WO2015074261A1

WO2015074261A1 - Method for saving photographed image, and electronic device

Info

Publication number: WO2015074261A1
Application number: PCT/CN2013/087725
Authority: WO
Inventors: 魏代玉; 罗巍; 邓斌
Original assignee: 华为终端有限公司
Priority date: 2013-11-22
Filing date: 2013-11-22
Publication date: 2015-05-28
Also published as: CN105453533B; CN105453533A; CN110121030A; CN110121030B

Abstract

Disclosed are a method for saving a photographed image, and an electronic device. The method comprises: determining whether a portrait of a photographed person in an image obtained on a first time point meets a storage condition; and after the portrait of the photographed person in the image obtained on the first time point does not meet the storage condition, selecting at least one image meeting the storage condition in a set time range after the first time point and/or before the first time point, and storing the at least one image meeting the condition.

Description

Method for saving captured image and electronic device

The present invention relates to the field of image processing technologies, and in particular, to a method for saving a captured image and an electronic device. Background technique

With the continuous development of science and technology, electronic technology has also developed rapidly, and there are more and more types of electronic products. People also enjoy the convenience brought by the development of science and technology. Nowadays, people can enjoy the comfortable life brought by the development of science and technology through various types of electronic devices.

For example, electronic devices such as smartphones, tablets, or digital cameras have image collection capabilities that allow users to take images anytime, anywhere, and retain the moments of life. In the process of taking pictures by the user using these electronic devices, taking a portrait of a person as an example, if the eyes of the photographer appear in the captured image are closed at the moment of photographing due to flash or blinking, or due to shaking of the electronic device at the moment of photographing If the subject's portrait is blurred or not, the user needs to re-shoot and spend more time. In some specific situations, such as shooting athletes participating in sports, if the image obtained by the shooting is not Meet the requirements, even unable to re-shoot.

Therefore, in the prior art, when an electronic device such as a smartphone, a tablet computer, or a digital camera captures an image, there is a technical problem that the user needs to take time to retake the image because the captured image does not satisfy the requirement. Summary of the invention

The embodiment of the invention provides a method for saving a captured image and an electronic device for solving the problem that the captured image does not meet the requirements when the electronic device such as a smart phone, a tablet computer or a digital camera in the prior art captures an image. The technical problem that makes it take time for the user to take time to shoot again. A first aspect of the present invention provides a method of saving a captured image, comprising: determining whether a portrait of a subject in an image obtained at a first time satisfies a saving condition; and wherein the image is obtained in the image obtained at the first time After the portrait of the photographer does not satisfy the saving condition, at least one image that satisfies the saving condition is selected from the first time period and/or a set time period before the first time, and is saved and satisfied. Save at least one image of the condition.

With reference to the first aspect, in a first possible implementation, the determining whether the portrait of the photographer in the image obtained at the first time meets the saving condition is specifically: determining that the image obtained at the first moment is photographed Whether the eyes of the person are open, wherein, when the subject's eyes are closed, determining that the portrait of the subject in the image obtained at the first moment does not satisfy the saving condition; and/or determining the first Whether the portrait of the subject is blurred in the image obtained at the time, wherein when the portrait of the subject is blurred in the image obtained at the first time, the subject in the image obtained at the first moment is determined The portrait does not satisfy the preservation condition.

With reference to the first possible implementation manner, in a second possible implementation manner, before the determining whether the eye of the photographer is opened in the image obtained at the first moment, the method further includes: Determining, at least one image obtained before the first time, that the subject's eyes are in a blinking state or a closed eye state, wherein when the subject's eyes are in the blinking state, performing steps : Judging whether the subject's eyes in the image obtained at the first moment are split.

In the third possible implementation manner, in the third possible implementation manner, determining whether the eye of the captured person in the image obtained by the first moment is split includes: acquiring the first moment Performing pre-processing on the face region of the subject in the image; locating at least two feature points of the face region, and obtaining at least two features extracted from the region where the at least two feature points are located a feature vector, the at least two feature points including at least an eye feature point and an eye corner feature point; determining, based on the feature vector, whether the subject's eyes in the image obtained at the first time are split.

