CN110705336A - Image processing method, system, electronic device and readable storage medium - Google Patents
Image processing method, system, electronic device and readable storage medium Download PDFInfo
- Publication number
- CN110705336A CN110705336A CN201810751097.8A CN201810751097A CN110705336A CN 110705336 A CN110705336 A CN 110705336A CN 201810751097 A CN201810751097 A CN 201810751097A CN 110705336 A CN110705336 A CN 110705336A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- marking
- detected
- suspected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The invention provides an image processing method, a system, an electronic device and a readable storage medium, wherein a frame of image is composed of a frame long exposure image, a frame middle exposure image and a frame short exposure image, and the image processing method comprises the following steps: and carrying out face detection on the mid-exposure image and judging whether a face is detected or not, if so, marking the face, otherwise, carrying out face detection on the long-exposure image and judging whether the face is detected or not, if so, marking the face, and if not, marking the face which is not detected. The invention utilizes the characteristic that the overall brightness of the image is higher in the long-exposure frame in one frame of picture, and uses the long-exposure frame to detect the face of the dark skin race in the dark and backlight scenes, thereby improving the detection rate of the face detection of the dark skin race.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to an image processing method, an image processing system, an electronic device, and a readable storage medium.
Background
At present, in the process of photographing by a mobile phone, the detection rate of detecting a dark skin color human face in a dark light/backlight environment is low, because under the conditions of dark light and backlight, because the exposure of the whole picture needs to be ensured to be reasonable by a camera automatic exposure global photometry algorithm, the face outline of a dark skin color race is not exposed sufficiently, so that the face outline of the dark skin color race is fused with the background color, the detection of the dark human face in the scene by the current general face recognition algorithm is invalid, the face of the dark skin color race cannot be exposed independently, and as a result, the face photographed by the dark skin color race in the environment cannot be enhanced and the picture is not good.
In order to solve the problem that in dark and backlight environments, the face of a dark skin color race in a photo is not exposed enough, the outline is not clear, and face recognition fails, an exposure strategy needs to be changed, and the face of the dark skin color race is made visible in an image by increasing the exposure. When the camera previews, the brightness of the whole picture needs to be considered, and the brightness is not purposely raised to detect the face of a person with dark skin color.
Currently, HDR algorithm exposure is usually synthesized by one frame long exposure, one frame medium exposure, and one frame short exposure, so as to achieve a high dynamic range of one frame of photo, and the long exposure and the short exposure frames are not displayed in preview.
Disclosure of Invention
In order to solve the above and other potential technical problems, an embodiment of the present invention provides an image processing method in which a frame image is composed of a long-exposure image, an in-exposure image, and a short-exposure image, the image processing method including: and carrying out face detection on the mid-exposure image and judging whether a face is detected or not, if so, marking the face, otherwise, carrying out face detection on the long-exposure image and judging whether the face is detected or not, if so, marking the face, and if not, marking the face which is not detected.
In an embodiment of the present invention, the performing face detection on the long exposure image and determining whether a face is detected specifically includes: reducing the long exposure image to obtain a reduced long exposure image; carrying out histogram equalization processing on the image dark part space of the reduced long exposure image to obtain a first equalized image; and carrying out face detection on the first equalized image and judging whether a face is detected or not, if so, marking the face, and if not, marking that the face is not detected.
In an embodiment of the present invention, the performing the face detection on the first equalized image includes: and if more than two suspected faces are detected in the first equalized image, marking the positions of the suspected faces respectively.
In an embodiment of the present invention, the image processing method further includes: according to the marked positions of the suspected faces, respectively extracting suspected face images of the corresponding positions of the suspected faces from the first equalized image; carrying out histogram equalization processing on the image dark part space of each suspected face image to obtain a second equalized image; and carrying out face detection on the second equalized image and judging whether a face is detected or not, if so, marking the face, and if not, marking that the face is not detected.
In an embodiment of the present invention, the marking the face includes marking a face frame at the face position and marking the face position.
