Soft segmentation method of financial OCR system handwritten numerical strings

Abstract

The invention discloses a soft segmentation method of financial OCR system handwritten numerical strings. Automatic recognition processing of financial paper realizes automatic input and rechecking of financial paper, seamlessly integrates the whole process of image processing, layout analysis and intelligent identification, and comprises automatic classification of financial paper images, image preprocessing of the financial paper, identification, supervision and checking of elements in the financial paper, and the like. OCR technology is the core part in a financial paper automatic recognition processing system, requires cutting connected character strings required for automatic processing of financial paper elements into single characters, and performing character recognition. The character recognizer at the present stage has high accuracy rate, so that the overall recognition rate of the OCR system depends on the accurate rate and the acceptability of character string segmentation. The method aims at solving the technical problem of a soft segmentation method for realizing connected numeric strings based on a fuzzy pattern recognition theory, so as to improve the accurate rate of the integral segmentation flow and reduce the false rejection rate of the system, and improve the overall performance of the recognition system.

Description

technical field [0001] The invention belongs to the technical field of OCR, and relates to a method for segmenting handwritten character strings. The method can extract fuzzy features from strokes in digital images and map them to feature fragment sets, and then form candidate segmentation hypotheses and Calculate the optimal segmentation result. Background technique [0002] At present, OCR has become the core technology of various systems, and has been widely used and involves many industries from finance, government, libraries to electric power, enterprises and institutions, such as document image recognition systems (including document entry, search, management, etc.) , Office automation text input, postal code automatic sorting system, document automatic classification system, license plate automatic recognition system, bill automatic processing system, etc. A complete OCR system generally requires the following steps: adjustment of tilted images, layout analysis and l...

AI Technical Summary

Problems solved by technology

The combination of multiple classifiers is an effective way to design a high-performance and stable handwritten digit recognizer, which overcomes the three types of reasons that lead to poor performance of the classifier to a certain extent: single feature does not fully reflect the nature of characters; noise and other factors Influence, leading to the instability of feature description for characters; Different types of classifiers have different sensitivities and stability to feature changes, resulting in a decline in the performance of a single classifier

Images