With reference to the first possible implementation manner, in a fourth possible implementation manner, the determining whether the portrait of the subject in the image obtained by the first moment is blurred, specifically includes: The image of the subject in the obtained image is edge-detected to obtain a local maximum a plurality of first intensity values corresponding to the plurality of edge points; reducing the image obtained at the first time by a preset ratio, and performing edge detection on the portrait of the subject in the reduced image to obtain a local maximum a plurality of second intensity values corresponding to the plurality of edge points of the value; determining whether a difference between the second intensity value corresponding to each of the plurality of edge points and the first intensity value is greater than one a threshold value, wherein, when a difference between the second intensity value and the first intensity value is greater than the threshold value, determining that each edge point is blurred; determining that the plurality of edge points are blurred Whether the number of edge points is greater than a preset value, wherein when the number of the blurred edge points is greater than the preset value, determining that the portrait of the subject in the image obtained at the first moment is blurred.

A second aspect of the present invention provides an electronic device, including: an image collection unit disposed on the casing; and a processing unit connected to the image collection unit for determining the image collection unit Whether the portrait of the subject in the image obtained at the first time satisfies the saving condition, and after the portrait of the subject does not satisfy the saving condition in the image obtained at the first time, from the first moment At least one image that satisfies the saving condition is selected after a set time period before the first time and/or the first time, and at least one image satisfying the saving condition is saved.

With reference to the second aspect, in a first possible implementation, the processing unit is specifically configured to determine whether an eye of the photographer in the image obtained at the first moment is split, wherein, in the image of the photographer When the eye is closed, determining that the portrait of the subject in the image obtained at the first moment does not satisfy the saving condition, and/or determining whether the portrait of the subject in the image obtained at the first moment is blurred, wherein When the portrait of the subject is blurred in the image obtained at the first time, it is determined that the portrait of the subject in the image obtained at the first time does not satisfy the saving condition.

With reference to the first possible implementation manner, in a second possible implementation manner, the processing unit is further configured to: before the eye of the photographer is opened in the image obtained by determining the first moment, based on At least one image obtained before the first moment determines that the subject's eyes are in a blinking state or a closed eye state.

With reference to the first possible implementation manner, in a third possible implementation, the processing unit is specifically configured to perform pre-processing on a face area of the subject in an image obtained at the first moment, and Locating at least two feature points of the face region and obtaining from the at least two feature points a feature vector composed of at least two features extracted by the region, the at least two feature points including at least an eye feature point and an eye feature point, and determining, according to the feature vector, the image obtained at the first moment Whether the eyes of the photographer are open.

With reference to the first possible implementation manner, in a fourth possible implementation, the processing unit is specifically configured to perform edge detection on the portrait of the subject in the image obtained at the first moment to obtain a local pole a plurality of first intensity values corresponding to the plurality of edge points of the large value, and reducing the image obtained at the first time by a preset ratio, and performing edge detection on the portrait of the subject in the reduced image, a plurality of second intensity values corresponding to the plurality of edge points of the local maximum value, and determining the second intensity value corresponding to each of the plurality of edge points and the first intensity value Whether the difference is greater than a threshold value, wherein, when the difference between the second intensity value and the first intensity value is greater than the threshold value, determining that each edge point is blurred, and determining the plurality of Whether the number of blurred edge points in the edge point is greater than a preset value, wherein, when the number of the edge points of the blur is greater than the preset value, determining the subject in the image obtained at the first moment of Like a blur.

One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

Since it is determined whether the portrait of the subject in the image obtained at the first time satisfies the saving condition, and the portrait of the subject in the image obtained at the first time does not satisfy the saving condition, after the first time and/or the first time In the previous set time period, at least one image satisfying the saving condition is selected, and a technical solution of at least one image satisfying the saving condition is saved, thereby avoiding the image obtained at the first moment appearing at the moment of being photographed by the photographer's eyes. The situation that the closed image or the image blur is not satisfactory, so that the electronic device such as a smart phone, a tablet computer or a digital camera in the prior art has an image that is not satisfied by the captured image, so that the user needs to spend the image. The technical problem of time to retake the shooting achieves the technical effect of saving the time taken by the user to retake the image. DRAWINGS

1 is a flowchart of a method for saving a captured image according to an embodiment of the present invention;

2 is a flowchart of an operation of an electronic device for applying a method for saving a captured image according to an embodiment of the present invention;

FIG. 3 is a functional block diagram of an electronic device according to an embodiment of the present invention. detailed description

The embodiment of the present invention solves the problem that the electronic device such as a smart phone, a tablet computer or a digital camera in the prior art has an image that does not meet the requirements when the image is captured by providing a method for saving a captured image and an electronic device. The technical problem that makes it take time for the user to take time to shoot again.

