 3 of the image length, and the position of the human eye is 1 / 3 of the image height from the upper edge of the image.
[0121] It should be understood that by setting the portrait model at 1 / 3 of the image, the image can present the face area and have enough screen to present the light box in the background, so as to facilitate the subsequent analysis of the background exposure in the backlit scene. However, the embodiment of the present application only takes the setting of the portrait model at 1 / 3 of the image as an example. In actual applications, the position of the portrait model in the image is not limited to this, as long as it can meet the requirements of presenting the face area and presenting a background screen sufficient for analyzing the background exposure.
[0122] S503, turning on the flat panel light and the light box, adjusting the light source, and taking a preset number of images in each shooting mode.
[0123] In some embodiments, adjusting the light source may include, for example, adjusting the brightness of the flat panel light by using a brightness adjustment button of the flat panel light, and detecting the brightness of the face area of the portrait model by using a illuminometer until the brightness of the face area reaches a preset brightness corresponding to the backlight scene, wherein the face brightness corresponding to different backlight scenes may be as shown in Table 1 above. In addition, by using a brightness adjustment button of a light box, the light box brightness is calculated according to the light ratio of the background brightness to the front brightness (i.e., the light box brightness to the face area brightness), and the light box is adjusted to a preset brightness.
[0124] In some embodiments, in order to ensure data integrity under the same mode and / or the same parameters, multiple images, for example, 5 images, may be captured in each shooting mode.
[0125] It should be noted that capturing a preset number of images in each shooting mode may include capturing a preset number of images under each parameter (such as shooting magnification) of each shooting mode. For example, as shown in Table 3 below, an example of a preset number of images corresponding to different shooting modes and different shooting parameters (taking shooting magnification as an example) provided in an embodiment of the present application is provided:
[0126] Table 3
[0127]
[0128] It should be noted that the preset number of captured images may be the same under different shooting modes or the same shooting parameters of different shooting modes. After each image under a shooting parameter of a shooting mode is captured, it may be checked whether there are any images that are missed or of poor quality, and if so, retake them in time.
[0129] It should also be noted that the shooting modes, shooting parameters and preset number of shots shown in Table 3 above are all examples and are not limited to the embodiments of the present application.
[0130] S504, switch to a different light source, and repeat steps S502 and S503 to collect data.
[0131] In some embodiments, switching different light sources may include: switching the light source of the flat panel light and / or switching the light source of the light box. The switching of light sources here may, for example, refer to adjusting the brightness of the flat panel light through a brightness adjustment button, or adjusting the brightness of the light box through a brightness adjustment button.
[0132] It should be understood that by adjusting the brightness adjustment button of the flat panel light, the brightness of the flat panel light can be adjusted so that the brightness of the face area meets the face brightness required in the current backlighting scene. Among them, switching different light sources of the flat panel light can be used to simulate different backlighting scenes, for example, when switching from simulating an outdoor backlighting scene to simulating an indoor backlighting scene, the brightness of the flat panel light can be dimmed so that the brightness of the face area meets the face brightness in the indoor backlighting scene; when switching from simulating an indoor backlighting scene to simulating a night scene light sign backlighting scene, the brightness of the flat panel light can be further dimmed so that the brightness of the face area meets the face brightness in the night scene light sign backlighting scene.
[0133] In some embodiments, after adjusting the brightness of the flat panel light, since the brightness of the face area changes, in order to make the light ratio between the background brightness and the front brightness (that is, the light box brightness and the face area brightness) reach the preset light ratio, it is also necessary to adjust the brightness of the light box behind the portrait model. The brightness of the light box can be calculated based on the brightness of the face area and the preset light ratio (the calculation formula can be referred to the formula (1-1) introduced above).
[0134] After adjusting the brightness of the tablet and the brightness of the light box, all or part of the operations in step S502 and step S503 can be repeated, such as adjusting to a preset shooting mode, setting parameters and / or adjusting the composition, and after adjusting the light source, taking a preset number of images in each shooting mode, that is, collecting data in another backlit scene again.