An embodiment of the present invention further provides an image processing system, in which a frame image is composed of a frame long exposure image, a frame mid exposure image, and a frame short exposure image, the image processing system including: the intermediate exposure image detection module is used for carrying out face detection on the intermediate exposure image and judging whether a face is detected or not; the long exposure image detection module is used for carrying out face detection on the long exposure image and judging whether a face is detected or not; and the marking module is respectively connected with the intermediate exposure image detection module and the long exposure image detection module and is used for marking a human face when the intermediate exposure image detection module or the long exposure image detection module detects the human face and marking the human face which is not detected when the human face is not detected.
In an embodiment of the present invention, the long exposure image detection module includes: an image reducing unit configured to reduce the long exposure image to obtain a reduced long exposure image; a first equalization processing unit, configured to perform histogram equalization processing on the image dark space of the reduced long exposure image to obtain a first equalized image; a first face detection unit, configured to perform face detection on the first equalized image and determine whether a face is detected; the marking module is connected with the first face detection unit and used for marking a face when the first face detection unit detects the face, and marking an undetected face when the face is not detected.
In an embodiment of the invention, if the first face detection unit detects more than two suspected faces, the marking module marks the positions of the suspected faces respectively.
In an embodiment of the invention, the long exposure image detection module further includes: a suspected face image extracting unit, configured to extract, according to the marked position of each suspected face, a suspected face image at a position corresponding to each suspected face from the first equalized image; the second equalization processing unit is used for carrying out histogram equalization processing on the image dark part space of each suspected face image to obtain a second equalized image; the second face detection unit is used for carrying out face detection on the second equalized image and judging whether a face is detected or not; the marking module is connected with the second face detection unit and used for marking a face when the second face detection unit detects the face, and marking an undetected face when the face is not detected.
In an embodiment of the present invention, the marking the face includes marking a face frame at the face position and marking the face position.
Embodiments of the present invention also provide an electronic device, including a processor and a memory, where the memory stores program instructions, and the processor executes the program instructions to implement the steps in the method as described above.
An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the steps in the method as described above.
As described above, the image processing method, system, electronic device, and readable storage medium of the present invention have the following advantageous effects:
the invention utilizes the characteristic that the overall brightness of the image is higher in the long-exposure frame in one frame of picture, and uses the long-exposure frame to detect the face of the dark skin race in the dark and backlight scenes, thereby improving the detection rate of the face detection of the dark skin race.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a frame of image processed by the image processing method of the present invention.
Fig. 2 is a schematic overall flow chart of the image processing method of the present invention.
Fig. 3 shows a simple schematic flow chart of the image processing method of the present invention.
Fig. 4 is a schematic flow chart illustrating the process of performing face detection on a long-exposure image in the image processing method according to the present invention.
Fig. 5 is a simple schematic flowchart for performing face detection on a long-exposure image in the image processing method of the present invention.
Fig. 6 is a schematic diagram illustrating a preferred flow of face detection for a long-exposure image in the image processing method of the present invention.
Fig. 7 shows a schematic block diagram of an image processing system of the present invention.
FIG. 8 is a schematic block diagram of a long exposure image detection module in the image processing system of the present invention.
FIG. 9 is a schematic block diagram of a long exposure image detection module in the image processing system of the present invention.
Description of the element reference numerals
100 image processing system
110 exposure image detection module
120 long exposure image detection module
121 image reduction unit
122 first equalization processing unit
123 first face detection unit
124 suspected face image extracting unit
125 second equalization processing unit
126 second face detection unit
130 marking module
S110 to S160
S141 to S1412 steps
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
Please refer to fig. 1 to 9. It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions under which the present invention can be implemented, so that the present invention has no technical significance, and any structural modification, ratio relationship change, or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.
The embodiment aims to provide an image processing method, an image processing system, an electronic device and a readable storage medium, which are used for solving the problem that in dark light and backlight environments, the exposure of a dark skin color race human face in a photo is insufficient, the outline is unclear, and the human face recognition fails. The principles and embodiments of the image processing method, system, electronic device and readable storage medium of the present invention will be described in detail below, so that those skilled in the art can understand the image processing method, system, electronic device and readable storage medium of the present invention without creative efforts.