The technical solution in the embodiment of the present invention is to solve the above technical problem. The general idea is as follows: First, it is determined whether the portrait of the photographer in the image obtained at the first moment satisfies the saving condition; and then, the image obtained at the first moment is photographed. After the portrait of the person does not satisfy the saving condition, at least one image that satisfies the saving condition is selected and saved from a set time period after the first time and/or within a set time period before the first time, for example, 2 seconds or 3 seconds, and the like. At least one image that satisfies the save condition.

It can be seen from the above that, since it is determined whether the portrait of the subject in the image obtained at the first time satisfies the saving condition, and the portrait of the subject in the image obtained at the first time does not satisfy the saving condition, the first moment And then selecting at least one image that satisfies the saving condition and storing a technical solution that satisfies at least one image of the saving condition in a set period of time before the first time, and avoiding that the image obtained at the first moment is taken. When the eyes of the person are closed at the moment of photographing or the image is blurred, the image is not satisfied, so that the electronic device such as a smart phone, a tablet computer or a digital camera in the prior art has an image that is not captured due to the captured image. A technical problem that satisfies the requirements and requires the user to spend time re-shooting, thereby saving the time taken by the user to retake the image.

In order to better understand the above technical solutions, the following description will be combined with the drawings and specific implementations. The above technical solution will be described in detail.

An embodiment of the present invention provides a method for saving a captured image. Referring to FIG. 1 , FIG. 1 is a flowchart of a method for saving a captured image according to an embodiment of the present invention. As shown in FIG. 1 , the method includes:

S 1: determining whether the portrait of the subject in the image obtained at the first moment satisfies the storage condition;

S2: after the portrait of the photographer in the image obtained at the first moment does not satisfy the saving condition, select at least one image that satisfies the saving condition from a set time period after the first time and/or before the first time, And save at least one image that satisfies the save condition.

Please refer to FIG. 2 . FIG. 2 is a flowchart showing the operation of the electronic device according to the method for saving a captured image according to an embodiment of the present invention. In the following part, the implementation of the present invention will be described in detail with reference to FIG. 1 and FIG. 2 . The method of saving a captured image and an electronic device provided by the example.

As shown in FIG. 2, an electronic device such as a smart phone, a tablet computer, or a digital camera that saves a method for capturing an image according to an embodiment of the present invention first calls an image collection unit such as a camera of an electronic device when capturing an image, and then Displaying the image collected by the image collection unit on the preview screen of the electronic device. Of course, it is necessary to save a plurality of preview images in the set time period, and the set time period may be, for example, 2 seconds, 3 seconds, etc. For example, the saved multiple preview images may be a full size image, and a person skilled in the art can set a specific value of the set time period according to actual conditions, which is not limited herein.

According to the multiple preview images saved in the set time period, an electronic device such as a smart phone, a tablet computer or a digital camera can determine whether there is a face in the captured image, specifically, it is possible to train a classifier offline, the classifier The meaning is that the feature value of the image sub-window can be calculated. When the feature value in the sub-window satisfies the threshold condition, the sub-window can be judged to include the human face by the electronic device, otherwise the face is not included.

When the classifier detects the image, the image data is continuously reduced according to a certain ratio to obtain a scaled image of different scales, and then on each scale image, the sub-window of all positions is exhausted, and the size of the sub-window is determined according to The characteristics of the classifier are determined, generally 20*20 (the unit can be a pixel). For each sub-window, the classifier is used to calculate the feature value of the sub-window. When the feature value satisfies the threshold condition, the window can be It is judged by the electronic device to include a human face, otherwise it is not included The face, finally searches all the child windows of all scale images, and merges the face results of all the child windows of the full image to determine whether the face is included in the captured image.

Of course, in an actual application, the electronic device may determine a human face in the captured image in the case that each of the saved multiple preview images includes a human face, or may be a preview image including a human face. If there is more than a certain number of cases, the face of the captured image is determined, and no limitation is imposed here.

As shown in Fig. 2, after determining the face of the captured image, the electronic device such as a smartphone, tablet or digital camera can enter the face mode. Of course, in addition to automatically entering the face mode by the electronic device such as a smart phone, a tablet computer, or a digital camera according to the judgment result of the saved multiple preview images, the user may trigger the electronic device to enter the face by pressing an operation button. The mode, or the user touches a touch button on the touch screen of the electronic device to trigger the electronic device to enter the face mode, and no limitation is imposed herein.