[0135] According to the image evaluation method provided in the embodiment of the present application, by building a scene including different types of light sources, portrait models, standard color cards, etc., an actual indoor or outdoor backlit scene is simulated, and in this scene, an image including a face is collected by using different models and / or different shooting parameters, and then the brightness, background exposure, and contrast of the face area in the image are calculated according to a unified standard to characterize the shooting effect of the face under backlighting. This method collects data in a standardized backlit simulation scene, and then uses a unified standard for data analysis to finally obtain the face shooting effect, which can solve the current problem of being unable to objectively and efficiently evaluate the portrait shooting effects of different models of cameras in backlighting.
[0136] After the data collection is completed, the data can be analyzed, that is, the data analysis process is carried out. The following still takes the electronic device being evaluated as a mobile phone as an example to introduce the data analysis process.
[0137] It should be noted that if you want to obtain a portrait image with better effect in a backlit scene, you need to at least solve the problems of backlit dark face, blurred image and overexposed background. Therefore, when evaluating the image, it is also necessary to obtain parameter results that can characterize the backlit face brightness, image contrast and background exposure. First, in order to avoid backlit dark faces, it is necessary to ensure the correct exposure of the face, that is, the brightness of the face area needs to be set within a suitable range (or the preset face brightness value must be within a suitable range). Secondly, in order to ensure that the image is not blurred on the basis of correct exposure of the portrait, the contrast needs to be set within a suitable range. Thirdly, on the basis of correct exposure of the portrait and no blurring of the image, in order to avoid overexposed background, it is necessary to obtain information entropy that can be used to characterize the background exposure. In other words, in an embodiment of the present application, the data analysis process may include: calculating the brightness of the face area, calculating the contrast of the foreground, and calculating the exposure of the background when the face area is correctly exposed.
[0138] In some embodiments, in order to improve the effect of calculation and data comparison, the collected data can be classified and sorted before performing the above calculations. Exemplarily, the classification and sorting method may include, for example: classifying data according to shooting mode and shooting parameters, that is, sorting data under the same shooting mode and the same shooting parameters into the same category. When there are multiple models of the device under test, data of different models under the same shooting mode and the same shooting parameters can be sorted into one category according to the shooting mode and shooting parameters. Exemplarily, as shown in Table 4 below, an exemplary result after data classification of different shooting modes (taking night scene mode and portrait mode as examples), different shooting parameters (taking shooting magnifications as an example) and different models (taking Honor 90 and Honor X50 as examples) provided in an embodiment of the present application is:
[0139] Table 4
[0140]
[0141] Combined with Table 4 above, it can be concluded that under the same shooting mode and the same shooting parameters, the number of images that different models of devices need to take can be the same. However, under different shooting modes or different shooting parameters, the number of images that different models of devices need to take can be different. For example, under the 1× shooting parameter of the photo mode, the images taken by Honor 90 and Honor X50 can both be 5; under the 2× shooting parameter of the portrait mode, the images taken by Honor 90 and Honor X50 can both be 6.
[0142] In addition, since the indicator setting range or threshold value under different light source conditions is different, it is necessary to classify and sort out the performance of different models under different light source conditions, and save and output the sorted data. For example, the corresponding relationship between different light sources, different shooting modes, different shooting parameters and image data of different models can be shown in the following Table 5:
[0143] Table 5
[0144]
[0145] It should be noted that classifying and organizing the data collected under different shooting modes and different shooting parameters can facilitate the subsequent comparison of the portrait shooting performance of different models in backlit scenes under the same shooting mode and the same shooting parameters, so as to determine the model with better performance. In addition, the above Table 5 only uses the different brightness of flat panel lights as an example to represent different light sources. In actual applications, the brightness of the light box can also be used, or the brightness of the flat panel light and the brightness of the light box can be used together to represent different light sources, or other identifiers used to represent light sources can be used to represent different light sources. The embodiments of the present application are not limited to this.
[0146] In some embodiments, in order to accurately obtain the brightness (such as average brightness), contrast and information entropy of the face area, after acquiring the image taken by the device, the face area, background area (such as the light box area on the right), and standard color card area in the image can be identified through an automatic detection algorithm. The automatic detection algorithm here can be, for example, a face recognition algorithm, a feature matching algorithm, etc.
[0147] In order to better understand the image evaluation method provided in the embodiment of the present application, the specific calculation method of each parameter result (i.e., the brightness of the face area, the foreground contrast, and the background exposure when the face area is correctly exposed) is introduced below.