In the embodiment, the characteristic that the whole brightness of the image is higher in the long-exposure frame is utilized, and the long-exposure frame is used for detecting the face of the dark skin race in the dark light and backlight scenes, so that the detection rate of the face detection of the dark skin race can be improved.
Example 1
Specifically, the present embodiment provides an image processing method, as shown in fig. 1, in which the images processed by the image processing method in the present embodiment are synthesized high-dynamic images, that is, one frame of image is synthesized by one frame of long-exposure image, one frame of in-exposure image, and one frame of short-exposure image, as shown in fig. 2, the image processing method includes:
step S110, carrying out face detection on the mid-exposure image;
step S120, determining whether a face is detected, if yes, executing step S130: marking the face, if not, executing step S140: carrying out face detection on the long exposure image;
step S150, determining whether a face is detected, if yes, executing step S130: marking the face, if not, executing step S160: the mark does not detect a face.
The image processing method of the present embodiment will be described in detail below.
Step S110, carrying out face detection on the mid-exposure image; step S120, determining whether a face is detected, if yes, executing step S130: marking the face, if not, executing step S140: and carrying out face detection on the long exposure image.
As shown in fig. 3, in a dark light and backlight environment, if a face is detected in a normal preview image (equivalent to a mid-exposure image), face detection is not performed on a high-exposure image, and image processing is performed according to a face position detected in the normal preview image. And under the dark and backlight environments, if the face is not detected in the normal predew image, the face detection is carried out on the high-exposure image.
Step S140: carrying out face detection on the long exposure image; step S150, determining whether a face is detected, if yes, executing step S130: marking the face, if not, executing step S160: the mark does not detect a face.
That is, as shown in fig. 3, in a dark light and backlight environment, if a face is not detected in a normal predew image, face detection is performed on a high-exposure image, if a face is detected, a position is marked, and algorithm processing is performed, and if a face is not detected, a face is not detected.
Specifically, in this embodiment, as shown in fig. 4, the performing face detection on the long exposure image and determining whether a face is detected specifically includes:
step S141, reducing the long exposure image to obtain a reduced long exposure image; as shown in fig. 5, the long-exposure image is reduced to obtain a reduced image. The reduction scale range of the reduced long-exposure image relative to the long-exposure image is preferably 2-8 times, and the resolution of the reduced image is generally ensured to be not less than 300x300 according to the requirement of computing power.
Step S142, carrying out histogram equalization processing on the image dark part space of the reduced long exposure image to obtain a first equalized image; namely, the histogram equalization operation of the image dark space is carried out on the reduced image, and the image dark light part is equivalently lightened, so that the subsequent face detection processing is facilitated.
The histogram equalization is a transformation function which can automatically achieve the effect only by inputting histogram information of an image, and is used for widening gray levels with a large number of pixels in the image and compressing gray levels with a small number of pixels in the image, so that the dynamic range of pixel values is expanded, the change of contrast and gray tone is improved, and the image is clearer. Are often used to increase the local contrast of many images, especially when the contrast of the useful data of the images is relatively close. By performing histogram equalization in the dark space of the image on the reduced image, the brightness of the reduced image can be distributed on the histogram more favorably. This can be used to enhance the local contrast without affecting the overall contrast. The specific operation of histogram equalization is well known to those skilled in the art and will not be described herein.
Step S143, performing face detection on the first equalized image, and determining whether a face is detected, if yes, executing step S144: marking a human face; if not, go to step S145: the mark does not detect a face.
The first face retrieval algorithm processing is performed on the reduced long exposure image subjected to the histogram equalization operation in the dark space, and the specific face retrieval algorithm may be any one of the prior art, which is not limited herein.
As shown in fig. 5, if a face is not retrieved on the reduced-long exposure image, a no-face flag is output, and if a face is retrieved, a face is marked.