Of course, if there is no face in the captured image, or the user does not control the electronic device to enter the face mode, the electronic device saves the photo according to the normal mode, and will not be described here.

The method for saving the captured image provided by the embodiment of the present invention further includes: before the first moment, the method for saving the captured image provided by the embodiment of the present invention, after determining that the captured image includes the face image, according to the plurality of preview images saved in the set time period. Obtain at least one image to determine that the subject's eyes are in a blinking state or a closed eye state.

Specifically, in the saved plurality of preview images, if the number of preview images closed by the photographer exceeds a certain ratio, such as more than 80%, etc., it indicates that the subject's eyes are in a closed-eye state; The number of preview images of the photographer blinking exceeds a certain percentage, such as more than 60%, etc., indicating that the subject's eyes are in a blinking state.

In the specific implementation process, it is determined that the subject's eyes in the image obtained at the first moment are blinking or closing the eyes, and specifically:

First, pre-processing the face region of the subject in the image obtained at the first moment, such as illumination correction, scaling to a certain ratio, etc., and then locating at least two feature points of the face region, and obtaining at least two features a feature vector composed of at least two features extracted from the region where the point is located, to The two feature points include at least the eye feature point and the eye feature point. Of course, the eyebrows, the face muscles, and the like may be included. Finally, the feature vector is classified and subjected to regression processing, and the degree of the degree of the blink is calculated, thereby being able to determine In the preview image, the subject's eyes are blinked or closed, for example, the degree of closure of the upper and lower eyelids of the eye (ie, the value of the blink) exceeds 60%, thereby determining that the preview image is The photographer's eyes are closed eyes. Of course, by the introduction of the embodiment, those skilled in the art can set the blink value to a suitable numerical range according to the actual situation, so as to meet the actual situation, no longer I will go into details.

Of course, the method for determining that the subject's eyes in the preview image is blinking or closing the eyes is only an example. Through the introduction of the embodiment, those skilled in the art can select according to the actual situation. Other suitable methods for judging the subject's eyes in the preview image are blinking or closing the eyes, and will not be described again here.

Referring to FIG. 1 and FIG. 2 simultaneously, after determining that the subject's eyes are blinked in the image captured at the first moment, the method for saving the captured image provided by the embodiment of the present invention proceeds to step S1, that is, determining the first Whether the portrait of the subject in the image obtained at the time satisfies the storage condition.

In the actual application, the first moment may be the moment when the save command is received, such as the moment when the user presses the shutter button of the electronic device by the finger, or clicks or touches the camera button of the electronic device, or may be set by the user. The moment of automatic photographing is not limited here; the saving condition may be "the image of the photographer is opened in the image obtained at the first moment", or "the portrait of the photographer in the image obtained at the first moment is clear." "Of course, the saving condition can also be set by the user according to the actual situation to meet the user's use requirements in different usage scenarios. For example, the image that the photographer desires to obtain is a closed-eye image, and the user can save the setting. The condition is "the eyes of the subject in the image obtained at the first moment are closed", and no limitation is imposed here.

In the specific implementation process, it is determined whether the portrait of the captured person in the image obtained at the first moment satisfies the saving condition. Specifically, it may be: determining whether the eye of the captured person in the image obtained at the first moment is opened, wherein When the subject's eyes are closed, it is determined whether the image obtained at the first moment does not satisfy the saving condition, and/or whether the portrait of the subject in the image obtained at the first moment is blurred, wherein, in the image obtained at the first moment, When the portrait of the photographer is blurred, determine the first moment to get The image does not satisfy the save condition.

It is judged whether or not the subject's eyes are opened in the image obtained at the first time, and it can be judged based on whether or not the subject's eyes in the preview image are opened in a similar manner as described in the foregoing section, and will not be described again.

