Handwritten form keyword detection method

Abstract

The invention discloses a handwritten form keyword detection method comprising that: characteristic points of keyword images in a keyword image database are extracted so that a keyword characteristic database is established; the characteristic points of texts in text images to be detected are extracted so that a characteristic point database of the text images to be detected is obtained; sliding windows of the text images to be detected are extracted, characteristic point sets corresponding to the sliding windows are extracted from the characteristic point database, and the characteristic point sets are compared so that initial matching point pair sets are obtained; the initial matching point pair sets are screened so that accurate matching point pairs are obtained; and the sliding windows in the text images to be detected are screened according to the matching point pairs and integrated so that detection results are obtained. In the process of characteristic extraction, SIFT characteristic representation is adopted. The method is applicable to detection of keywords of large amounts of handwritten form documents, such as historical literatures, correspondences, notes, etc. Under the premise of establishing a black list image database, the keywords in a black list can be effectively detected and handwriting of different authors can also be distinguished.

Description

technical field [0001] The invention relates to image detection technology, in particular to a method for detecting keywords in handwritten handwriting of a specific writer based on local features of characters. Background technique [0002] Handwritten keyword detection is to detect specific keywords in a large number of handwritten text images. The current method of handwritten keyword detection is usually to perform character retrieval on the basis of text recognition. [0003] However, there are many types of Chinese characters and changing writing styles. The existing handwritten keyword error detection methods based on text recognition first need to establish a huge Chinese character template library, and spend a lot of time on feature training and classification. The early image preprocessing and text Segmentation also greatly affects the results of character recognition, which in turn affects the results of keyword detection; in addition, this method of relying on r...

AI Technical Summary

Problems solved by technology

[0004] The invention overcomes the defect in the prior art that the handwritten characters of a specific writer cannot be effectively identified, and proposes a handwritten keyword detection method

Images