Abstract: An electronic device includes a rear cover and a camera decoration component. The camera decoration component includes a decoration member, a dial plate, a plurality of positioning members, and a plurality of induction members. The dial plate is annular, and is sleeved on an outer peripheral side of the decoration member. The decoration member includes a virtual rotation axis, and the dial plate is rotatably connected to the decoration member. The decoration member is configured to rotate around the virtual rotation axis of the decoration member. The positioning members and the induction members are configured to control the dial plate to be in a hovering state.

Abstract: Example array substrates are provided. One example array substrate includes an underlying substrate, an antenna and a component layer, where the antenna and the component layer are located on a same side of the underlying substrate, where the component layer and the antenna are disposed at intervals, where the component layer includes a plurality of metal laminates and a plurality of dielectric laminates that are stacked, and where the plurality of metal laminates and the plurality of dielectric laminates are alternately disposed to form a plurality of thin film transistors.

Abstract: An electronic device includes a rear cover and a camera decoration component. The camera decoration component includes a decoration member, a dial plate, a plurality of positioning members, and a plurality of induction members. The dial plate is annular, and is sleeved on an outer peripheral side of the decoration member. The decoration member includes a virtual rotation axis, and the dial plate is rotatably connected to the decoration member. The decoration member is configured to rotate around the virtual rotation axis of the decoration member. The positioning members and the induction members are configured to control the dial plate to be in a hovering state.

Abstract: This disclosure describes systems, devices, and techniques for training neural networks to identify avascular and signal reduction areas of Optical Coherence Tomography Angiography (OCTA) images and for using trained neural networks. By identifying signal reduction areas in OCTA images, the avascular areas can be detected with high accuracy, even when the OCTA images include artifacts and other types of noise. Accordingly, various implementations described herein can accurately identify avascular areas from real-world clinical OCTA images. In various implementations, a method can include identifying images of retinas. The images may include thickness images, reflectance intensity maps, and OCTA images of the retinas. Avascular maps corresponding to the OCTA images can be identified. A neural network can be trained based on the images and the avascular maps.

Abstract: Methods for automatically identifying retinal boundaries from a reflectance image are disclosed. An example of the method includes identifying a reflectance image of the retina of a subject; generating a gradient map of the reflectance image, the gradient map representing dark-to-light or light-to-dark reflectance differentials between adjacent pixel pairs in the reflectance image; generating a guidance point array corresponding to a retinal layer boundary depicted in the reflectance image using the gradient map; generating multiple candidate paths estimating the retinal layer boundary in the reflectance image by performing a guided bidirectional graph search on the reflectance image using the guidance point array; and identifying the retinal layer boundary by merging two or more of the multiple candidate paths.

Abstract: This disclosure describes systems, devices, and techniques for training neural networks to identify avascular and signal reduction areas of Optical Coherence Tomography Angiography (OCTA) images and for using trained neural networks. By identifying signal reduction areas in OCTA images, the avascular areas can be detected with high accuracy, even when the OCTA images include artifacts and other types of noise. Accordingly, various implementations described herein can accurately identify avascular areas from real-world clinical OCTA images. In various implementations, a method can include identifying images of retinas. The images may include thickness images, reflectance intensity maps, and OCTA images of the retinas. Avascular maps corresponding to the OCTA images can be identified. A neural network can be trained based on the images and the avascular maps.

Abstract: An example method includes generating, using a multi-scale block of a convolutional neural network (CNN), a first output image based on an optical coherence tomography (OCT) reflectance image of a retina and an OCT angiography (OCTA) image of the retina. The method further includes generating, using an encoder of the CNN, at least one second output image based on the first output image and generating, using a decoder of the CNN, a third output image based on the at least one second output image. An avascular map is generated based on the third output image. The avascular map indicates at least one avascular area of the retina depicted in the OCTA image.

Abstract: Example array substrates are provided. One example array substrate includes an underlying substrate, an antenna and a component layer, where the antenna and the component layer are located on a same side of the underlying substrate, where the component layer and the antenna are disposed at intervals, where the component layer includes a plurality of metal laminates and a plurality of dielectric laminates that are stacked, and where the plurality of metal laminates and the plurality of dielectric laminates are alternately disposed to form a plurality of thin film transistors.

Abstract: Methods for automatically identifying retinal boundaries from a reflectance image are disclosed. An example of the method includes identifying a reflectance image of the retina of a subject; generating a gradient map of the reflectance image, the gradient map representing dark-to-light or light-to-dark reflectance differentials between adjacent pixel pairs in the reflectance image; generating a guidance point array corresponding to a retinal layer boundary depicted in the reflectance image using the gradient map; generating multiple candidate paths estimating the retinal layer boundary in the reflectance image by performing a guided bidirectional graph search on the reflectance image using the guidance point array; and identifying the retinal layer boundary by merging two or more of the multiple candidate paths.

Abstract: An example method includes generating, using a multi-scale block of a convolutional neural network (CNN), a first output image based on an optical coherence tomography (OCT) reflectance image of a retina and an OCT angiography (OCTA) image of the retina. The method further includes generating, using an encoder of the CNN, at least one second output image based on the first output image and generating, using a decoder of the CNN, a third output image based on the at least one second output image. An avascular map is generated based on the third output image. The avascular map indicates at least one avascular area of the retina depicted in the OCTA image.

