TW202316852A - Image color adjustment method and image color adjustment device - Google Patents

Abstract

An image color adjustment method and an image color adjustment device are disclosed. The method includes: obtaining a target image; performing a neutral point detection on a color distribution of the target image; entering a first adjustment mode or a second adjustment mode according to a detection result of the neutral point detection; in the first adjustment mode, performing a face detection on the target image, and performing an image color adjustment on the target image according to a detection result of the face detection; and in the second adjustment mode, performing the image color adjustment on the target image according to the color distribution of the target image without performing the face detection.

Description

Image color adjustment method and image color adjustment device

The present invention relates to an image color adjustment technology, and in particular to an image color adjustment method and an image color adjustment device.

At present, most electronic devices with a camera function (such as smart phones) generally support the image adjustment function of automatic white balance, so as to perform color compensation on the captured image, such as adjusting the color temperature of the image. However, this automatic white balance mechanism often has problems in use. For example, when there are human faces and the background in the captured image, if the entire image is adjusted with the image tone of the background, the human face in the image may have a color cast. Therefore, in practice, a more ideal way is to detect faces in the image before adjusting the image, and then adjust the entire image according to the color of the face. However, in some cases (for example, when there is only a single ambient light source in the image), since the face may only occupy a small part of the entire image, if the entire image is only based on the color of the face in the image Making color adjustments may cause color casts in the entire image.

In view of this, the embodiments of the present invention provide an image color adjustment method and an image color adjustment device, which can improve the above problems.

An embodiment of the present invention provides an image color adjustment method, which includes: obtaining a target image; performing neutral point (neutral point) detection on the color distribution of the target image; an adjustment mode or a second adjustment mode; in the first adjustment mode, face recognition is performed on the target image, and image color adjustment is performed on the target image according to a recognition result of the face recognition; and in the first adjustment mode, In the second adjustment mode, when the face recognition is not performed, the image color adjustment is performed on the target image according to the color distribution of the target image.

An embodiment of the invention further provides an image color adjustment device, which includes a storage circuit and a processor. The storage circuit is used for storing the target image. The processor is coupled to the storage circuit and is used to: obtain the target image; perform neutral point detection on the color distribution of the target image; enter a first adjustment mode according to the detection result of the neutral point detection; or The second adjustment mode; in the first adjustment mode, perform face recognition on the target image, and perform image color adjustment on the target image according to the recognition result of the face recognition; and in the second adjustment mode, In the adjustment mode, the image color adjustment is performed on the target image according to the color distribution of the target image when the face recognition is not performed.

Based on the above, after the target image is obtained, neutral point detection may be performed on the color distribution of the target image. According to the detection result of the neutral point detection, one of the first adjustment mode and the second adjustment mode can be selectively activated. In the first adjustment mode, face recognition may be performed on the target image, and image color adjustment may be performed on the target image according to a recognition result of the face recognition. On the other hand, in the second adjustment mode, the face recognition will not be activated, and in the state where the face recognition is not performed, the image color adjustment performed on the target image can be performed according to the The color distribution of the target image is performed. In this way, face recognition can be selectively activated for different types of images, thereby effectively improving the efficiency of color adjustment for the entire image.

FIG. 1 is a schematic diagram of an image color adjustment device according to an embodiment of the present invention. Please refer to FIG. 1, the device (also called image color adjustment device) 10 can be a smart phone, a tablet computer, a notebook computer, a video camera, a camera, a game machine, a desktop computer, an industrial computer or a server, etc. An electronic device with data processing and image processing functions. In an embodiment, the device 10 may also have an image capture function.

The device 10 includes a processor 11 , a storage circuit 12 and an input/output (I/O) interface 13 . The processor 11 is coupled to a storage circuit 12 and an input/output device 13 . The processor 11 is responsible for the whole or part of the operation of the device 10 . For example, the processor 11 may include a central processing unit (Central Processing Unit, CPU), a graphics processing unit (graphics processing unit, GPU), or other programmable general-purpose or special-purpose microprocessors, digital signal processors (Digital Signal Processor, DSP), programmable controller, application specific integrated circuit (Application Specific Integrated Circuits, ASIC), programmable logic device (Programmable Logic Device, PLD) or other similar devices or a combination of these devices.