[0148] (I) Calculation method for brightness of face area
[0149] In some embodiments, an automatic detection algorithm is used to identify a face region in an image, wherein the automatic detection algorithm may be a face recognition algorithm, or any existing algorithm capable of identifying a specific region (such as a face region).
[0150] For the brightness of the face area of the portrait model, the average brightness of the face area can be calculated based on the brightness values of each pixel in the face area. Specifically, the RGB image collected by the device can be converted into a Lab image; then, based on the recognized face area, the brightness component (L) of each pixel in the face area can be calculated; then, the average brightness component of each pixel in the face area is calculated and used as the face brightness (L * -face) average.
[0151] (II) Calculation method for foreground contrast
[0152] The foreground contrast here may refer to the scene in front of the subject. In the embodiment of the present application, the subject may refer to a portrait model, and the foreground may specifically refer to a standard color card in front of the portrait model.
[0153] The foreground contrast in this application can be specifically represented by the contrast result in the standard color card. Specifically, the automatic recognition algorithm can be used to identify the standard color card area in the image; then, the pure white blocks in the standard color card (such as Figure 3 The grayscale average value of the last color block in the first row of the color card shown in the figure) and the pure black block in the standard color card (such as Figure 3 Then, according to the grayscale average of the pure white block and the grayscale average of the pure black block, the contrast ratio of the standard color card area is calculated according to the following formula (1-2):
[0154]
[0155] Among them, C is contrast, L is black is the grayscale average value of the pure black block, L white is the average grayscale value of pure white blocks.
[0156] It should be noted that the grayscale average value of the pure black block in the standard color card may be the average value of the grayscale of each pixel in the pure black block, and the grayscale average value of the pure white block in the standard color card may be the average value of the grayscale of each pixel in the pure white block. The method for obtaining the grayscale value of each pixel in the pure black block and the grayscale value of each pixel in the pure white block may be any existing method, and the embodiments of the present application are not limited thereto.
[0157] (III) Calculation method for background exposure
[0158] In the embodiment of the present application, the background exposure condition can be represented by information entropy. Specifically, Figure 8 As shown, the light box on the right can display a variety of information, such as grayscale bar 50, color card 60 and other information. If the light box in the captured image has more information, it means that the background exposure effect is better; if the light box in the captured image has less information, it means that the exposure effect is worse. The amount of information in the light box displayed in the image can correspond to the result of information entropy. The greater the information entropy, the more information in the light box that can be displayed in the image; the smaller the information entropy, the less information in the light box that can be displayed in the image.
[0159] In some embodiments, information entropy can be calculated using the following formula (1-3):
[0160]
[0161] Among them, H is information entropy, hist gs (K) is the histogram of the grayscale value of the image, where K is the grayscale (from 0 to 255).
[0162] After calculating and obtaining the face brightness, contrast, and information entropy according to the above method, the performance of the device in taking portraits in backlit scenes can be obtained. Specifically, the preset range of face area brightness, preset range of contrast, and information entropy threshold corresponding to different light sources can be pre-set. Exemplarily, the preset range of face area brightness can be shown as the following formula (1-4):
[0163]
[0164] Among them, y L-face is the average brightness of the face area; when x∈[L1,L2]1, y L-face =100 can be regarded as the appropriate range of face area brightness is [L1,L2], that is, when the face area brightness belongs to [L1,L2], the face brightness effect is better; when x∈[L1,L2], y L-face =0 can be regarded as the face brightness is not well presented when the face brightness is other than [L1, L2].
[0165] In some embodiments, the values of L1 and L2 can be flexibly set according to requirements. For example, when simulating an outdoor backlighting scene, L1 can be 50 and L2 can be 60; when simulating an indoor backlighting scene, L1 can be 50 and L2 can be 55. However, this embodiment of the present application is not limited to this.
[0166] Exemplarily, the preset range of contrast may be as shown in the following formula (1-5):
[0167]
[0168] Among them, y contrast is the foreground contrast; when x∈[C1,C2]1, y contrast =100 can be regarded as the appropriate range of contrast as [C1, C2]. That is, when the contrast belongs to [C1, C2], the portrait effect under backlight is better. When x∈[C1, C2], y contrast =0 can be regarded as the face area brightness is other than [C1, C2], the portrait effect under backlight is not good.
