Character translation and display method and device based on augmented reality and electronic equipment

Abstract

The invention provides a character translation and display method based on augmented reality, and the method comprises the steps of recognizing a character in an image collected by an image collectiondevice of terminal equipment, and determining the position information of the recognized character in an image plane coordinate system; translating the recognized characters into target translated characters of a target language; according to the position information of the character in the image plane coordinate system, determining a superposition position of the target translation character ina physical three-dimensional space coordinate system corresponding to the augmented reality display information; and displaying the augmented reality display information of the target translated character at the superposition position in an augmented reality mode in a superposition manner. According to the method and the device, the augmented reality display information of the target translated character is displayed at the superposition position through the augmented reality technology, so that the augmented reality display information is seamlessly fit and displayed relative to the characterin the image, and the display effect is more vivid. The invention further provides a character translation and display device based on augmented reality and electronic equipment.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular, the present application relates to a text translation and display method, device and electronic equipment based on augmented reality. Background technique [0002] The text recognition and translation technology in the prior art usually realizes the translation of the text through a translation engine. The specific process is: the user performs a photo operation to obtain an image with text, and inputs the image to the translation engine, and the translation engine interprets the text in the image. The text is translated to obtain the translated text, and finally the translated text is displayed in the translation result display area. [0003] However, when translating the text in the image through the above method, since the entire translation process needs to be carried out step by step, that is, the user needs to perform a photo operation to obtain an image wit...

AI Technical Summary

Problems solved by technology

[0003] However, when translating the text in the image through the above method, since the entire translation process needs to be carried out step by step, that is, the user needs to perform a photo operation to obtain an image with text, and then realize the recognition and translation of the text in the image through the translation engine. That is, the user needs to go through two steps to get the translated text, and since the translated text is displayed in the translation result display area, that is, the translated text and the text in the image are displayed separately, the translated text is separated from the image display, and the user is viewing the translation When translating text, the translated text cannot be replaced directly with the original text in an accurate and intuitive one-to-one correspondence

[0004] Therefore, the defects in the prior art are: the operation of the photo-translation process is relatively complicated, and the convenience is not high, and because the translated text is separated from the image display, when the user views the translated text, the translated text cannot be directly compared with the original text accurately and intuitively. One-to-one replacement, so the display method is not very user-friendly

Images