WO2020082827A1

WO2020082827A1 - Photographing method, device, terminal, and computer storage medium

Info

Publication number: WO2020082827A1
Application number: PCT/CN2019/097352
Authority: WO
Inventors: 钮晨霄; 姜万泉
Original assignee: 中兴通讯股份有限公司
Priority date: 2018-10-24
Filing date: 2019-07-23
Publication date: 2020-04-30
Also published as: CN111093022A

Abstract

Disclosed is a photographing method, comprising: acquiring location information of a target object in a current image in a viewfinder in a photographing mode; acquiring, on the basis of the location information of the target object, a target parameter used for expressing whether the target object has a posture distortion; when the target parameter is determined as satisfying a set posture distortion criterion, determining that the target object has a set posture distortion and issuing a prompt message; the prompt message being used for promoting an adjustment to the photographing of the target object. Also disclosed are a photographing device, a terminal, and a computer storage medium.

Description

Image shooting method, device, terminal and computer storage medium

cross reference

The present invention requires the priority of a Chinese patent application filed on October 24, 2018, with the application number 201811243683.8, and the invention titled "Image Capture Method, Device, Terminal, and Computer Storage Medium," and the entire content of the application is passed The reference is incorporated in the present invention.

Technical field

The present invention relates to the field of images, and in particular, to an image capturing method, device, terminal, and computer storage medium.

Background technique

At present, the field of view of cameras of terminal products such as mobile phones and cameras are basically greater than 90 degrees, which makes it easy for the subject to be distorted in the edge area of the viewfinder during the process of taking photos or videos. For example, when shooting outdoors, portraits in the edge area of the framing frame are prone to face distortions such as distortions and unbalanced facial proportions. In addition, non-professional photographers are prone to problems such as disproportion in the image, such as portrait distortion or portrait distortion due to the shooting angle and other reasons due to reasons such as low number of photographs and poor shooting experience.

Summary of the invention

In order to solve the existing technical problems, the embodiments of the present invention provide an image shooting method, device, terminal, and computer storage medium that can effectively solve posture distortion and thereby improve the image shooting quality.

To achieve the above objective, the technical solutions of the embodiments of the present invention are implemented as follows:

In a first aspect, an embodiment of the present invention provides an image capturing method, and the method includes:

Obtain the position information of the target object in the current image in the framing frame in the shooting mode; obtain the target parameter characterizing whether the target object has posture distortion according to the position information of the target object; determine that the target parameter satisfies the set posture distortion In the condition, it is determined that the target object has a set posture distortion, and a prompt message is issued; the prompt message is used to prompt adjustment of the shooting of the target object.

In a second aspect, an embodiment of the present invention provides an image capturing device, the device including:

The obtaining module is used to obtain the position information of the target object in the current image in the framing frame in the shooting mode; the processing module is used to obtain target parameters characterizing whether the target object has posture distortion according to the position information of the target object; The judging module is used to determine that the target object has the set posture distortion when the target parameter satisfies the set posture distortion condition; the prompt module is used to issue a prompt message; the prompt message is used to prompt adjustment of the target Object shooting.

In a third aspect, an embodiment of the present invention provides a terminal, the terminal includes a processor and a memory for storing a computer program that can be run on the processor; wherein, when the processor is used to run the computer program, The steps of the image capturing method described in the first aspect are performed.

According to a fourth aspect, an embodiment of the present invention provides a computer storage medium in which a computer program is stored. When the computer program is executed by a processor, the steps of the image capturing method of the first aspect are implemented.

BRIEF DESCRIPTION

1 is a schematic flowchart of an image capturing method in an embodiment of the invention;

2 is a schematic diagram of a person's face in an image in an embodiment of the invention;

3 is a schematic diagram of a person's face in an image in another embodiment of the invention;

4 is a schematic diagram of a person in an image in an embodiment of the invention;

5 is a schematic diagram of a person in an image in another embodiment of the invention;

6 is a schematic diagram of a person in an image in another embodiment of the invention;

7 is a schematic structural diagram of an image capturing device according to an embodiment of the invention;

8 is a schematic structural diagram of a terminal in an embodiment of the present invention;

9 is a schematic structural diagram of an image capture device in a specific embodiment of the present invention.

detailed description

The technical solution of the present invention will be further elaborated below with reference to the drawings and specific embodiments of the specification. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention. The terminology used in the description of the present invention herein is for the purpose of describing specific embodiments, and is not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more related listed items.

Referring to FIG. 1, an image capturing method provided by an embodiment of the present invention, which is applied to a terminal, includes the following steps:

Step S101: Obtain the position information of the target object in the current image in the framing frame in the shooting mode;

Here, the shooting mode may be a photographing mode or a camera mode. The viewfinder frame is located on the terminal and is used to display the captured image and the like. Before the terminal turns on the camera or activates the camera module to take a picture and does not receive a shooting instruction, an image composed of the object such as the target object is displayed in the viewfinder. The target object may be a person or an object, or a certain part of the person or a certain part of the object. The position information of the target object is used to indicate the position of the target object in the current image. It should be noted that when the target object is a person's face, since the shape of the person region image obtained by performing face detection on the image is a rectangle, the actual image of the person's face is located within the rectangle. Therefore, the The position information of a person's face can be represented by coordinates corresponding to the four vertices of the rectangle. In addition, the position information of the person can also be obtained according to the face position information of the person. As shown in FIG. 2, suppose that the four vertices of the rectangle abcd corresponding to the face image of the person obtained by recognizing the image are a, b, c, and d. Since the coordinates of each point in the image are fixed, then The coordinates of the four points a, b, c, and d can be used to represent the facial position information of the person.