In this embodiment, as shown in fig. 6, the performing face detection on the first equalized image includes: if the face is retrieved, step S147 is executed: judging whether more than two suspected faces are detected in the first equalized image, if not, indicating that only one face is detected, directly marking the face, if so, indicating that more than two suspected faces are detected in the first equalized image, and executing step S148: and marking the positions of the suspected human faces respectively.
As shown in fig. 5, that is, if no face is retrieved on the first equalized image, a no-face mark is output, and if a plurality of suspected faces are retrieved on the first equalized image, the positions of the suspected face frames are recorded.
Specifically, in this embodiment, as shown in fig. 5, the image processing method further includes:
step S149, according to the marked positions of the suspected faces, respectively extracting suspected face images of the corresponding positions of the suspected faces from the first equalized image;
step 1410, performing histogram equalization processing on the image dark space of each suspected face image to obtain a second equalized image; as shown in fig. 5, that is, based on the position of the retrieved pseudo face frame, image data at the corresponding position is extracted from the original long-exposure image, and histogram equalization processing in the dark space of the image is performed on these image data.
Step S1411, performing face detection on the second equalized image;
in step S1412, it is determined whether a face is detected, and if yes, step S144 is executed: marking a human face; if not, go to step S145: the mark does not detect a face.
As shown in fig. 5, the image data after histogram equalization processing in the dark space of the image is subjected to a second face retrieval algorithm processing to remove incorrect face data, and a result of the second face retrieval is output and is output as a final result, so that the accuracy of face detection is improved.
In this embodiment, the marking of the face includes marking a face frame at the face position and marking the face position.
Therefore, the image processing method of the embodiment improves the detection rate of the human face with dark skin color in dark light and backlight environments, and can perform special processing on the detected human face in subsequent processing.
An embodiment of the present invention further provides an electronic device, which includes a processor and a memory, where the memory stores program instructions, and the processor executes the program instructions to implement the steps in the image processing method described above, where the image processing method has been described in detail above, and is not described herein again.
The present example provides an electronic device including: a processor, memory, transceiver, communication interface, or/and system bus; the memory is used for storing the computer program, the communication interface is used for communicating with other devices, and the processor and the transceiver are used for operating the computer program to enable the electronic device to execute the steps of the image processing method.
The above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components.
The electronic device is, for example, an electronic device such as a smart phone, a tablet computer, a notebook computer, and a smart camera.
Embodiments of the present invention also provide a computer-readable storage medium, such as a memory configured to store various types of data to support operations at a device. Examples of such data include instructions, messages, pictures, etc. for any application or method operating on the electronic device. The memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), high speed random access memory (high speed ram), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic memory, flash memory, magnetic or optical disks, or the like. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps in the image processing method as described above, which has been described in detail above and will not be described herein again.
Example 2
The present embodiment provides an image processing system, as shown in fig. 1, in which the image processed by the image processing system in the present embodiment is a synthesized high-dynamic image, that is, an image of one frame is synthesized by a long-exposure image of one frame, an exposure image of one frame, and a short-exposure image of one frame, as shown in fig. 7, the image processing system 100 includes: a medium exposure image detection module 110, a long exposure image detection module 120 and a marking module 130.
In this embodiment, the mid-exposure image detection module 110 is configured to perform face detection on a mid-exposure image and determine whether a face is detected; the long exposure image detection module 120 is configured to perform face detection on a long exposure image and determine whether a face is detected; the marking module 130 is respectively connected to the mid-exposure image detection module 110 and the long-exposure image detection module 120, and is configured to mark a face when the mid-exposure image detection module 110 or the long-exposure image detection module 120 detects a face, and mark an undetected face when the face is not detected.
The image processing system 100 of the present embodiment is explained in detail below.
The mid-exposure image detection module 110 performs face detection on a mid-exposure image, determines whether a face is detected, if so, the marking module 130 marks the face, otherwise, the long-exposure image detection module 120 performs face detection on the long-exposure image, determines whether the face is detected, if so, the marking module 130 marks the face, and if not, the marking module 130 marks that the face is not detected.