Determining whether the portrait of the subject in the image obtained at the first time is blurred may be performing edge detection on the portrait of the subject in the image obtained at the first time, and obtaining a plurality of plurality of edge points corresponding to the local maximum An intensity value, and reducing the image obtained at the first moment by a preset ratio, and performing edge detection on the image of the captured person in the reduced image to obtain a plurality of second intensities corresponding to the plurality of edge points of the local maximum value a value, and then determining whether a difference between the second intensity value corresponding to each edge point of the plurality of edge points and the first intensity value is greater than a threshold value, wherein a difference between the second intensity value and the first intensity value is greater than a threshold When the limit value is determined, it is determined that each edge point is blurred, and finally determining whether the number of blurred edge points in the plurality of edge points is greater than a preset value, wherein when the number of blurred edge points is greater than a preset value, determining the first The portrait of the subject in the image obtained at any time is blurred.

Through the introduction of this embodiment, the person skilled in the art can set the threshold value to a suitable value according to the actual situation, to meet the needs of the actual situation, and will not be described herein.

Of course, the method for determining whether the portrait of the subject in the image obtained at the first time is blurred is only an example. Through the introduction of the embodiment, those skilled in the art can select other according to the actual situation. A suitable way to judge whether the portrait of the subject in the image obtained at the first moment is blurred is not described herein.

The above section describes two forms for judging whether or not the portrait of the subject in the image obtained at the first time satisfies the saving condition. With the introduction of the embodiment, those skilled in the art can deduce the image obtained at the first moment. Whether the portrait of the subject satisfies other forms of preservation conditions will not be described here.

Continuing to refer to FIG. 1 and FIG. 2, after the step S1, after determining that the portrait of the subject in the image obtained at the first time does not satisfy the saving condition, the method for saving the captured image provided by the embodiment of the present invention proceeds to step S2, that is, : selecting at least one image that satisfies the saving condition from a set time period after the first time and/or before the first time, and saving at least one image that satisfies the saving condition. Specifically, since the first time is the time when the save command is received, for example, the time when the user presses the shutter, or the time of the set automatic photographing, after the first time and/or before the first time During the set time period, that is, at least another image that meets the storage condition is selected at other times near the first time, a person skilled in the art can set a specific value of the set time period, for example, 2 seconds or according to actual conditions. 3 seconds, etc., and save the selected at least one image that satisfies the saving condition, for example, it can be saved in the memory card of the electronic device.

Judging whether the image in the set time period after the first time and/or before the first time satisfies the preservation condition is similar to the method principle described in the foregoing section, and for the sake of brevity of the description, it will not be described again here.

It can be seen from the above that, since it is determined whether the portrait of the subject in the image obtained at the first time satisfies the saving condition, and the portrait of the subject in the image obtained at the first time does not satisfy the saving condition, the first moment And then selecting at least one image that satisfies the saving condition and storing a technical solution that satisfies at least one image of the saving condition in a set period of time before the first time, and avoiding that the image obtained at the first moment is taken. When the eyes of the person are closed at the moment of photographing or the image is blurred, the image is not satisfied, so that the electronic device such as a smart phone, a tablet computer or a digital camera in the prior art has an image that is not captured due to the captured image. The technical problem that the user needs to spend time re-shooting is satisfied, and the technical effect of saving the time taken by the user to retake the image is realized.

Based on the same inventive concept, an embodiment of the present invention further provides an electronic device. In an actual application, the electronic device may be a smart phone, a tablet computer, or a digital camera, which is not limited herein.

Please refer to FIG. 3. FIG. 3 is a functional block diagram of an electronic device according to an embodiment of the present invention. As shown in FIG. 3, the electronic device includes: an image collection unit 301, and a processing unit 302 connected to the image collection unit 301. And determining whether the portrait of the photographer in the image obtained by the image collection unit 301 at the first time satisfies a saving condition, wherein the first time is a time when the save instruction is received, and is captured in the image obtained at the first time After the portrait of the person does not satisfy the saving condition, at least one image satisfying the saving condition is selected from a set time period after the first time and/or before the first time, and at least one image satisfying the saving condition is saved. The image collection unit 301 can be a camera, such as a lens, a CCD sensor or a CMOS sensor, an ISP (Image Signal Processing), and the like. The processing unit 302 can be a CPU (Central Processing Unit). It can be an ARM-integrated processor integrated with ISP or an X86-based processor, etc., and is not limited here.

In the embodiment of the present invention, the processing unit 302 is specifically configured to determine whether the eyes of the photographer in the image obtained at the first moment are opened, wherein when the eyes of the photographer are closed, it is determined that the image obtained at the first moment is The portrait of the photographer does not satisfy the saving condition, and/or determines whether the portrait of the subject in the image obtained at the first moment is blurred, wherein the first moment is determined when the portrait of the photographer is blurred in the image obtained at the first moment The portrait of the subject in the obtained image does not satisfy the saving condition.