Step S102: Acquire target parameters characterizing whether the target object has posture distortion according to the position information of the target object;

Here, after determining the position information of the target object, information such as the area size, height, width, and posture angle of the target object relative to the current image can be obtained, so as to further know the character Describe whether the target object has the target parameter of posture distortion. It should be noted that the posture distortion can be set according to actual needs. If the target object is a person's face, the corresponding posture distortion can be a face distortion; if the target object is a person, the corresponding The distortion of posture can be distortion of portrait ratio, distortion of character composition and so on. Correspondingly, for different posture distortions, the correspondingly characterized target parameters may be different. For example, for facial distortion, the corresponding target parameter may be the ratio between the area occupied by the face of the person in the set warning area and the area of the face of the person. For portrait distortion, the corresponding target parameter may be the ratio between the height of the face of the person and the height of the person. Since there may be multiple posture distortions set, the obtaining of the target parameter used to characterize whether the target object has posture distortion according to the position information of the target object may be obtaining the target object according to the position information of the target object There are target parameters corresponding to each posture distortion respectively.

Step S103: when it is determined that the target parameter satisfies the set posture distortion condition, it is determined that the target object has the set posture distortion, and a prompt message is issued; the prompt message is used to prompt adjustment of shooting of the target object.

Here, by matching the target parameter acquired in step S102 with the posture distortion condition that needs to be satisfied when the target object has posture distortion, it is detected whether the target object has the set posture distortion. The posture distortion condition may be set according to the corresponding posture distortion, the posture distortion is different, and the corresponding posture distortion condition may also be different. If the target parameter satisfies the posture distortion condition corresponding to the posture distortion, it indicates that the target object has a corresponding posture distortion. If the target parameter does not satisfy the posture distortion condition corresponding to the posture distortion, it means that there is no corresponding posture distortion for the target object. In addition, when it is determined that the target object has the set posture distortion according to the target parameter, a message prompting to adjust the shooting of the target object is issued to eliminate the target object by adjusting the shooting of the target object Existing posture distortion improves the quality of image capture.

It should be noted that, the prompt message may be a text message displayed on the current image in the framing frame, or may be prompted by vibration.

In summary, in the image shooting method provided in the above embodiment, the target parameters used to characterize whether the target object has posture distortion are acquired according to the acquired position information of the target object in the current image in the viewfinder in the shooting mode to determine the target When the parameter satisfies the set posture distortion condition, it is determined that the target object has the set posture distortion, and a prompt message is issued to remind the adjustment of the shooting of the target object. In this way, after it is determined that the target object in the current image in the viewfinder in the shooting mode has the posture distortion set, a message prompting to adjust the shooting of the target object is promptly issued, which effectively solves the problem of posture distortion in image shooting Image quality.

In an optional embodiment, the acquiring the position information of the target object in the current image in the viewfinder in the shooting mode includes:

Obtain the face position information of the person in the current image in the framing frame in shooting mode;

The acquiring, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion includes:

Determine the area of the face of the person and the area occupied by the face of the person in the set warning area according to the position information of the face of the person;

According to the area of the face of the person and the area occupied by the face of the person in the set warning area, determine the area between the area occupied by the face of the person in the set warning area and the area of the face of the person Ratio

When it is determined that the target parameter satisfies the set posture distortion condition, determining that the target object has the set posture distortion includes:

When it is determined that the ratio between the area occupied by the face of the person in the set warning area and the face area of the person is greater than the set first threshold, it is determined that the target object has facial distortion.

Here, the acquiring the face position information of the person in the current image in the framing frame in the shooting mode may use an existing face recognition algorithm to perform face detection on the current image in the framing frame in the shooting mode to obtain a face area, According to the point coordinates of the face area of the person, the face position information of the person is obtained. It should be noted that when performing face detection, the shape of the detected face area image is a rectangle, and the actual face area image of the person is located within the rectangle. Therefore, the position information of the face of the person can be The coordinates of the vertices. After the face position information of the person is determined, the face area of the person can be directly obtained according to the face position information of the person. Please refer to FIG. 2 again, assuming that the facial position information of the person can be represented by four points a, b, c, and d, and the distance between point a and point b or the distance between point c and point d can be used as The width of the face of a person, using the distance between point a and point c or the distance between point b and point d as the height of the face of the person, to obtain the face area of the person, that is, the width of the face of the person and the person The product of the height of the face. The warning area is used to warn the area where face distortion may occur, and the shape and size of the warning area can be set according to actual needs. In this embodiment, the area in the framing frame is divided into a warning area and a non-warning area. The shape of the non-warning area may be rectangular, square, or oval, etc. The warning area is divided into the framing frame. The area other than the non-warning area is the area between the edge of the framing frame and the non-warning area. Since the position of the warning area is known, the area occupied by the face of the person in the set warning area can be known according to the position information of the face of the person. Referring to FIG. 3, assume that the shape of the non-alert area is a rectangle efgh, and the four vertices corresponding to the rectangle are e, f, g, and h. The alert area is an area other than the rectangular efgh. The location information of the face is represented by four points a, b, c, d, then according to the coordinates of the eight points a, b, c, d, e, f, g, h, the person can be known The coordinates of the critical points i and j between the warning area and the non-alert area, so that the area of the rectangle aijc can be obtained according to the coordinates of the four points a, i, j, and c, that is, the person The area occupied by the face in the warning area. The first threshold may be set according to actual needs, such as 0.5 or 0.75. When the ratio of the area of the face of the person in the set warning area to the area of the face of the person is greater than the set first threshold, it means that the face of the person occupies in the warning area The area of is larger, and there will be face distortion in the image taken at this time, and it is necessary to adjust the shooting of the face of the person.