The storage circuit 12 is used for storing data. For example, the storage circuit 12 may include a volatile storage circuit and a non-volatile storage circuit. The volatile storage circuit is used for volatile storage of data. For example, the volatile storage circuit may include random access memory (Random Access Memory, RAM) or similar volatile storage media. The non-volatile storage circuit is used for non-volatile storage of data. For example, the non-volatile storage circuit may include a read only memory (Read Only Memory, ROM), a solid state disk (solid state disk, SSD), a traditional hard disk (Hard disk drive, HDD) or similar non-volatile storage media .

The input/output device 13 may include various signal input/output devices such as a camera lens, a communication interface, a mouse, a keyboard, a screen, a touch screen, a speaker, and/or a microphone. The present invention does not limit the device type of the input/output device 13 .

In one embodiment, the processor 11 can capture an image of the environment image through a camera lens in the input/output (I/O) device 13 to obtain an image (also referred to as a target image) 101 . Alternatively, in one embodiment, the processor 11 can receive the image 101 from other electronic devices through the communication interface in the input/output (I/O) device 13 . The image 101 can be stored in the storage circuit 12 . In an embodiment, the image 101 may include a face image of a person. Or, in an embodiment, the image 101 may not include a face image of a person.

In one embodiment, the processor 11 can obtain the image 101 . For example, the processor 11 can read the image 101 from the storage circuit 12 . The processor 11 can perform color analysis on the image 101 to obtain the color distribution of the image 101 . For example, the image 101 may include multiple pixels. Each pixel in the image 101 can correspond to a color code combination, and a color code combination can correspond to a visual color. For example, a color code combination can be composed of the color codes of the three primary colors of red (R), green (G) and blue (B). Take the color code combination (198, 164, 162) corresponding to a certain pixel as an example, the color code combination (198, 164, 162) means that at this pixel point, the color code of the primary color R is 198, and the color code of the primary color G is The code is 164, and the color code of primary color B is 162. The processor 11 can obtain the color distribution of the image 101 according to the combination of color codes corresponding to at least part of the pixels in the image 101 .

After obtaining the color distribution of the image 101 , the processor 11 may perform neutral point detection on the color distribution of the image 101 . The neutral point detection can be used to detect a neutral point (also called a neutral color reference point) in the color distribution of the image 101 . A neutral point corresponds to a color distribution. One color distribution can correspond to one color temperature. According to the detection result of the neutral point detection, the processor 11 can selectively enter the first adjustment mode or the second adjustment mode.

In the first adjustment mode, the processor 11 can perform facial recognition on the image 101 . Then, the processor 11 may perform image color adjustment on the image 101 according to the recognition result of the facial recognition. For example, the image color adjustment includes adjusting the white balance of the image 101 . On the other hand, in the second adjustment mode, the processor 11 may perform the image color adjustment on the image 101 according to the color distribution of the image 101 when the face recognition is not performed.

In one embodiment, if there is only a single color distribution (or color temperature) in the color distribution of the image 101 , the detection result of the neutral point detection may reflect that there is a single neutral point in the color distribution of the image 101 . The single neutral point can reflect or be used to describe the statistical characteristics or distribution characteristics of the single color distribution (or color temperature). For example, the single neutral point may reflect whether the overall color distribution (or color temperature) of the image 101 is cooler or warmer.

In one embodiment, if multiple color distributions (or color temperatures) exist in the color distribution of the image 101 at the same time, the detection result of the neutral point detection may reflect that there are multiple neutral points in the color distribution of the image 101 . The plurality of neutral points can respectively reflect or be used to describe the respective statistical characteristics or distribution characteristics of the plurality of color distributions (or color temperatures). For example, one of the plurality of neutral points may reflect that the color distribution (or color temperature) of a part of the image 101 is cooler, and the other of the plurality of neutral points may reflect that the color distribution (or color temperature) of a part of the image 101 is cooler. The color distribution (or color temperature) of some areas is warmer.

In one embodiment, if the color distribution of the image 101 cannot be clearly identified, grouped or defined, the detection result of the neutral point detection may reflect that there is no neutral point in the color distribution of the image 101 .

In one embodiment, the detection result of the neutral point detection may reflect whether there is any neutral point in the color distribution of the image 101 and/or the total number of neutral points in the color distribution of the image 101 . In response to the detection result of the neutral point detection reflecting that there are multiple neutral points or no neutral point in the color distribution of the image 101 , the processor 11 may enter the first adjustment mode. Then, the processor 11 can perform image color adjustment on the image 101 in the first adjustment mode. Alternatively, in response to the detection result of the neutral point detection reflecting that there is only a single neutral point in the color distribution of the image 101 , the processor 11 may enter the second adjustment mode. Then, the processor 11 can perform image color adjustment on the image 101 in the second adjustment mode.