In the embodiment of the present invention, the processing unit 302 is further configured to determine, according to the at least one image obtained before the first moment, before the eye of the photographer is split in the image obtained at the first moment, determining the subject's The eyes are in a blinking state or in a closed eye state.

In the embodiment of the present invention, the processing unit 302 is specifically configured to preprocess the face region of the captured image in the image obtained at the first time, and locate at least two feature points of the face region, and obtain at least two a feature vector composed of at least two features extracted from a region where the feature point is located, at least two feature points including at least an eye feature point and an eye feature point, and based on the feature vector, determining an eye of the captured person in the image obtained at the first moment Whether to open it.

In the embodiment of the present invention, the processing unit 302 is specifically configured to perform edge detection on the portrait of the captured person in the image obtained at the first moment, and obtain a plurality of first intensity values corresponding to the plurality of edge points of the local maximum value, and The image obtained at the first moment is reduced according to a preset ratio, and the image of the captured person in the reduced image is edge-detected, and a plurality of second intensity values corresponding to the plurality of edge points of the local maximum value are obtained, and the plurality of judgments are determined. Whether the difference between the second intensity value corresponding to each edge point and the first intensity value is greater than a threshold value, wherein when the difference between the second intensity value and the first intensity value is greater than a threshold value, determining Each edge point is blurred, and it is determined whether the number of blurred edge points in the plurality of edge points is greater than a preset value, wherein when the number of blurred edge points is greater than a preset value, determining an image obtained at the first moment The portrait of the photographer is blurred.

The method of saving the captured image in the electronic device in this embodiment and the foregoing embodiment is based on the same In the two aspects of the inventive concept, the implementation process of the method has been described in detail above, so that those skilled in the art can clearly understand the structure and implementation process of the electronic device in this embodiment according to the foregoing description, for the specification. The simplicity is not repeated here.

The technical solution in the above embodiment of the present invention has at least the following technical effects or advantages: since it is determined whether the portrait of the subject in the image obtained at the first moment satisfies the saving condition, and the photographer is photographed in the image obtained at the first moment. After the portrait is not satisfied with the saving condition, at least one image satisfying the saving condition is selected from a set time period after the first time and/or before the first time, and a technical solution of saving at least one image satisfying the saving condition is saved. The image obtained at the first moment is prevented from being closed by the photographer's eyes at the moment of photographing or the image is blurred, so that the electronic device such as a smart phone, a tablet computer or a digital camera is photographed in the prior art. In the case of an image, there is a technical problem that the user needs to take time to retake the image because the captured image does not satisfy the requirement, and the technical effect of saving the time taken by the user to retake the image is realized.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can be embodied in the form of one or more computer program products embodied on a computer-usable storage medium (including but not limited to disk storage, CD-ROM, optical storage, etc.) in which computer usable program code is embodied.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowcharts and/or block diagrams, and combinations of flow and/or blocks in the flowcharts and/or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

These computer program instructions can also be stored in a bootable computer or other programmable data processing device. In a computer readable memory that operates in a particular manner, causing instructions stored in the computer readable memory to produce an article of manufacture comprising instruction means implemented in one or more flows and/or block diagrams of the flowchart The function specified in the box or in multiple boxes.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram. The spirit and scope of the invention. Thus, it is intended that the present invention cover the modifications and variations of the inventions

Claims

Rights request

1. A method of saving captured images, characterized by including:

Determine whether the portrait of the subject in the image obtained at the first moment satisfies the preservation condition; after the portrait of the subject in the image obtained at the first moment does not meet the preservation condition, from the first moment onwards And/or select at least one image that satisfies the saving condition within a set time period before the first moment, and save at least one image that satisfies the saving condition.

2. The method of claim 1, wherein the step of determining whether the portrait of the subject in the image obtained at the first moment satisfies the preservation conditions is as follows:

Determine whether the subject's eyes in the image obtained at the first moment are open, wherein, when the subject's eyes are closed, it is determined that the portrait of the subject in the image obtained at the first moment does not meet the requirements. the storage conditions described above; and/or

Determine whether the portrait of the subject in the image obtained at the first time is blurred, wherein, when the portrait of the subject in the image obtained at the first time is blurred, determine whether the portrait obtained at the first time is blurred. The portrait of the subject in the image does not meet the storage conditions.