In this way, according to the position information of the face of the person in the current image in the framing frame in the shooting mode, determine the area of the face of the person and the area occupied by the face of the person in the set warning area, and then determine the person Area of the face and the area occupied by the face of the person in the set warning area meet the set face distortion conditions, it is determined that there is face distortion, and a prompt is issued to prompt adjustment of the face of the person The news of shooting, so as to effectively solve the problem of face distortion in image shooting, improve the quality of image shooting, and the operation is simple and convenient.

Acquiring the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the face of the person;

Acquiring the position information of the person according to the position information of the face of the person and the depth of field;

Determine the face height of the person according to the face position information of the person;

Acquiring the height of the person according to the position information of the person;

Determining the ratio between the height of the face of the person and the height of the person according to the height of the face of the person and the height of the person;

When it is determined that the ratio between the height of the face of the person and the height of the person is greater than the set second threshold and less than the set third threshold, it is determined that the target object has a portrait distortion.

Here, the acquiring the face position information of the person in the current image in the framing frame in the shooting mode may use an existing face recognition algorithm to perform face detection on the current image in the framing frame in the shooting mode to obtain a face area, According to the point coordinates of the face area of the person, the face position information of the person is obtained. It should be noted that when performing face detection, the shape of the detected face area image is a rectangle, and the actual face area image of the person is located within the rectangle. Therefore, the position information of the face of the person can be The coordinates of the vertices. The acquiring the depth of field of the person in the current image in the framing frame in the shooting mode may be calculating the depth of field of the face of the person in the current image in the framing frame in the shooting mode using an existing single-shot algorithm or a dual-shot algorithm. The acquiring the position information of the person according to the face position information of the person and the depth of field may be based on the face position information of the person, acquiring the same or similar pixels of the person's face and the depth of field In the same area, the position information of the person is determined according to the area. It should be noted that, when detecting the human region, the shape of the detected human region image is a rectangle, and the actual image of the human is within the rectangle. Therefore, the position information of the human can be represented by the coordinates of the four vertices corresponding to the rectangle. After the face position information of the person is determined, the face height of the person can be directly obtained according to the face position information of the person. After the position information of the person is determined, the height of the person can be directly obtained according to the position information of the person. Referring to FIG. 4, it is assumed that the face position information of the person is represented by four points a, b, c, and d, and the person is determined according to the face position information of the person and the depth of field of the person Is the area corresponding to the rectangular klmn, the distance between point a and point c or the distance between point b and point d can be used as the face height of the person, and the distance between point k and point m or The distance between point l and point n is taken as the height of the character. The second threshold can be set according to actual needs, such as 0.125 or 0.2. The third threshold is greater than the second threshold, and may also be set according to actual needs, such as 0.25 or 0.3. When the ratio between the height of the face of the person and the height of the person is greater than the set second threshold and less than the set third threshold, it means that the height of the face of the person is divided by the face of the person The heights of the parts other than the part are close, and the person photographed in this way may not meet the aesthetic requirements, so it is determined that the target object has a portrait distortion. When the ratio between the height of the face of the person and the height of the person is greater than the set third threshold, it means that the shot may be a half-length shot or a head shot, etc. At this time, whether the target object is There is a portrait distortion to judge.

In this way, according to the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the face of the person, the height of the face of the person and the height of the person are obtained, and the person ’s height is determined When the ratio between the height of the face and the height of the person satisfies the set portrait distortion condition, it is determined that there is a portrait distortion, and a message prompting to adjust the shooting of the person is promptly issued, thereby effectively solving the problem of image shooting The problem of portrait distortion occurs, which improves the quality of image shooting, and the operation is simple and convenient.

Acquiring the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the person;

Determine the center position of the person according to the position information of the person;

Acquiring the distance of the person in the current image relative to the center position of the current image according to the center position of the person and the center position of the current image;

When it is determined that the distance is greater than the set fourth threshold, it is determined that the target object has distortion of the human composition.

Here, the acquiring the face position information of the person in the current image in the framing frame in the shooting mode may use an existing face recognition algorithm to perform face detection on the current image in the framing frame in the shooting mode to obtain a face area, According to the point coordinates of the face area of the person, the face position information of the person is obtained. It should be noted that when performing face detection, the shape of the detected face area image is a rectangle, and the actual face area image of the person is located within the rectangle. Therefore, the position information of the face of the person can be The coordinates of the vertices. The acquiring the depth of field of the person in the current image in the framing frame in the shooting mode may be calculating the depth of field of the face of the person in the current image in the framing frame in the shooting mode using an existing single-shot algorithm or a dual-shot algorithm. The acquiring the position information of the person according to the face position information of the person and the depth of field may be based on the face position information of the person, acquiring the same or similar pixels of the person's face and the depth of field In the same area, the position information of the person is determined according to the area. It should be noted that, when detecting the human region, the shape of the detected human region image is a rectangle, and the actual image of the human is within the rectangle. Therefore, the position information of the human can be represented by the coordinates of the four vertices corresponding to the rectangle. After the position information of the person is determined, the center position of the person can be directly determined according to the position information of the person. For example, the four vertices characterizing the position information of the person are diagonally connected, and the intersection of the diagonal lines is the center position of the person. Since the center position of the current image is known, the acquiring the distance of the person in the current image relative to the center position of the current image may be acquiring the center position of the person and the current The vector value between the center positions of the image. Referring to FIG. 5, assuming that the center position of the current image is point o, the position information of the person is the area corresponding to the rectangle klmn, and the center position of the person is point p, then the person is relative to the current image The distance of the center position of can be expressed by the modulus | op | of the vector op. The fourth threshold can be set according to actual needs, for example, it can be set to 2.5 cm or 3 cm. When photographing an image, the character composition usually requires that the person should be near the center position of the framing frame. If the distance between the center position of the person and the center position of the current image is greater than the set fourth threshold, it means that the person is not It is in the vicinity of the center position of the framing frame, that is, the person has a positional deviation, which does not correspond to the person's composition, so it is determined that the target object has a person's composition distortion.