Abstract: Embodiments include a middle frame for a mobile terminal and a mobile terminal. The middle frame for a mobile terminal includes a metal outer frame. An inner side of the metal outer frame is internally connected to a tray using a location structure. A plastic outer frame is formed on the inner side of the metal outer frame using an insert injection molding process, and the plastic outer frame is separately joined with the metal outer frame and the tray for curing.

Abstract: A method for controlling display of a touchscreen, and a mobile device are presented, which relate to the field of electronic device technologies, so that the mobile device can control to zoom-in or zoom-out displayed content on the touchscreen according to received information about two touches. The method in the present disclosure includes receiving first touch information, where the first touch information comprises a first touch position; receiving second touch information, where the second touch information comprises a second touch position; determining zooming times according to a distance between the first touch position and the second touch position; and zooming displayed content on the touchscreen according to a position relationship between the first touch position and the second touch position and the zooming times. The present disclosure is applicable to a mobile device.

Abstract: Embodiments include a middle frame for a mobile terminal and a mobile terminal. The middle frame for a mobile terminal includes a metal outer frame. An inner side of the metal outer frame is internally connected to a tray using a location structure. A plastic outer frame is formed on the inner side of the metal outer frame using an insert injection molding process, and the plastic outer frame is separately joined with the metal outer frame and the tray for curing.

Abstract: An antenna circuit includes a first antenna circuit, a second antenna circuit, and a connection hole. The first antenna circuit is disposed on a non-exterior surface of a terminal device; the second antenna circuit is disposed on an exterior surface of the terminal device, where the exterior surface is a surface of the terminal device visible to a user, and the non-exterior surface is disposed opposite to the exterior surface; and the connection hole penetrates through the non-exterior surface and the exterior surface, where the first antenna circuit and the second antenna circuit are electrically connected by using the connection hole.

Abstract: A method for controlling display of a touchscreen, and a mobile device are presented, which relate to the field of electronic device technologies, so that the mobile device can control to zoom-in or zoom-out displayed content on the touchscreen according to received information about two touches. The method in the present disclosure includes receiving first touch information, where the first touch information comprises a first touch position; receiving second touch information, where the second touch information comprises a second touch position; determining zooming times according to a distance between the first touch position and the second touch position; and zooming displayed content on the touchscreen according to a position relationship between the first touch position and the second touch position and the zooming times. The present disclosure is applicable to a mobile device.

Abstract: A method for controlling display of a touchscreen, and a mobile device are presented, which relate to the field of electronic device technologies, so that the mobile device can control to zoom-in or zoom-out displayed content on the touchscreen according to received information about two touches. The method in the present disclosure includes receiving first touch information, where the first touch information comprises a first touch position; receiving second touch information, where the second touch information comprises a second touch position; determining zooming times according to a distance between the first touch position and the second touch position; and zooming displayed content on the touchscreen according to a position relationship between the first touch position and the second touch position and the zooming times. The present disclosure is applicable to a mobile device.

Abstract: A method for controlling display of a touchscreen, and a mobile device are presented, which relate to the field of electronic device technologies, so that the mobile device can control to zoom-in or zoom-out displayed content on the touchscreen according to received information about two touches. The method in the present disclosure includes receiving first touch information, where the first touch information comprises a first touch position; receiving second touch information, where the second touch information comprises a second touch position; determining zooming times according to a distance between the first touch position and the second touch position; and zooming displayed content on the touchscreen according to a position relationship between the first touch position and the second touch position and the zooming times. The present disclosure is applicable to a mobile device.

Abstract: Embodiments of the present disclosure disclose a method for controlling display of a touchscreen, and a mobile device, which relate to the field of electronic device technologies, so that the mobile device can control to zoom-in or zoom-out displayed content on the touchscreen according to received information about two touches. The method in the present disclosure includes receiving first touch information, where the first touch information comprises a first touch position; receiving second touch information, where the second touch information comprises a second touch position; determining zooming times according to a distance between the first touch position and the second touch position; and zooming displayed content on the touchscreen according to a position relationship between the first touch position and the second touch position and the zooming times. The present disclosure is applicable to a mobile device.

Abstract: An antenna circuit includes a first antenna circuit, a second antenna circuit, and a connection hole. The first antenna circuit is disposed on a non-exterior surface of a terminal device; the second antenna circuit is disposed on an exterior surface of the terminal device, where the exterior surface is a surface of the terminal device visible to a user, and the non-exterior surface is disposed opposite to the exterior surface; and the connection hole penetrates through the non-exterior surface and the exterior surface, where the first antenna circuit and the second antenna circuit are electrically connected by using the connection hole.

Abstract: Embodiments of the present disclosure disclose a method for controlling display of a touchscreen, and a mobile device, which relate to the field of electronic device technologies, so that the mobile device can control to zoom-in or zoom-out displayed content on the touchscreen according to received information about two touches. The method in the present disclosure includes receiving first touch information, where the first touch information comprises a first touch position; receiving second touch information, where the second touch information comprises a second touch position; determining zooming times according to a distance between the first touch position and the second touch position; and zooming displayed content on the touchscreen according to a position relationship between the first touch position and the second touch position and the zooming times. The present disclosure is applicable to a mobile device.