3. The method of claim 2, wherein before determining whether the subject's eyes are open in the image obtained at the first moment, the method further includes:

Based on at least one image obtained before the first moment, it is determined that the subject's eyes are in an eye-open state or a closed-eye state, wherein, when the subject's eyes are in the eye-open state, Execution steps: Determine whether the subject's eyes are open in the image obtained at the first moment.

4. The method of claim 2, wherein determining whether the subject's eyes are open in the image obtained at the first moment specifically includes:

Preprocess the face area of the photographed person in the image obtained at the first moment; locate at least two feature points of the face area, and obtain the region where the at least two feature points are located. A feature vector composed of at least two features, the at least two feature points at least include eye feature points and eye corner feature points;

Based on the feature vector, determine whether the subject's eyes in the image obtained at the first moment are Are your eyes open?

5. The method of claim 2, wherein the determining whether the portrait of the subject in the image obtained at the first moment is blurred specifically includes:

Perform edge detection on the portrait of the subject in the image obtained at the first moment, and obtain multiple first intensity values corresponding to multiple edge points of local maximum values;

Reduce the image obtained at the first moment according to a preset ratio, perform edge detection on the portrait of the subject in the reduced image, and obtain a plurality of second values corresponding to the plurality of edge points with local maximum values. intensity value;

Determine whether the difference between the second intensity value corresponding to each edge point in the plurality of edge points and the first intensity value is greater than a threshold value, wherein, between the second intensity value and the first intensity value, When the difference between intensity values is greater than the threshold value, each edge point is determined to be blurred;

Determine whether the number of blurred edge points among the plurality of edge points is greater than a preset value, wherein, when the number of blurred edge points is greater than the preset value, determine whether the number of blurred edge points in the image obtained at the first moment is The subject's portrait is blurry.

6. An electronic device, characterized by including:

Image collection unit;

A processing unit, connected to the image collection unit, used to determine whether the portrait of the subject in the image obtained by the image collection unit at the first moment meets the storage conditions, and in the image obtained at the first moment After the portrait of the photographed person does not meet the storage condition, select at least one image that satisfies the storage condition from a set time period after the first moment and/or before the first moment, and save at least one image that meets the saving conditions.

7. The electronic device according to claim 6, wherein the processing unit is specifically configured to determine whether the subject's eyes are open in the image obtained at the first moment, wherein, when the subject is photographed, When the eyes are closed, it is determined that the portrait of the subject in the image obtained at the first moment does not meet the storage condition, and/or it is determined whether the portrait of the subject in the image obtained at the first moment is blurred, Wherein, when the portrait of the subject in the image obtained at the first moment is blurred, it is determined that the portrait of the subject in the image obtained at the first moment does not satisfy the storage condition.

8. The electronic device of claim 7, wherein the processing unit is further configured to, before determining whether the subject's eyes are open in the image obtained at the first moment, based on the At least one image obtained before the first moment determines whether the subject's eyes are open or closed.

9. The electronic device according to claim 7, wherein the processing unit is specifically configured to preprocess the face area of the photographed person in the image obtained at the first moment, and locate the face area of the photographed person. At least two feature points of the human face area, and obtain a feature vector composed of at least two features extracted from the area where the at least two feature points are located, the at least two feature points at least include eye feature points and eye corner features point, and based on the feature vector, determine whether the eyes of the subject in the image obtained at the first moment are open.

10. The electronic device according to claim 7, wherein the processing unit is specifically configured to perform edge detection on the portrait of the subject in the image obtained at the first moment, and obtain a local maximum value. Multiple first intensity values corresponding to multiple edge points, and reduce the image obtained at the first moment according to a preset ratio, and perform edge detection on the portrait of the subject in the reduced image to obtain a local maximum a plurality of second intensity values corresponding to the plurality of edge points, and determine whether the difference between the second intensity value corresponding to each edge point in the plurality of edge points and the first intensity value is greater than A threshold value, wherein when the difference between the second intensity value and the first intensity value is greater than the threshold value, it is determined that each edge point is blurred, and it is determined that among the plurality of edge points Whether the number of blurred edge points is greater than a preset value, wherein, when the number of blurred edge points is greater than the preset value, it is determined that the portrait of the subject in the image obtained at the first moment is blurred .