Camera-based point reading positioning method and device

Abstract

The invention provides a camera-based point reading positioning method and a camera-based point reading positioning device, which belong to the field of image processing. The method comprises: shooting an image of a current text page, differentiating the shot current image with a template image to detect if an indicator in the current image appears, and updating the template image to the current image if the indicator is not detected or stopping updating the template image if the indicator is detected; shooting an image of the current text page, performing positioned detection according to the differences of the images behind the template image, and determining a positioned image having the indicator; and determining the position of the indicator in the current text page according to the difference image of the positioned image and the template image. In the invention, the indicator is positioned by differentiating the image shot by the camera and the template image, so that the position of the indicator is determined; a user can perform point reading on the camera directly through the indicator such as a finger without using peripheral equipment for operation; and thus, a great convenience is brought to the user.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a point reading positioning method, in particular to a point reading positioning method and device based on a camera. Background technique [0002] The camera is a new type of image acquisition device, which acquires images of documents and other materials through a camera, performs image processing, layout analysis, etc. on the images, and then sends the text area to the OCR engine for text recognition. Since the camera combines functions such as copying, scanning, projection, photographing, video recording, faxing, and mail delivery, it has been widely used in the industry. [0003] In the field of education and office, if the user needs to perform point reading operations on the camera, the current common method is to recognize the image captured by the camera, and use a mouse, stylus and other equipment to select The target text will be called, and the TTS engine will be called...

AI Technical Summary

Problems solved by technology

[0003] In the field of education and office, if the user needs to perform point reading operations on the camera, the current common method is to recognize the image captured by the camera, and use a mouse, stylus and other equipment to select The target text will be called, and the TTS engine will be called to read the target text. In this way, the user must use peripheral devices such as a mouse and a stylus to perform point-reading operations on a computer equipped with recognition software and point-reading software. It not only brings inconvenience but also increases the cost of equipment, and the teaching also seems dull

Images