In this way, according to the position information of the face of the person in the current image in the framing frame and the depth of field of the face of the person in the shooting mode, the center position of the person is obtained, and the person relative to the position in the current image is determined When the distance between the center position of the current image meets the set character composition distortion condition, it is determined that there is a character composition distortion, and a message prompting to adjust the shooting of the character is promptly issued, thereby effectively solving the character composition distortion that occurs in image shooting Problem, improve the quality of image shooting, and the operation is simple and convenient.

Determine the area of the person according to the position information of the person;

Obtaining the ratio between the area of the person and the area of the current preview image according to the area of the person;

When it is determined that the ratio between the area of the person and the area of the current preview image is less than the set fifth threshold, it is determined that there is a person composition distortion in the target object.

Here, the acquiring the face position information of the person in the current image in the framing frame in the shooting mode may use an existing face recognition algorithm to perform face detection on the current image in the framing frame in the shooting mode to obtain a face area, According to the point coordinates of the face area of the person, the face position information of the person is obtained. It should be noted that when performing face detection, the shape of the detected face area image is a rectangle, and the actual face area image of the person is located within the rectangle. Therefore, the position information of the face of the person can be The coordinates of the vertices. The acquiring the depth of field of the person in the current image in the framing frame in the shooting mode may be calculating the depth of field of the face of the person in the current image in the framing frame in the shooting mode using an existing single-shot algorithm or a dual-shot algorithm. The acquiring the position information of the person according to the face position information of the person and the depth of field may be based on the face position information of the person, acquiring the same or similar pixels of the person's face and the depth of field In the same area, the position information of the person is determined according to the area. It should be noted that, when detecting the human region, the shape of the detected human region image is a rectangle, and the actual image of the human is within the rectangle. Therefore, the position information of the human can be represented by the coordinates of four vertices corresponding to the rectangle. After the position information of the person is determined, the area of the person can be directly determined according to the position information of the person. Please refer to FIG. 5 again, assuming that the position information of the person is the area corresponding to the rectangle klmn, the distance between point k and point m or the distance between point l and point n can be taken as the height of the person, The distance between the point l or the distance between the point m and the point n is taken as the width of the character, thereby obtaining the area of the character, that is, the product of the width of the character and the height of the character. Since the area of the current image is known, the ratio between the area of the person and the area of the current preview image can be determined. The fifth threshold can be set according to actual needs, such as 0.3 or 0.4. When the ratio between the area of the character and the area of the current preview image is less than the set fifth threshold, it means that the area occupied by the character in the current image is small, and it can be considered that the current image It is difficult to see the person clearly in the image. The image captured at this time may have distortion of the person's composition, and the shooting of the person needs to be adjusted.

In this way, according to the position information of the face of the person in the current image in the shooting frame and the depth of field of the face of the person in the shooting mode, the area of the person is obtained, and the area of the person in the current image is determined relative to When the area of the current image satisfies the set character composition distortion condition, it is determined that there is a character composition distortion, and a message prompting to adjust the shooting of the character is promptly issued, so as to effectively solve the problem of character composition distortion that occurs in image shooting, Improve the quality of image shooting, and the operation is simple and convenient.

Determine the center position of the face of the person according to the face position information of the person;

Acquiring the posture angle of the person relative to the current image in the current image according to the center position of the person and the center position of the face of the person;

When it is determined that the posture angle of the person relative to the current image is less than the set tilt angle threshold and the posture angle of the terminal is less than the tilt angle threshold, it is determined that the target object has posture distortion.

Here, the acquiring the face position information of the person in the current image in the framing frame in the shooting mode may use an existing face recognition algorithm to perform face detection on the current image in the framing frame in the shooting mode to obtain a face area, According to the point coordinates of the face area of the person, the face position information of the person is obtained. It should be noted that when performing face detection, the shape of the detected face area image is a rectangle, and the actual face area image of the person is located within the rectangle. Therefore, the position information of the face of the person can be The coordinates of the vertices. The acquiring the depth of field of the person in the current image in the framing frame in the shooting mode may be calculating the depth of field of the face of the person in the current image in the framing frame in the shooting mode using an existing single-shot algorithm or a dual-shot algorithm. The acquiring the position information of the person according to the face position information of the person and the depth of field may be based on the face position information of the person, acquiring the same or similar pixels of the person's face and the depth of field In the same area, the position information of the person is determined according to the area. It should be noted that, when detecting the human region, the shape of the detected human region image is a rectangle, and the actual image of the human is within the rectangle. Therefore, the position information of the human can be represented by the coordinates of the four vertices corresponding to the rectangle. After the face position information of the person is determined, the center position of the face of the person can be directly determined according to the face position information of the person. For example, the four vertices representing the position information of the face of the person are diagonally connected, and the intersection of the diagonal lines is the center position of the face of the person. After the position information of the person is determined, the center position of the person can be directly determined according to the position information of the person. For example, the four vertices characterizing the position information of the person are diagonally connected, and the intersection of the diagonal lines is the center position of the person. According to the center position of the face of the person and the center position of the person, the posture angle of the person in the current image relative to the current image can be directly determined. For example, the angle formed between the line between the center position of the face of the person and the center position of the person, and the horizontal line in the current image is taken as the pose of the person relative to the current image angle. Referring to FIG. 6, it is assumed that the position information of the person is the area corresponding to the rectangle klmn, the position information of the face of the person is the area corresponding to the rectangle abcd, the center position of the person is the point p, and the face of the person The center position of is the point q, and the posture angle of the person in the current image relative to the current image is the angle θ between the line between the point p and the point q and the horizontal line of the current image. When shooting images normally, the terminal is usually in a horizontal or vertical state, that is, the posture angle of the terminal is equal to or greater than the set tilt angle threshold, and the posture angle of the person relative to the current image should generally be greater than the set A tilt angle threshold, the tilt angle threshold may be set to 80 degrees, 85 degrees, or the like. If the posture angle of the person relative to the current image is less than the set tilt angle threshold, it may indicate that the terminal is tilted in viewfinder or the terminal has jitter. If it is determined that the posture angle of the terminal is also less than the set tilt angle threshold, There is a pose framing distortion on the person, and if it is determined that the terminal is only shaking, it means that there is no pose framing distortion on the person. Here, when it is determined that the posture angle of the terminal is also smaller than the set tilt angle threshold, the posture angle of the terminal may be equal to the posture angle of the person relative to the current image. The posture angle of the terminal and whether there is jitter in the terminal can be obtained by analyzing the terminal's own gyroscope data.

