Invoice tilt detection and geometric correction method based on image recognition

Abstract

The invention discloses an invoice tilt detection and geometric correction method based on image recognition, which aims at detecting a tilt angle of an invoice image. The invoice tilt detection and geometric correction method comprises the steps of: utilizing image acquisition equipment to acquire an invoice image, and performing grayscale processing on the acquired invoice image to obtain a grayscale image; then converting the grayscale image into a binary image, performing edge detection on the binary image of an invoice by utilizing a Sobel operator to obtain an edge image of the invoice;and finally adopting Hough transform on the edge image of the invoice, detecting the longest straight line in the invoice, calculating an invoice tilt angle, and rotating the invoice image to obtain the corrected invoice image. through introducing the Sobel operator and Hough transform in the field of image processing, the invoice tilt detection and geometric correction method can detect the tiltangle of invoice image precisely, carries out geometric correction on the invoice according to the tilt angle, solves the problem that invoice cannot be recognized properly because of the tilt of invoice during invoice recognition, can be applied to various kinds of invoices, and has high application value in intelligent financial reimbursement.

Description

technical field [0001] The invention relates to an invoice inclination detection and geometric correction method based on image recognition, and belongs to the fields of image processing and artificial intelligence. Background technique [0002] With the rapid development of social economy, the usage of invoices in my country is increasing day by day. At present, hundreds of millions of invoices are used for reimbursement in my country every year, and there is an upward trend. But now most of the invoice reimbursement work is done manually. Manual reimbursement of invoices is inefficient, the reimbursement process is long, time-consuming, and the error rate is extremely high. Manual reimbursement of invoices not only increases the workload of the financial staff, but also takes up a lot of extra energy of the reimburser, and will increase the production cost of the enterprise. [0003] In recent years, with the rapid development of image processing and computer vision tec...

AI Technical Summary

Problems solved by technology

But now most of the invoice reimbursement work is done manually

Manual reimbursement of invoices is inefficient, the reimbursement process is long, time-consuming, and the error rate is extremely high

Manual reimbursement of invoices not only increases the workload of financial personnel, but also takes up a lot of extra energy for reimbursers, and will increase the production cost of the enterprise

Images