Huawei Technologies Co., Limited

Yuewan Lu

Wenmei Gao

Hao Liu

Chen Dong

Lei Qin

Xin Ding

Hongwei Hu

Yongtao Jiang

Lin Zhao

Heng Zhou

Tianluo Chen

Deyu Zhou

Tianyu Yao

Embodiments of this application provide a speech recognition method. The speech recognition method includes: obtaining a facial depth image and a to-be-recognized voice of a user, where the facial depth image is an image collected by using a depth camera; recognizing a mouth shape feature from the facial depth image, and recognizing a voice feature from a to-be-recognized audio; and fusing the voice feature and the mouth shape feature into an audio-video feature, and recognizing, based on the audio-video feature, a voice uttered by the user.

Electronic device, speech recognition method therefor, and medium

The technology of this application relates to an artificial intelligence terminal-based image detection method and apparatus, and an electronic device. The method includes obtaining a to-be-detected image, determining a light source region of the to-be-detected image and a foreground region of the to-be-detected image, and determining a blurring degree of the to-be-detected image based on the light source region and the foreground region. Impact of a light source on clarity of the to-be-detected image is determined by performing light source region detection and foreground region detection on the to-be-detected image, to effectively detect whether an image shot in a backlight condition is blurred.

Image detection method and apparatus, and electronic device

A photographing method implemented by an electronic device includes receiving a photographing instruction of a user, shooting a primary camera image using a primary camera, shooting a wide-angle image using a wide-angle camera, and generating a three-dimensional (3D) image based on the primary camera image and the wide-angle image, where the 3D image includes a plurality of frames of images that is converted from a 3D viewing angle and corresponds to different viewing angles.

Photographing method, image processing method, and electronic device

An image processing method includes: converting a red yellow blue RYB image into a grid image based on a red green blue RGB format; generating a first brightness layer of the grid image, and determining a reference gain compensation array used to adjust the first brightness layer; obtaining, based on a preset compensation array correspondence, a target gain compensation array that is associated with the reference gain compensation array and based on an RYB format; and adjusting a second brightness layer of the RYB image by using the target gain compensation array, to generate a corrected image.

Image processing method and apparatus, terminal, and storage medium

Growing community of inventors

Shenzhen, China

Yuewan Lu