In this way, according to the position information of the face of the person in the current image in the framing frame and the depth of field of the face of the person in the shooting mode, the center position of the face of the person and the center position of the person are obtained, and the current image is determined When the posture angle of the person with respect to the current image satisfies the set posture distortion condition, it is determined that there is posture distortion, and a message prompting to adjust the shooting of the person is sent out in time to effectively solve the problem of image shooting The problem of posture distortion appears, which improves the quality of image shooting, and the operation is simple and convenient.

In an optional embodiment, the issuing of the prompt message includes:

The target object with posture distortion is identified by the set identification method, and a moving direction for the target object is prompted.

Here, the identification method can be set according to actual needs, for example, it can be set as a solid line frame or a dotted line frame, etc., or it can be set as a solid line frame or a dotted line frame of different colors. When the target object is a person's face and there is facial distortion, the target object with posture distortion is identified by the set identification method, and the direction of movement of the target object is prompted, including: The face of the person is identified by the set identification method, and it is suggested that the non-alert area of the viewfinder should be moved toward the target object. When the target object is a person's face and the person and there is a portrait distortion, the target object with posture distortion is identified by the set identification method, and a movement direction for the target object is prompted , Including: identifying the person with the set identification method, and prompting that the framing frame should be far away from the person or prompting to move the framing frame down and photographing the person from bottom to top. When the target object is a person and the distance between the person in the current image and the center position of the current image is too large, that is, there is a person's composition distortion, the target object that will have a posture distortion adopts the set The identification method identifies and prompts the moving direction of the target object, which includes: identifying the person using the set identification method, and prompting that the center area of the framing frame should be moved toward the target object. When the target object is a person and the ratio between the area of the person and the area of the current preview image is too small, that is, there is distortion of the person's composition, the target object that will have posture distortion adopts the set identification method Marking and prompting the moving direction of the target object include: marking the person using the set mark mode, and prompting that the framing frame should be close to the person. When the target object is a person and there is posture distortion, the target object with posture distortion is identified by using the set identification method, and the direction of movement of the target object is prompted, including: Use the set marking method to mark, and prompt that the viewfinder should not be tilted.

In this way, by identifying the target object with posture distortion and prompting the moving direction of the target object, a prompt to automatically correct posture distortion is realized, and the image shooting quality is further improved. In addition, through automatic prompting, non-professional photographers can also obtain good quality images.

In an optional embodiment, after determining that the target object has a set posture distortion, the method further includes:

Refusing to respond to the received shooting instruction until it is detected that there is no set posture distortion of the target object.

Here, after it is determined that the target object has the set posture distortion, if a shooting instruction is received, it will refuse to respond to the shooting instruction, that is, the target object will not be photographed until the target object is not detected again After the set posture is distorted, it will respond to the shooting instruction. When the terminal is a device such as a camera or a video camera, the refusal to respond to the received shooting instruction may be to lock the shutter.

In this way, by directly refusing to respond to the received shooting instruction when it is determined that the target object has the set posture distortion, it can effectively ensure that there is no posture distortion problem in the captured image, which further improves the image shooting quality.

To implement the above method, an image capturing device is also provided corresponding to an embodiment of the present invention. As shown in FIG. 7, the device includes:

The obtaining module 10 is used to obtain the position information of the target object in the current image in the framing frame in the shooting mode;

The processing module 11 is configured to acquire, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion;

The determining module 12 is configured to determine that the target object has the set posture distortion when the target parameter meets the set posture distortion condition;

The prompting module 13 is used to issue a prompting message; the prompting message is used to prompt to adjust the shooting of the target object.

In summary, in the image shooting device provided in the above embodiment, the target parameters for characterizing whether the target object has posture distortion are acquired according to the acquired position information of the target object in the current image in the framing frame in the shooting mode to determine the target When the parameter satisfies the set posture distortion condition, it is determined that the target object has the set posture distortion, and a prompt message is issued to remind the adjustment of the shooting of the target object. In this way, after it is determined that the target object in the current image in the viewfinder in the shooting mode has the posture distortion set, a message prompting to adjust the shooting of the target object is promptly issued, which effectively solves the problem of posture distortion in image shooting and improves Image quality.

In an alternative embodiment,

The obtaining module 10 is specifically used to obtain the position information of the face of the person in the current image in the viewfinder in the shooting mode;

The processing module 11 is specifically configured to determine the area of the face of the person and the area occupied by the face of the person in the set warning area according to the position information of the face of the person; and, according to the The area of the face of the person and the area occupied by the face of the person in the set warning area, determine the ratio between the area occupied by the face of the person in the set warning area and the area of the face of the person ;

The judging module 12 is specifically configured to determine the target when the ratio between the area occupied by the face of the person in the set warning area and the face area of the person is greater than the set first threshold Subject has facial distortion.