[0169] In some embodiments, the values of C1 and C2 can be flexibly set according to the requirements, for example, when simulating an outdoor backlighting scene, C1 can be 75% and C2 can be 90%; when simulating an indoor backlighting scene, C1 can be 70% and C2 can be 85%. However, this embodiment of the application is not limited to this.
[0170] Exemplarily, the information entropy index can be shown as the following formula (1-6):
[0171] y H =k*x (1-6)
[0172] Among them, y H is the information entropy index, k is the coefficient, and x is the value of information entropy.
[0173] It should be noted that the above formula (1-6) is only the information entropy index y H An example of the relationship between the value x of information entropy and various information entropy indicators y in practical applications H The corresponding relationship between the information entropy value x and the information entropy value x may also be in other forms, such as a nonlinear corresponding relationship, which is not limited in the present application embodiment.
[0174] In some embodiments, when the background exposure effect is better, the range of the corresponding information entropy index can be, for example, [5 bit, 6 bit] or [5 bit, 8 bit].
[0175] According to the image evaluation method provided in the embodiment of the present application, by combining the data of face brightness, information entropy, and contrast, the performance of the mobile phone camera in the backlit portrait scene can be objectively evaluated, and models with incorrect face exposure and small dynamic range capabilities can be identified, saving the time of professional evaluators and improving evaluation efficiency.
[0176] For example, Fig.9A and Fig. 9BThe figure is a schematic diagram of portrait shooting effects of different models in the same backlit scene provided by the embodiment of the present application. It can be seen from the figure that in the image corresponding to model 1, the brightness of the face area in the portrait model is darker; in the image corresponding to model 2, the brightness of the face area in the portrait model is brighter. Therefore, it can be concluded that the portrait shooting effect of model 2 in the backlit scene is better than that of model 1.
[0177] According to the image evaluation method provided in the embodiment of the present application, by building a scene including different types of light sources, portrait models, standard color cards, etc., an actual indoor or outdoor backlit scene is simulated, and in this scene, an image including a face is collected by using different models and / or different shooting parameters, and then the brightness, background exposure, and contrast of the face area in the image are calculated according to a unified standard to characterize the shooting effect of the face under backlighting. This method collects data in a standardized backlit simulation scene, and then uses a unified standard for data analysis to finally obtain the face shooting effect, which can solve the current problem of being unable to objectively and efficiently evaluate the portrait shooting effects of different models of cameras in backlighting.
[0178] For example, Fig.10 FIG. 1 is a schematic flow chart of an image evaluation method provided in an embodiment of the present application. The process may specifically include the following steps:
[0179] S1001, under a first shooting parameter of a first shooting mode, capturing an image including a portrait model, the image also including a color card placed in front of the portrait model, and a first light source placed behind the portrait model, the light-emitting screen of the first light source displaying a plurality of grayscale bars.
[0180] S1002, obtaining the average brightness of the face area in the portrait model according to the image.
[0181] S1003, obtaining a contrast value corresponding to the image according to the color card; and obtaining information entropy according to information of grayscale bars displayed on the image, where the information entropy is used to indicate an exposure condition of the image.
[0182] In a possible implementation, the portrait model and the color card can be located in the same focal plane, that is, the color card can be close to the front side of the portrait model. The color card here can be a standard color card, such as a 24-color standard color card, which includes pure black blocks and pure white blocks.
[0183] In some embodiments, the method also includes: adjusting the horizontal position of the portrait model, or adjusting the horizontal position of the first light source, so that the portrait model is located at a first distance from the left edge of the first light source or the right edge of the first light source; and adjusting the height of the portrait model, or adjusting the height of the first light source, so that the eye part of the portrait model is located at a second distance from the upper edge of the first light source.
[0184] In some embodiments, the method further includes: disposing at least one second light source in front of the portrait model; and adjusting the second light source so that the brightness of the face area of the portrait model reaches a preset brightness.
[0185] In some embodiments, when there are two second light sources, the method further includes: respectively arranging the two second light sources on the left and right sides in front of the portrait model, and the angles between the lines connecting each second light source and the portrait model and the vertical line on the front of the portrait model are the same.
[0186] In some embodiments, the method also includes: setting a bracket in front of the portrait model and fixing the device to be tested in the bracket; turning on the photo taking or video recording function of the device to be tested; adjusting the position of the device to be tested so that the portrait model is located at a third distance from the left edge of the shooting screen or the right edge of the shooting screen, and the human eye part of the portrait model is located at a fourth distance from the upper edge of the shooting screen.