As shown in fig. 3, in a dark light and backlight environment, if a face is detected in a normal preview image (equivalent to a mid-exposure image), face detection is not performed on a high-exposure image, and image processing is performed according to a face position detected in the normal preview image. And under the dark and backlight environments, if the face is not detected in the normal predew image, carrying out face detection on the high-exposure image, if the face is detected, marking the position, carrying out algorithm processing, and if the face is not detected, marking that the face is not detected.
Specifically, in this embodiment, as shown in fig. 8, the long exposure image detection module 120 includes: an image reduction unit 121, a first equalization processing unit 122, and a first face detection unit 123.
The image reducing unit 121 is configured to reduce the long-exposure image to obtain a reduced long-exposure image; the reduction scale range of the reduced long-exposure image relative to the long-exposure image is preferably 2-8 times, and the resolution of the reduced image is generally ensured to be not less than 300x300 according to the requirement of computing power.
The first equalization processing unit 122 is configured to perform histogram equalization processing on the image dark space of the reduced long-exposure image to obtain a first equalized image; namely, the histogram equalization operation of the image dark space is carried out on the reduced image, and the image dark light part is equivalently lightened, so that the subsequent face detection processing is facilitated. The first face retrieval algorithm processing is performed on the reduced long exposure image subjected to the histogram equalization operation in the dark space, and the specific face retrieval algorithm may be any one of the prior art, which is not limited herein.
The first face detection unit 123 is configured to perform face detection on the first equalized image and determine whether a face is detected; the marking module 130 is connected to the first face detecting unit 123, and is configured to mark a face when the first face detecting unit 123 detects a face, and mark an undetected face when the face is not detected.
As shown in fig. 5, if a face is not retrieved on the reduced-long exposure image, a no-face flag is output, and if a face is retrieved, a face is marked.
In this embodiment, if the first face detection unit 123 detects more than two suspected faces, the marking module 130 marks the positions of the suspected faces respectively.
In this embodiment, as shown in fig. 9, the long exposure image detection module 120 further includes: a suspected face image extraction unit 124; a second equalization processing unit 125 and a second face detection unit 126.
The suspected face image extracting unit 124 is configured to extract a suspected face image at a position corresponding to each suspected face from the first equalized image according to the marked position of each suspected face.
The second equalization processing unit 125 is configured to perform histogram equalization processing on the image dark space of each suspected face image to obtain a second equalized image; as shown in fig. 5, that is, based on the position of the retrieved pseudo face frame, image data at the corresponding position is extracted from the original long-exposure image, and histogram equalization processing in the dark space of the image is performed on these image data.
The second face detection unit 126 is configured to perform face detection on the second equalized image and determine whether a face is detected, if so, the marking module 130 marks the face, and if not, the marking module 130 marks that the face is not detected.
In this embodiment, the marking of the face includes marking a face frame at the face position and marking the face position.
Therefore, the image processing system 100 of the present embodiment improves the detection rate of the human face with dark skin color in the dark and backlight environments, and can perform special processing on the detected human face in the subsequent processing.
It should be noted that the division of each module or unit of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And the modules can be realized in a form that all software is called by the processing element, or in a form that all the modules are realized in a form that all the modules are called by the processing element, or in a form that part of the modules are called by the hardware. These above modules or units may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors (DSPs), one or more Field Programmable Gate Arrays (FPGAs), and the like. When a module is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. These modules may be integrated together and implemented in the form of a System-on-a-chip (SOC).
In summary, the invention utilizes the characteristic that the overall brightness of the image is higher in the long-exposure frame in one frame of the photo, and uses the long-exposure frame to detect the face of the dark skin race in the dark and backlight scenes, so that the detection rate of the face detection of the dark skin race can be improved. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention shall be covered by the claims of the present invention.
Claims (12)
1. An image processing method, wherein a frame image is composed of a frame long exposure image, a frame in exposure image, and a frame short exposure image, the image processing method comprising:
and carrying out face detection on the mid-exposure image and judging whether a face is detected or not, if so, marking the face, otherwise, carrying out face detection on the long-exposure image and judging whether the face is detected or not, if so, marking the face, and if not, marking the face which is not detected.