In an alternative embodiment,

The acquiring module 10 is specifically configured to: acquire the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the person;

The processing module 11 is specifically configured to: determine the face height of the person according to the face position information of the person;

The judgment module 12 is specifically configured to determine that the target object has a portrait when the ratio between the height of the face of the person and the height of the person is greater than the set second threshold and less than the set third threshold Proportional distortion.

In an alternative embodiment,

The acquiring module 10 is specifically configured to: acquire the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the face of the person;

The processing module 11 is specifically configured to: determine the center position of the person according to the position information of the person;

The judging module 12 is specifically configured to: when it is determined that the distance is greater than the set fourth threshold, determine that the target object has distortion of the human composition.

In an alternative embodiment,

The processing module 11 is specifically configured to determine the center position of the person according to the position information of the person;

The judging module 12 is specifically configured to: when the ratio between the area of the person and the area of the current preview image is less than the set fifth threshold, determine that there is a person composition distortion in the target object.

In an alternative embodiment,

The processing module 11 is specifically configured to: determine the center position of the face of the person according to the face position information of the person;

The judging module 12 is specifically configured to determine that when the posture angle of the person with respect to the current image is less than the set tilt angle threshold and the posture angle of the terminal is less than the tilt angle threshold, it is determined that the target object has a pose framing distortion.

In an optional embodiment, the processing module 11 is further configured to: refuse to respond to the received shooting instruction until it is detected that there is no set posture distortion of the target object.

In an alternative embodiment, the prompting module 12 is specifically configured to: mark the target object with posture distortion using the set identification method, and prompt the moving direction for the target object.

In this way, by identifying the target object with posture distortion and prompting the moving direction of the target object, a prompt to automatically correct posture distortion is realized, and the image shooting quality is further improved.

It should be noted that when the image capturing apparatus provided in the above embodiments implements the image capturing method, only the above-mentioned division of each program module is used as an example for illustration. In practical applications, the above-mentioned processing may be allocated by different program modules according to needs. That is, the internal structure of the image capturing device is divided into different program modules to complete all or part of the processing described above. In addition, the image capturing device provided in the above embodiment and the corresponding image capturing method embodiment belong to the same concept. For the specific implementation process, see the method embodiment, and details are not described here.

An embodiment of the present invention provides a terminal. As shown in FIG. 8, the terminal includes: a processor 310 and a memory 311 for storing a computer program that can run on the processor 310; wherein, the processor illustrated in FIG. 8 310 is not used to refer to the number of processors 310 as one, but only used to refer to the positional relationship of the processor 310 relative to other devices. In actual applications, the number of processors 310 may be one or more; Similarly, the memory 311 illustrated in FIG. 8 has the same meaning, that is, it is only used to refer to the positional relationship of the memory 311 relative to other devices. In actual applications, the number of the memory 311 may be one or more.

When the processor 310 is used to run the computer program, the following steps are performed:

Obtain the position information of the target object in the current image in the framing frame in shooting mode;

Acquiring target parameters characterizing whether the target object has posture distortion according to the position information of the target object;

When it is determined that the target parameter satisfies the set posture distortion condition, it is determined that the target object has the set posture distortion, and a prompt message is issued; the prompt message is used to prompt adjustment of the shooting of the target object.

In an alternative embodiment, when the processor 310 is further used to run the computer program, the following steps are performed:

The terminal also includes: at least one network interface 312. The various components in the terminal are coupled together via the bus system 313. It can be understood that the bus system 313 is used to implement connection and communication between these components. In addition to the data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, various buses are marked as the bus system 313 in FIG. 8.

Among them, the memory 311 may be a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM, Read Only Memory), programmable read-only memory (PROM, Programmable Read-Only Memory), erasable programmable read-only memory (EPROM, Erasable Programmable Read- Only Memory), Electrically Erasable Programmable Read-Only Memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), Magnetic Random Access Memory (FRAM, Ferromagnetic Random Access Memory), Flash Memory (Flash) Memory, Magnetic Surface Memory , Compact disc, or read-only compact disc (CD-ROM, Compact, Read-Only Memory); the magnetic surface memory can be a disk storage or a tape storage. The volatile memory may be a random access memory (RAM, Random Access Memory), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM, Static Random Access Memory), synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory), dynamic random access Memory (DRAM, Dynamic Random Access), Synchronous Dynamic Random Access Memory (SDRAM, Synchronous Dynamic Random Access Memory), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM, Double Data Rate, Synchronous Dynamic Random Access Random Access Memory), enhanced Type synchronous dynamic random access memory (ESDRAM, Enhanced Synchronous Dynamic Random Access Memory), synchronous connection dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), direct memory bus random access memory (DRRAM, Direct Rambus Random Access Random Access Memory ). The memory 311 described in this embodiment of the present invention is intended to include, but is not limited to, these and any other suitable types of memories.

The memory 311 in the embodiment of the present invention is used to store various types of data to support the operation of the terminal. Examples of these data include: any computer programs used to operate on the terminal, such as operating systems and applications; contact data; phone book data; messages; pictures; videos, etc. Among them, the operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application program may include various application programs, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. Here, the program for implementing the method of the embodiment of the present invention may be included in the application program.