In one embodiment, in the first adjustment mode, the processor 11 may determine whether there is a human facial pattern (ie, a human face) in the image 101 according to the recognition result of the facial recognition. In the first adjustment mode, if the recognition result of the facial recognition reflects that there is a human facial pattern in the image 101 , the processor 11 may perform image color adjustment on the image 101 according to the color distribution of the facial pattern. For example, the processor 11 may adjust the white balance of the entire image 101 (including the area where the face is located and the area other than the face in the image 101 ) according to the color distribution of the facial pattern (eg, skin color). Wherein, the color temperature of the area covered by the facial pattern in the image 101 may be the same as or different from the color temperature of the area other than the facial pattern in the image 101 .

From another point of view, in the first adjustment mode, if there is a human facial pattern in the image 101, the processor 11 may ignore the color distribution of the area other than the human facial pattern in the image 101, and only According to the color distribution of the facial pattern, the overall white balance of the image 101 is adjusted. On the other hand, in the first adjustment mode, if the recognition result of face recognition reflects that there is no human facial pattern in the image 101, the processor 11 can adjust the overall white of the image 101 according to the overall color distribution of the image 101. balance.

In an embodiment, in the second adjustment mode, the processor 11 may not perform face recognition on the image 101 . Thereby, the efficiency of the processor 11 in performing image color adjustment in the second adjustment mode can be improved. Especially, in the second adjustment mode, even if there is a human face pattern in the image 101 , the processor 11 still adjusts the overall white balance of the image 101 according to the overall color distribution of the image 101 . That is, in the second adjustment mode, even if there is a human face pattern in the image 101, the processor 11 still considers the color distribution of the area where the human face is located in the image 101 and the color distribution of the area other than the human face to adjust the image 101. Overall white balance.

In one embodiment, if there are multiple neutral points or no neutral point in the color distribution of the image 101 , it means that multiple areas in the image 101 may have different color distributions (or color temperatures). In this situation, in the first adjustment mode, the processor 11 can preferentially adjust the overall white balance of the image 101 based on the color distribution of the face pattern (or the color temperature of the ambient light source where the face is located). Thereby, in the shooting environment of the image 101, there are multiple light sources (i.e. mixed light sources) or the conditions of the light sources are not clear, the color shift that may appear on the human face in the image 101 after the color adjustment can be effectively reduced, and further Improves the color adjustment quality of images.

On the other hand, if there is only a single neutral point in the color distribution of the image 101, it means that there is only a single light source in the shooting environment of the image 101 and the overall color distribution (or color temperature) of the image 101 tends to be consistent. In this situation, in the second adjustment mode, the processor 11 may skip the face recognition process and directly adjust the white balance of the entire image 101 based on the overall color distribution of the image 101 . Thereby, the efficiency of performing color adjustment on the image 101 can be improved under the premise that the color adjustment quality of the image 101 is hardly affected.

FIG. 2 is a flowchart of an image color adjustment method according to an embodiment of the invention. Please refer to FIG. 2 , in step S201 , a target image is obtained. In step S202, a neutral point detection is performed on the color distribution of the target image. In step S203, enter the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection. In step S204 , in the first adjustment mode, face recognition is performed on the target image, and image color adjustment is performed on the target image according to a recognition result of the face recognition. In step S205 , in the second adjustment mode, the image color adjustment is performed on the target image according to the color distribution of the target image when the face recognition is not performed.

FIG. 3 is a flowchart of an image color adjustment method according to an embodiment of the invention. Referring to FIG. 3 , in step S301 , a target image is obtained. In step S302, a neutral point detection is performed on the color distribution of the target image. In step S303, it is determined whether there is a neutral point in the color distribution of the target image. If there is no neutral point in the color distribution of the target image, in step S304, enter the first adjustment mode. If there is at least one neutral point in the color distribution of the target image, in step S305, it is determined whether the number of the neutral points is greater than one. If the number of neutral points is greater than one, in step S304, enter the first adjustment mode. Or, if the number of neutral points is not greater than one, in step S306, enter the second adjustment mode.