[0187] In some embodiments, the method further includes: starting a first shooting mode of the device under test and adjusting to a first shooting parameter; and shooting a preset number of the images under the first shooting mode and the first shooting parameter.
[0188] In some embodiments, the method also includes: adjusting the brightness of the second light source so that the brightness of the facial area in the portrait model meets a first preset brightness; obtaining the brightness corresponding to the first light source based on the brightness of the facial area and a preset light ratio; and adjusting the first light source based on the brightness corresponding to the first light source.
[0189] In some embodiments, the first light source is a light box, and the second light source is a flat panel light.
[0190] In some embodiments, the method further includes: identifying a face area in the image, a background area corresponding to the first light source, and an area corresponding to the color card.
[0191] In some embodiments, obtaining the average brightness of the facial area in the portrait model based on the image specifically includes: calculating the average brightness of each pixel included in the facial area in each image under the same shooting mode and the same shooting parameters, and obtaining the average brightness of the facial area in each image; calculating the average brightness of the facial area in the preset number of images based on the average of the average brightness of the facial area in each image, and obtaining the average brightness of the facial area.
[0192] In some embodiments, the contrast is calculated according to the following formula: Wherein, C is the contrast, L black is the grayscale average value of the pure black block in the color card, L white is the average grayscale value of the pure white blocks in the color card.
[0193] In some embodiments, the information entropy is calculated according to the following formula: Among them, H is information entropy, hist gs (K) is the histogram of the grayscale value of the image, and K is the grayscale.
[0194] According to the image evaluation method provided in the embodiment of the present application, by building a scene including different types of light sources, portrait models, standard color cards, etc., an actual indoor or outdoor backlit scene is simulated, and in this scene, an image including a face is collected by using different models and / or different shooting parameters, and then the brightness, background exposure, and contrast of the face area in the image are calculated according to a unified standard to characterize the shooting effect of the face under backlighting. This method collects data in a standardized backlit simulation scene, and then uses a unified standard for data analysis to finally obtain the face shooting effect, which can solve the current problem of being unable to objectively and efficiently evaluate the portrait shooting effects of different models of cameras in backlighting.
[0195] Based on the same technical concept, an embodiment of the present application also provides an image evaluation system, including a portrait model, a first light source located behind the portrait model, a second light source located in front of the portrait model, a color card located in front of the portrait model and on the same focal plane as the portrait model, and a device to be tested, wherein the image evaluation system is used to simulate a backlit scene.
[0196] Based on the same technical concept, an embodiment of the present application also provides an image evaluation device, including: one or more processors; one or more memories; the one or more memories store one or more computer programs, and the one or more computer programs include instructions. When the instructions are executed by the one or more processors, the image evaluation device obtains the average brightness of the face area in the portrait model according to the image; obtains the contrast corresponding to the image according to the color card; and obtains information entropy according to the information of the grayscale bars displayed in the image, and the information entropy is used to indicate the exposure condition of the image.
[0197] Based on the same technical concept, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable program instructions. When the computer-executable program instructions are executed on a computer, the computer or processor executes one or more steps in any of the above methods.
[0198] Based on the same technical concept, an embodiment of the present application also provides a computer program product comprising instructions, wherein the computer program product includes computer program code. When the computer program code runs on a computer, the computer or processor executes one or more steps in any of the above methods.
[0199] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.
[0200] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.
[0201] The above is only a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the embodiment of the present application should be included in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiment of the present application should be based on the protection scope of the claims.
Claims
1. A method for image evaluation, characterized in that: Used to evaluate the performance of the camera of the device under test in backlit portrait scenes, including: Under the first shooting parameter of the first shooting mode, an image including a portrait model is captured, the image also including a color card placed in front of the portrait model, and a first light source placed behind the portrait model, the light-emitting screen of the first light source displays a plurality of grayscale bars; Acquire the average brightness of the face area in the portrait model according to the image; Acquire the contrast corresponding to the image according to the color card; and, Information entropy is obtained according to information of the grayscale bar displayed by the image, and the information entropy is used to indicate the background exposure condition of the image.