This embodiment also provides a computer storage medium in which a computer program is stored. The computer storage medium may be a magnetic random access memory (FRAM, ferromagnetic random access memory), a read-only memory (ROM, Read Only Memory), programmable read-only memory (PROM, Programmable Read-Only Memory), erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory), electrically erasable programmable read-only memory (EEPROM, Electrically Erasable Programmable Read-Only Memory, Flash Memory, Magnetic Surface Memory, CD-ROM, or CD-ROM (Compact Disc Read-Only Memory), etc .; can also include one of the above-mentioned memories or Any combination of various devices, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

A computer storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the following steps are performed:

In an alternative embodiment, when the computer program is run by the processor, the following steps are also performed:

In an alternative embodiment, in an alternative embodiment, when the computer program is executed by the processor, the following steps are also performed:

The following further describes the embodiment of the present invention in detail through a specific example. In this example, the target object is a person. As shown in FIG. 9, it is an image capturing device provided by a specific embodiment of the present invention, including: a camera module 20, a main control module 21, a display module 22, a sound effect module 23, and a feedback module 24; wherein, the camera module 20 is used to obtain Framing image; the main control module 21 is mainly responsible for the overall process control, including acquiring the image obtained by the camera module and processing the image, and then outputting to the display module 22, at the same time can control the sound effect module 23 and the feedback module 24 to provide corresponding feedback ; The display module 22, sound effect module 23 and feedback module 24 are used to output corresponding feedback signals according to the control of the main control module 21.

Based on the above image shooting device, some suspected undesirable distortions can be actively reminded when taking pictures, mainly including: facial distortion reminder, portrait proportion distortion reminder, character composition distortion reminder, posture distortion distortion reminder, etc.

1) Reminder for facial distortion

In shooting portraits, especially self-portraits, when the face area is too close to the edge of the frame, it is easy to cause distortion and distortion of the face, that is, face distortion. In the viewfinder range, the warning area is defined in this embodiment. After obtaining the preview image by the camera module 20, the image is transmitted to the display module 22 through the main control module 21. Using the basic face detection algorithm, the range of each face within the framing range can be obtained. Suppose that the defined warning threshold is A, for example, 75%. When the proportion of a certain face in the warning area exceeds A, it is considered that the warning is triggered. At this time, a red frame can be used to identify a human face, and the sound control module 23 and the display module 22 can be controlled by the main control module 21 to alert the user of the risk of facial distortion.

In addition to being prone to facial distortions when taking photos with multiple people, self-portraits often show that the face area is too marginal. However, because the face area is relatively large when taking selfies, the distortion is only a small part, which may cause users to ignore those details when taking selfies. For this reason, in the case of self-portraits, a warning area is also established accordingly. When a human face accounts for a large proportion in the warning area, a distortion alarm will be issued.

2) Reminder of portrait distortion

When taking full-body shots, inexperienced photographers tend to disproportionately capture the proportion of the person being photographed. However, many female users have higher requirements for the proportion of the figure in the photo.

Here, the face is first detected by a face detection-related algorithm; then the dual-shot algorithm can be used to calculate the depth of field characteristics, and the body in the same plane as the face is selected to obtain the face height L and the person height H. Assuming that the set body ratio is M, calculate the size of L / H and M. Here, the optional base M is 8, which is the so-called 8 head body. If the acquired L / H is less than M, the framing interface will prompt the user that “the body proportion does not meet the preset standard”, display a red prompt frame around the person, and prompt the user to move the framing position down to take a portrait from the bottom and lock Dead shutter. When L / H is greater than M, the shutter is released and no prompt box is displayed.

When the reminder function for portrait distortion is turned on, it is possible to take a full-length photo instead of a full-length photo. By detecting whether the ratio of the head and the range of the framed portrait in the image coincide with the lower edge of the framing frame, it is decided whether to trigger the reminder function of portrait distortion. If the head-to-head ratio is too large, such as 1: 3 or 1: 4, it will be considered as a half-length photo, and the reminder function of portrait distortion will not be triggered at this time. If the detected lower edge of the body coincides with the lower edge of the framing frame, it will be determined that the body is beyond the range of the framing, not a full-body portrait, and the reminder function of portrait distortion will not be triggered at this time.

3) Reminder of distortion of character composition

When shooting large scenes, many of the provided composition tools are useless to most people, and it is easy to cause people to deviate from the center, the ratio of people and scenes is not correct, and even errors such as lens tilt.

After the main control module 21 obtains the portrait range, it can further obtain the center position of the entire human body, and calculate the vector position of the center position of the human body and the center position of the image. If the vector value is too large, it may be considered that the portrait position shifts seriously. The following situations may occur: the position of the person is too high, which is higher than the center horizontal line of the image; the position of the person is too low, which is far lower than the center horizontal line of the image; the portrait is too far away from the position of reasonable composition. In addition, if the size of the obtained portrait is significantly smaller than the size of the image scene, it can be considered that the portrait is difficult to see in the image, and a warning such as "the portrait is too small" will be prompted.

4) Reminder for posture distortion

Inexperienced photographers often have tilted framing when using terminals such as cameras. Through the main control module 21, the range of the person's face and the whole range of the person can be obtained, and their centers are respectively taken, and the central axis is obtained by connecting these two points, and then the portrait posture clip is obtained according to the center horizontal line of the image Angle α. Assuming that the posture tilt threshold β is set to 85 degrees, when α is smaller than β, it is considered that there is a case of excessive tilt of the portrait. At this time, additional gyroscope attitude data in the terminal can be obtained for confirmation. If the gyroscope status is stable and the tilt data of the two are basically the same, a warning of "Tilt tilt" will be displayed on the viewfinder interface. When the gyroscope data shows that the mobile phone has jitter, it is determined that the terminal holder did not stabilize the terminal during shooting, and it will prompt: "There is jitter in the picture, please hold it steady."