However, each step in FIG. 2 and FIG. 3 has been described in detail above, and will not be repeated here. It should be noted that each step in FIG. 2 and FIG. 3 can be implemented as a plurality of program codes or circuits, which is not limited by the present invention. In addition, the methods shown in FIG. 2 and FIG. 3 can be used together with the above exemplary embodiments, or can be used alone, which is not limited by the present invention.

To sum up, the embodiment of the present invention can perform neutral point detection on the color distribution of the image to be processed at the moment and decide whether to perform face recognition on the image in the subsequent image color adjustment operation according to the detection result . Thereby, a better balance can be achieved between the color adjustment quality and the color adjustment efficiency of the image.

Although the present invention has been disclosed above with the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field may make some changes and modifications without departing from the spirit and scope of the present invention. The scope of protection of the present invention should be defined by the scope of the appended patent application.

10: Image color adjustment device 11: Processor 12: storage circuit 13: Input/output (I/O) interface 101: Image S201~S205, S301~S306: steps

FIG. 1 is a schematic diagram of an image color adjustment device according to an embodiment of the present invention. FIG. 2 is a flowchart of an image color adjustment method according to an embodiment of the invention. FIG. 3 is a flowchart of an image color adjustment method according to an embodiment of the invention.

S201~S205: steps

Claims (10)

A method for image color adjustment, comprising: Obtain the target image; performing a neutral point detection on the color distribution of the target image; Entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection; In the first adjustment mode, face recognition is performed on the target image, and image color adjustment is performed on the target image according to a recognition result of the face recognition; and In the second adjustment mode, when the face recognition is not performed, the image color adjustment is performed on the target image according to the color distribution of the target image. The image color adjustment method according to claim 1, wherein the step of entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection includes: In response to the detection result of the neutral point detection reflecting that there are multiple neutral points or no neutral point in the color distribution of the target image, the first adjustment mode is entered. The image color adjustment method according to claim 1, wherein the step of entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection includes: In response to the detection result of the neutral point detection reflecting that there is only a single neutral point in the color distribution of the target image, the second adjustment mode is entered. The image color adjustment method according to claim 1, wherein the step of entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection includes: judging whether there is a neutral point in the color distribution of the target image; Entering the first adjustment mode in response to the absence of any neutral point in the color distribution of the target image; In response to the presence of at least one neutral point in the color distribution of the target image, determine whether the number of the at least one neutral point is greater than one; entering the first adjustment mode in response to the number of the at least one neutral point being greater than one; and In response to the number of the at least one neutral point being not greater than one, the second adjustment mode is entered. The image color adjustment method as described in Claim 1, wherein the step of performing the image color adjustment on the target image according to the recognition result of the facial recognition includes: The image color adjustment is performed on the target image according to the color distribution of the face image in the target image. An image color adjustment device, comprising: a storage circuit for storing the target image; a processor, coupled to the storage circuit and used for: Obtain the target image; performing a neutral point detection on the color distribution of the target image; Entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection; In the first adjustment mode, face recognition is performed on the target image, and image color adjustment is performed on the target image according to a recognition result of the face recognition; and In the second adjustment mode, when the face recognition is not performed, the image color adjustment is performed on the target image according to the color distribution of the target image. The image color adjustment device according to claim 6, wherein the operation of entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection includes: In response to the detection result of the neutral point detection reflecting that there are multiple neutral points or no neutral point in the color distribution of the target image, the first adjustment mode is entered. The image color adjustment device according to claim 6, wherein the operation of entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection includes: In response to the detection result of the neutral point detection reflecting that there is only a single neutral point in the color distribution of the target image, the second adjustment mode is entered. The image color adjustment device according to claim 6, wherein the operation of entering the first adjustment mode or the second adjustment mode according to the detection result of the neutral point detection includes: judging whether there is a neutral point in the color distribution of the target image; Entering the first adjustment mode in response to the absence of any neutral point in the color distribution of the target image; In response to the presence of at least one neutral point in the color distribution of the target image, determine whether the number of the at least one neutral point is greater than one; entering the first adjustment mode in response to the number of the at least one neutral point being greater than one; and In response to the number of the at least one neutral point being not greater than one, the second adjustment mode is entered. The image color adjustment device according to claim 6, wherein the operation of performing the image color adjustment on the target image according to the recognition result of the facial recognition includes: The image color adjustment is performed on the target image according to the color distribution of the face image in the target image.

Images