2. The image processing method according to claim 1, wherein the performing face detection on the long exposure image and determining whether a face is detected specifically comprises:
reducing the long exposure image to obtain a reduced long exposure image;
carrying out histogram equalization processing on the image dark part space of the reduced long exposure image to obtain a first equalized image;
and carrying out face detection on the first equalized image and judging whether a face is detected or not, if so, marking the face, and if not, marking that the face is not detected.
3. The image processing method of claim 2, wherein the performing face detection on the first equalized image comprises: and if more than two suspected faces are detected in the first equalized image, marking the positions of the suspected faces respectively.
4. The image processing method according to claim 3, further comprising:
according to the marked positions of the suspected faces, respectively extracting suspected face images of the corresponding positions of the suspected faces from the first equalized image;
carrying out histogram equalization processing on the image dark part space of each suspected face image to obtain a second equalized image;
and carrying out face detection on the second equalized image and judging whether a face is detected or not, if so, marking the face, and if not, marking that the face is not detected.
5. The image processing method according to any one of claims 1 to 4, wherein the marking of the face comprises marking a face box and marking a face position at the face position.
6. An image processing system characterized in that an image of one frame is composed of an image of one frame long exposure, an image of one frame mid exposure, and an image of one frame short exposure, said image processing system comprising:
the intermediate exposure image detection module is used for carrying out face detection on the intermediate exposure image and judging whether a face is detected or not;
the long exposure image detection module is used for carrying out face detection on the long exposure image and judging whether a face is detected or not;
and the marking module is respectively connected with the intermediate exposure image detection module and the long exposure image detection module and is used for marking a human face when the intermediate exposure image detection module or the long exposure image detection module detects the human face and marking the human face which is not detected when the human face is not detected.
7. The image processing system of claim 6, wherein the long exposure image detection module comprises:
an image reducing unit configured to reduce the long exposure image to obtain a reduced long exposure image;
a first equalization processing unit, configured to perform histogram equalization processing on the image dark space of the reduced long exposure image to obtain a first equalized image;
a first face detection unit, configured to perform face detection on the first equalized image and determine whether a face is detected;
the marking module is connected with the first face detection unit and used for marking a face when the first face detection unit detects the face, and marking an undetected face when the face is not detected.
8. The image processing system according to claim 7, wherein the labeling module labels the positions of the respective suspected human faces if the first human face detection unit detects two or more suspected human faces.
9. The image processing system of claim 8, wherein the long exposure image detection module further comprises:
a suspected face image extracting unit, configured to extract, according to the marked position of each suspected face, a suspected face image at a position corresponding to each suspected face from the first equalized image;
the second equalization processing unit is used for carrying out histogram equalization processing on the image dark part space of each suspected face image to obtain a second equalized image;
the second face detection unit is used for carrying out face detection on the second equalized image and judging whether a face is detected or not;
the marking module is connected with the second face detection unit and used for marking a face when the second face detection unit detects the face, and marking an undetected face when the face is not detected.
10. The image processing system of any of claims 6 to 9, wherein the labeling of the face comprises labeling a face box and labeling a face location at a face location.
