Bill image rapid red seal detection method, system and device

Abstract

The invention belongs to the technical field of image processing and character recognition, and particularly relates to a bill image rapid red seal detection method, system and device. The invention aims at solving the problems that an existing red seal detection method seriously depends on candidate boxes and the setting difficulty of the candidate boxes is large, so that the detection real-timeperformance and accuracy are poor. The method of the system comprises the following steps: acquiring a to-be-detected bill image as an input image; extracting multi-color space features of each pixelpoint in the input image; based on the multi-color spatial features, classifying the pixel points through an SVM classifier to obtain a classification result graph of the red seal pixel points, and taking the classification result graph as a first result graph; carrying out morphological expansion on the first result graph, and carrying out connected domain marking; and sequentially judging whether the width, the height and the aspect ratio of the connected domain of each mark are within a preset threshold range or not, and if so, outputting the position of the connected domain in the bill image and the corresponding first result image as detection results. The real-time performance and accuracy of red seal detection are improved.

Description

technical field [0001] The invention belongs to the technical fields of image processing and character recognition, and in particular relates to a method, system and device for quickly detecting a red stamp on a bill image. Background technique [0002] The text in the bill image can express a wealth of financial information, while the traditional manual entry of financial information is slow, has a high error rate, and requires a lot of manpower and material resources. In recent years, the upsurge of artificial intelligence has been increasing day by day, related technologies such as image processing, pattern recognition, computer vision, etc. have also been developed rapidly, and intelligent reimbursement systems have gradually emerged. [0003] With the continuous development of society, the intelligent reimbursement system has an increasing demand for automatic detection and recognition of text in bill images. Document recognition technology has great economic benefits a...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the existing red badge detection method is heavily dependent on the candidate frame and the setting of the candidate frame is difficult, resulting in poor detection real-time performance and accuracy, the first aspect of the present invention , a fast red stamp detection method for bill images is proposed, which includes:

Images