2. The method according to claim 1, characterized in that Before acquiring the image including the portrait model, the method further includes: adjusting the horizontal position of the portrait model or adjusting the horizontal position of the first light source so that the portrait model is located at a first distance from the left edge of the first light source or from the right edge of the first light source; and, The height of the portrait model is adjusted, or the height of the first light source is adjusted, so that the eye part of the portrait model is located at a second distance from the upper edge of the first light source.
3. The method according to claim 1 or 2, characterized in that: Before acquiring the image including the portrait model, the method further includes: At least one second light source is arranged on the front side of the portrait model; The second light source is adjusted so that the brightness of the face area of the portrait model reaches a preset brightness.
4. The method according to claim 3, characterized in that When there are two second light sources, before collecting the image including the portrait model, the method further includes: The two second light sources are respectively arranged on the left and right sides in front of the portrait model, and the angles between the lines connecting each of the second light sources and the portrait model and the vertical line on the front of the portrait model are the same.
5. The method according to claim 3 or 4, characterized in that: Before acquiring the image including the portrait model, the method further includes: A bracket is arranged in front of the portrait model, and a device to be tested is fixed in the bracket; Turn on the photo taking or video recording function of the device under test; Adjust the position of the device under test so that the portrait model is located at a third distance from the left edge of the shooting screen or the right edge of the shooting screen, and the eye part of the portrait model is located at a fourth distance from the upper edge of the shooting screen.
6. The method according to claim 5, characterized in that The method further comprises: Turning on a first shooting mode of the device under test and adjusting to a first shooting parameter; Under the first shooting mode and the first shooting parameters, a preset number of the images are shot.
7. The method according to any one of claims 3 to 6, characterized in that: Before acquiring the image including the portrait model, the method further includes: Adjusting the brightness of the second light source so that the brightness of the face area in the portrait model meets a first preset brightness; According to the brightness of the face area and a preset light ratio, acquiring the brightness corresponding to the first light source; The first light source is adjusted according to the brightness corresponding to the first light source.
8. The method according to any one of claims 3 to 7, characterized in that: The first light source is a light box, and the second light source is a flat panel light.
9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: A face area in the image, a background area corresponding to the first light source, and an area corresponding to the color card are identified.
10. The method according to claim 6, characterized in that The step of obtaining the average brightness of the face area in the portrait model according to the image specifically includes: Calculating the average brightness of each pixel included in the face area in each image under the same shooting mode and the same shooting parameters to obtain the average brightness of the face area in each image; According to the average of the average brightness of the face area in each image, the average of the brightness of the face area in the preset number of images is calculated to obtain the average brightness of the face area.
11. The method according to any one of claims 1 to 10, characterized in that The contrast ratio is calculated according to the following formula: Wherein, C is the contrast, is the average grayscale value of the pure black block in the color card, is the average grayscale value of the pure white blocks in the color card.
12. The method according to any one of claims 1 to 11, characterized in that The information entropy is calculated according to the following formula: in, is the information entropy, is the histogram of the image grayscale value, is grayscale.
13. An image evaluation system, characterized in that: To evaluate the performance of the camera of the electronic device under test in backlit portrait scenes, including: Portrait models; A color plate, the color plate is arranged in front of the portrait model and does not block the face area of the portrait model, and the color plate and the portrait model are located in the same focal plane; A first light source, the first light source is arranged behind the portrait model, and a light-emitting screen of the first light source displays a plurality of grayscale bars; a second light source, the second light source being disposed at the front side of the portrait model; A bracket is arranged in front of the portrait model and is used to fix the electronic device to be tested.
14. An image evaluation device, characterized in that: Used to evaluate the performance of the camera in backlit portrait scenes, including: one or more processors; one or more memories; The one or more memories store one or more computer programs, and the one or more computer programs include instructions. When the instructions are executed by the one or more processors, the image evaluation device implements the steps of the method according to any one of claims 1 to 12.
15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable program instructions, and when the computer-executable program instructions are executed on a computer, the computer is enabled to implement the steps of the method according to any one of claims 1 to 12.
Citation Information
Patent Citations
Backlighting scene detection method and device and imaging device
CN105657287A
Color night vision camera performance evaluation test system and method
CN112082738A
Camera image testing device and camera image testing system
CN114584756A
Camera evaluation method and equipment
CN115379208A
Evaluation method of image sensor, electronic equipment and storage medium
CN115550631A
