Image-text identification system and identification method thereof

Abstract

The invention discloses an image-text identification system. The system comprises an intelligent terminal which is used for image-text collecting, selecting and uploading and a server which is used for image-text conversion. The identification method comprises the steps that a picture in the display interface of a display screen is collected; a four-corner indicator in the picture is collected, a to-be-identified text or the image is selected by adjusting the position of the four-corner indicator; the range of the picture is selected, and a language is identified to carry out image-text identification; the image-text angle is adjusted; the image-text is uploaded; the server carries out identification; and the text is downloaded and displayed. According to the invention, the process of image-text identification is carried out through the intelligent device and the cloud server; the intelligent device carries out image-text collecting, selecting and uploading; the cloud server carries out image-text identification; and the image-text identification system has the advantages of good instantaneity, high identification rate and strong pertinence.

Description

technical field [0001] The invention belongs to the technical field of graphic-text recognition, and in particular relates to a graphic-text recognition system and a recognition method thereof. Background technique [0002] To extract text from pictures or scanned documents, save them in our documents. However, after using a lot of software, the effect is not very satisfactory, and we still need to manually check it, which greatly affects our work efficiency. [0003] OCR (Optical Character Recognition, Optical Character Recognition) means that an electronic device (such as a scanner or a digital camera) checks characters printed on paper, determines its shape by detecting dark and bright patterns, and then uses character recognition to translate the shape into a computer The process of text; that is, for printed characters, the text in the paper document is converted into a black and white dot matrix image file by optical means, and the text in the image is converted into ...

AI Technical Summary

Problems solved by technology

If it needs to be restored to the same format as the original text, manual typesetting is required after recognition, which is time-consuming and labor-intensive

[0005] The existing patent ZL201210146093.X discloses "A Method and Device for Graphic and Text Recognition". This technology uses graphic and text recognition software to select and recognize the pictures and characters in the point area, but the recognition range of this method is small and it is not easy to fix the point. select

[0006] The existing patent ZL201610562245.2 discloses a "Graphic Text Recognition Method and Its Device". This technology is mostly used for verification code character recognition through binarized image pixel point matching recognition technology. For image text arrays, real-time and accurate recognition cannot be achieved. identify

Images