According to the method, device and computer storage medium provided in the above embodiments, according to the acquired location information of the target object in the current image in the framing frame in the shooting mode, the target parameter characterizing whether the target object has posture distortion is acquired, and the When the target parameter satisfies the set posture distortion condition, it is determined that the target posture has a set posture distortion, and a prompt message is issued to remind the user to adjust the shooting of the target target. In this way, after it is determined that the target object in the current image in the viewfinder in the shooting mode has the posture distortion set, a message prompting to adjust the shooting of the target object is promptly issued, which effectively solves the problem of posture distortion in image shooting and improves Image quality.

The above are only specific embodiments of the present invention, but the scope of protection of the present invention is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present invention. It should be covered by the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

An image shooting method applied to a terminal, characterized in that the method includes:

Obtain the position information of the target object in the current image in the framing frame in shooting mode;

Acquiring target parameters characterizing whether the target object has posture distortion according to the position information of the target object;

When it is determined that the target parameter satisfies the set posture distortion condition, it is determined that the target object has the set posture distortion, and a prompt message is issued; the prompt message is used to prompt adjustment of the shooting of the target object.
The method according to claim 1, wherein the acquiring position information of the target object in the current image in the framing frame in the shooting mode includes:

Obtain the face position information of the person in the current image in the framing frame in shooting mode;

The acquiring, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion includes:

Determine the area of the face of the person and the area occupied by the face of the person in the set warning area according to the position information of the face of the person;

According to the area of the face of the person and the area occupied by the face of the person in the set warning area, determine the area between the area occupied by the face of the person in the set warning area and the area of the face of the person Ratio

When it is determined that the target parameter satisfies the set posture distortion condition, determining that the target object has the set posture distortion includes:

When it is determined that the ratio between the area occupied by the face of the person in the set warning area and the face area of the person is greater than the set first threshold, it is determined that the target object has facial distortion.
The method according to claim 1, wherein the acquiring the position information of the target object in the current image in the framing frame in the shooting mode includes:

Acquiring the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the person;

Acquiring the position information of the person according to the position information of the face of the person and the depth of field;

The acquiring, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion includes:

Determine the face height of the person according to the face position information of the person;

Acquiring the height of the person according to the position information of the person;

Determining the ratio between the height of the face of the person and the height of the person according to the height of the face of the person and the height of the person;

When it is determined that the target parameter satisfies the set posture distortion condition, determining that the target object has the set posture distortion includes:

When it is determined that the ratio between the height of the face of the person and the height of the person is greater than the set second threshold and less than the set third threshold, it is determined that the target object has a portrait distortion.
The method according to claim 1, wherein the acquiring position information of the target object in the current image in the framing frame in the shooting mode includes:

Acquiring the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the face of the person;

Acquiring the position information of the person according to the position information of the face of the person and the depth of field;

The acquiring, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion includes:

Determine the center position of the person according to the position information of the person;

Obtaining the distance of the person in the current image relative to the center position of the current image according to the center position of the person and the center position of the current image;

When it is determined that the target parameter satisfies the set posture distortion condition, determining that the target object has the set posture distortion includes:

When it is determined that the distance is greater than the set fourth threshold, it is determined that the target object has distortion of the human composition.
The method according to claim 1, wherein the acquiring position information of the target object in the current image in the framing frame in the shooting mode includes:

Acquiring the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the person;

Acquiring the position information of the person according to the position information of the face of the person and the depth of field;

The acquiring, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion includes:

Determine the area of the person according to the position information of the person;

Obtaining the ratio between the area of the person and the area of the current preview image according to the area of the person;

When it is determined that the target parameter satisfies the set posture distortion condition, determining that the target object has the set posture distortion includes:

When it is determined that the ratio between the area of the person and the area of the current preview image is less than the set fifth threshold, it is determined that there is a person composition distortion in the target object.
The method according to claim 1, wherein the acquiring position information of the target object in the current image in the framing frame in the shooting mode includes:

Acquiring the position information of the face of the person in the current image in the framing frame in the shooting mode and the depth of field of the person;

Acquiring the position information of the person according to the position information of the face of the person and the depth of field;

The acquiring, according to the position information of the target object, target parameters characterizing whether the target object has posture distortion includes:

Determine the center position of the face of the person according to the face position information of the person;

Determine the center position of the person according to the position information of the person;

Acquiring the posture angle of the person relative to the current image in the current image according to the center position of the person and the center position of the face of the person;

When it is determined that the target parameter satisfies the set posture distortion condition, determining that the target object has the set posture distortion includes:

When it is determined that the posture angle of the person relative to the current image is less than the set tilt angle threshold and the posture angle of the terminal is less than the tilt angle threshold, it is determined that the target object has posture distortion.
The method according to any one of claims 1 to 6, wherein after determining that the target object has a set posture distortion, the method further includes:

Refusing to respond to the received shooting instruction until it is detected that there is no set posture distortion of the target object.
The method according to any one of claims 1 to 6, wherein the issuing of the prompt message includes:

The target object with posture distortion is identified by the set identification method, and a moving direction for the target object is prompted.
An image shooting device, characterized in that it includes:

The acquisition module is used to acquire the position information of the target object in the current image in the framing frame in the shooting mode;

A processing module, configured to acquire target parameters characterizing whether the target object has posture distortion according to the position information of the target object;

The judging module is used to determine that the target object has the set posture distortion when the target parameter satisfies the set posture distortion condition;

The prompting module is used to issue a prompting message; the prompting message is used to prompt to adjust the shooting of the target object.
A terminal, characterized in that the terminal includes a processor and a memory for storing a computer program that can run on the processor; wherein,

When the processor is used to run the computer program, it executes the steps of the image capturing method according to any one of claims 1 to 8.
A computer storage medium, characterized in that a computer program is stored in the computer storage medium, and when the computer program is executed by a processor, the steps of the image capturing method according to any one of claims 1 to 8 are realized.