11. An electronic device comprising a processor and a memory, the memory storing program instructions, wherein the processor executes the program instructions to implement the steps in the method of any of claims 1 to 5.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810751097.8A CN110705336B (en) | 2018-07-10 | 2018-07-10 | Image processing method, system, electronic device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810751097.8A CN110705336B (en) | 2018-07-10 | 2018-07-10 | Image processing method, system, electronic device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110705336A true CN110705336A (en) | 2020-01-17 |
| CN110705336B CN110705336B (en) | 2022-09-09 |
Family
ID=69192503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810751097.8A Active CN110705336B (en) | 2018-07-10 | 2018-07-10 | Image processing method, system, electronic device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705336B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7444958B1 (en) | 2022-12-12 | 2024-03-06 | レノボ・シンガポール・プライベート・リミテッド | Information processing device and control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101909150A (en) * | 2009-06-03 | 2010-12-08 | 索尼公司 | Imaging apparatus and imaging control method |
| CN103699877A (en) * | 2013-12-02 | 2014-04-02 | 广东欧珀移动通信有限公司 | Method and system for improving face recognition effects |
| CN105069745A (en) * | 2015-08-14 | 2015-11-18 | 济南中景电子科技有限公司 | face-changing system based on common image sensor and enhanced augmented reality technology and method |
| CN106682620A (en) * | 2016-12-28 | 2017-05-17 | 北京旷视科技有限公司 | Human face image acquisition method and device |
| CN107592473A (en) * | 2017-10-31 | 2018-01-16 | 广东欧珀移动通信有限公司 | Exposure parameter method of adjustment, device, electronic equipment and readable storage medium storing program for executing |
-
2018
- 2018-07-10 CN CN201810751097.8A patent/CN110705336B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101909150A (en) * | 2009-06-03 | 2010-12-08 | 索尼公司 | Imaging apparatus and imaging control method |
| CN103699877A (en) * | 2013-12-02 | 2014-04-02 | 广东欧珀移动通信有限公司 | Method and system for improving face recognition effects |
| CN105069745A (en) * | 2015-08-14 | 2015-11-18 | 济南中景电子科技有限公司 | face-changing system based on common image sensor and enhanced augmented reality technology and method |
| CN106682620A (en) * | 2016-12-28 | 2017-05-17 | 北京旷视科技有限公司 | Human face image acquisition method and device |
| CN107592473A (en) * | 2017-10-31 | 2018-01-16 | 广东欧珀移动通信有限公司 | Exposure parameter method of adjustment, device, electronic equipment and readable storage medium storing program for executing |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7444958B1 (en) | 2022-12-12 | 2024-03-06 | レノボ・シンガポール・プライベート・リミテッド | Information processing device and control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110705336B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428366B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN110276767B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| US20200019760A1 (en) | Three-dimensional living-body face detection method, face authentication recognition method, and apparatuses | |
| JP6160004B2 (en) | Scene recognition method and apparatus | |
| CN111325716B (en) | Screen scratch and fragmentation detection method and equipment | |
| CN112602088B (en) | Method, system and computer readable medium for improving quality of low light images | |
| WO2021068618A1 (en) | Method and device for image fusion, computing processing device, and storage medium | |
| CN112565636B (en) | Image processing method, device, equipment and storage medium | |
| CN108510557B (en) | Image tone mapping method and device | |
| CN111325717B (en) | Mobile phone defect position identification method and equipment | |
| CN111368587B (en) | Scene detection method, device, terminal equipment and computer readable storage medium | |
| CN110991310B (en) | Portrait detection method, device, electronic equipment and computer readable medium | |
| CN110443766B (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN111601048B (en) | Image processing method and device | |
| CN113496208B (en) | Video scene classification method and device, storage medium and terminal | |
| CN111028276A (en) | Image alignment method and device, storage medium and electronic equipment | |
| CN107704798A (en) | Image weakening method, device, computer-readable recording medium and computer equipment | |
| CN111311556A (en) | Mobile phone defect position identification method and equipment | |
| CN115115562A (en) | Image fusion method and device | |
| CN110705336B (en) | Image processing method, system, electronic device and readable storage medium | |
| CN113129298A (en) | Definition recognition method of text image | |
| CN111080683B (en) | Image processing method, device, storage medium and electronic equipment | |
| CN111539975A (en) | Method, device and equipment for detecting moving target and storage medium | |
| CN108810407B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN115222653A (en) | Test method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 350003 building 18, No.89, software Avenue, Gulou District, Fuzhou City, Fujian Province Patentee after: Ruixin Microelectronics Co.,Ltd. Address before: 350003 building 18, No.89, software Avenue, Gulou District, Fuzhou City, Fujian Province Patentee before: FUZHOU ROCKCHIP ELECTRONICS Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |