Image acquisition method, apparatus, system, and electronic device
The present disclosure provides image acquisition methods, apparatuses, systems and electronic devices. One image acquisition method includes: acquiring an initial face image of a user by a first image acquisition apparatus; controlling a second image acquisition apparatus to acquire an eye print image of the user according to an acquisition parameter, the acquisition parameter being determined based on the initial face image; and synthesizing the initial face image and the eye print image into a target face image of the user.
1. An image acquisition method, comprising:
acquiring an initial face image of a user by a first image acquisition apparatus;
determining an acquisition parameter of a second image acquisition apparatus based on the initial face image of the user, wherein determining the acquisition parameter comprises:
determining eye region spatial location information of the user based on the initial face image of the user; and
determining the acquisition parameter based on the eye region spatial location information of the user, wherein the eye region spatial location information of the user comprises location information of two pupil centers of the user;
sending the acquisition parameter to a gimbal;
controlling, by the gimbal, the second image acquisition apparatus to acquire an eye region image of the user according to the acquisition parameter, and segmenting the eye region image using a full convolutional depth neural network to acquire an eye print image of the user with a sharpness meeting a preset condition; and
synthesizing the initial face image and the eye print image acquired from the eye region image into a target face image of the user for face recognition.
2. The method of claim 1 , wherein:
a Field of View (FoV) of the first image acquisition apparatus is greater than an FoV of the second image acquisition apparatus.
3. The method of claim 1 , wherein:
a Field of View (FoV) of the first image acquisition apparatus is greater than or equal to 45°*100°; and
an FoV of the second image acquisition apparatus is greater than or equal to 50 mm*140 mm.
4. The method of claim 1 , wherein a lens of the second image acquisition apparatus is one of an optical zoom lens or a prime lens.
5. The method of claim 1 , wherein a Depth of Field (DoF) of the second image acquisition apparatus is greater than or equal to 2 cm.
6. An electronic device, comprising:
a memory storing instructions; and
a processor configured to execute the instructions to:
acquire an initial face image of a user by a first image acquisition apparatus;
determine an acquisition parameter of a second image acquisition apparatus based on the initial face image of the user, wherein determining the acquisition parameter comprises:
determining eye region spatial location information of the user based on the initial face image of the user; and
determining the acquisition parameter based on the eye region spatial location information of the user, wherein the eye region spatial location information of the user comprises location information of two pupil centers of the user;
send the acquisition parameter to a gimbal;
control, by the gimbal, the second image acquisition apparatus to acquire an eye region image of the user according to the acquisition parameter, and segment the eye region image using a full convolutional depth neural network to acquire an eye print image of the user with a sharpness meeting a preset condition; and
synthesize the initial face image and the eye print image acquired from the eye region image into a target face image of the user for face recognition.
7. The electronic device of claim 6 , wherein:
a Field of View (FoV) of the first image acquisition apparatus is greater than an FoV of the second image acquisition apparatus.
8. The electronic device of claim 6 , wherein:
a Field of View (FoV) of the first image acquisition apparatus is greater than or equal to 45°*100°; and
an FoV of the second image acquisition apparatus is greater than or equal to 50 mm*140 mm.
9. The electronic device of claim 6 , wherein a lens of the second image acquisition apparatus is one of an optical zoom lens or a prime lens.
10. The electronic device of claim 6 , wherein a Depth of Field (DoF) of the second image acquisition apparatus is greater than or equal to 2 cm.
11. A non-transitory computer-readable medium storing instructions that, when executed by a processor of a device, cause the device to perform an image acquisition method, the method comprising:
acquiring an initial face image of a user by a first image acquisition apparatus;
determining an acquisition parameter of a second image acquisition apparatus based on the initial face image of the user, wherein determining the acquisition parameter comprises:
determining eye region spatial location information of the user based on the initial face image of the user; and
determining the acquisition parameter based on the eye region spatial location information of the user, wherein the eye region spatial location information of the user comprises location information of two pupil centers of the user;
sending the acquisition parameter to a gimbal;
controlling, by the gimbal, the second image acquisition apparatus to acquire an eye region image of the user according to the acquisition parameter, and segmenting the eye region image using a full convolutional depth neural network to acquire an eye print image of the user with a sharpness meeting a preset condition; and
synthesizing the initial face image and the eye print image acquired from the eye region image into a target face image of the user for face recognition.