US-20260127399-A1 - BARCODE RECOGNITION METHOD AND BARCODE READER CAMERA

US20260127399A1US 20260127399 A1US20260127399 A1US 20260127399A1US-20260127399-A1

Abstract

A method of recognizing a barcode by using a barcode reader (BCR) camera installed in a conveyor environment includes: obtaining, by using a BCR camera, a barcode image of a barcode on an object on a conveyor; obtaining a field of view of the BCR camera based on a conveyor environmental condition and a BCR camera setting condition; obtaining a moving distance of the object on the conveyor by using the field of view of the BCR camera, the conveyor environmental condition, and the BCR camera setting condition; generating a blur kernel of the barcode based on a moving direction of the object and the moving distance of the object; and deblurring the barcode image by using a pre-trained deblurring algorithm based on the blur kernel.

Inventors

Soo Hyun Jung
Chang Hyun Kim

Assignees

HANWHA VISION CO., LTD.

Dates

Publication Date: 20260507
Application Date: 20251104
Priority Date: 20241105

Claims (14)

1 . A method of recognizing a barcode by using a barcode reader (BCR) camera installed in a conveyor environment, the method comprising: obtaining, by using a BCR camera, a barcode image of a barcode on an object on a conveyor; obtaining a field of view of the BCR camera based on a conveyor environmental condition and a BCR camera setting condition; obtaining a moving distance of the object on the conveyor by using the field of view of the BCR camera, the conveyor environmental condition, and the BCR camera setting condition; generating a blur kernel of the barcode based on a moving direction of the object and the moving distance of the object; and deblurring the barcode image by using a pre-trained deblurring algorithm based on the blur kernel.
2 . The method of claim 1 , wherein the obtaining the field of view of the BCR camera comprises: obtaining a horizontal viewing angle and a vertical viewing angle based on an installation height of the BCR camera with respect to the conveyor, a size of an image sensor the BCR camera, and a focal length of the BCR camera; and obtaining a horizontal field of view area and a vertical field of view area based on the horizontal viewing angle and the vertical viewing angle, respectively.
3 . The method of claim 2 , wherein the obtaining the moving distance comprises: obtaining an actual moving distance of the object according to a single frame based on a speed of the conveyor and a shutter speed of the BCR camera; and converting the actual moving distance into a moving distance according to a single pixel.
4 . The method of claim 3 , wherein the generating the blur kernel comprises: obtaining a motion vector based on the moving distance according to the single pixel and the moving direction of the object; and generating the blur kernel based on the motion vector.
5 . The method of claim 1 , wherein the deblurring comprises deblurring the barcode image based on the blur kernel and the barcode image by using a Wiener filter algorithm.
6 . A barcode reader (BCR) camera installed in a conveyor environment, the BCR camera comprising: an image sensor configured to obtain a barcode image of a barcode on an object moving in a moving direction at a constant speed on a conveyor at a fixed distance from the BCR camera; and a processor configured to obtain a field of view of the BCR camera based on a conveyor environmental condition and a BCR camera setting condition, obtain a moving distance of the object on the conveyor by using the field of view of the BCR camera, the conveyor environmental condition, and the BCR camera setting condition, generate a blur kernel based on the moving direction of the object and the moving distance of the object, and deblur the barcode image by using a pre-trained deblurring algorithm based on the blur kernel.
7 . The BCR camera of claim 6 , wherein the processor is further configured to obtain a horizontal viewing angle and a vertical viewing angle based on an installation height of the BCR camera with respect to the conveyor, a size of the image sensor of the BCR camera, and a focal length of the BCR camera, and obtain a horizontal field of view area and a vertical field of view area based on the horizontal viewing angle and the vertical viewing angle, respectively.
8 . The BCR camera of claim 7 , wherein the processor is further configured to obtain an actual moving distance of the object according to a single frame based on a speed of the conveyor and a shutter speed of the BCR camera, and convert the actual moving distance into a moving distance according to a single pixel.
9 . The BCR camera of claim 8 , wherein the processor is further configured to obtain a motion vector based on the moving distance according to the single pixel and the moving direction of the object, and generate a blur kernel based on the motion vector.
10 . The BCR camera of claim 6 , wherein the processor is further configured to deblur the barcode image based on the blur kernel and the barcode image by using a Wiener filter algorithm.
11 . The BCR camera of claim 6 , wherein the moving direction is the only direction in which the object is moving on the conveyor.
12 . A method of recognizing a barcode by using a barcode reader (BCR) camera installed in a conveyor environment, the method comprising: obtaining, by using the BCR camera, a barcode image of a barcode on an object moving in a moving direction on a conveyor at a fixed distance from the BCR camera; receiving a conveyor environmental condition and a BCR camera setting condition from a user; obtaining a field of view of the BCR camera based on the conveyor environmental condition and the BCR camera setting condition, and obtaining a moving distance of the object on the conveyor by using the field of view of the BCR camera, the conveyor environmental condition, and the BCR camera setting condition; generating a blur kernel based on the moving direction and the moving distance of the object; and deblurring the barcode image by using a pre-trained deblurring algorithm based on the blur kernel.
13 . The method of claim 12 , wherein the generating the blur kernel comprises recalculating a moving speed of the object on the conveyor at preset time intervals or based on a user input, recalculating the moving distance, and regenerating the blur kernel based on the recalculated moving distance.
14 . The method of claim 12 , wherein the moving direction is the only direction in which the object is moving on the conveyor.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is based on and claims priority under 35 U.S.C. § 119 to Korean Patent Application No. 10-2024-0155668, filed on Nov. 5, 2024, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein in its entirety by reference. BACKGROUND 1. Field Embodiments of the disclosure relate to a barcode recognition method and a barcode reader (BCR) camera. 2. Description of the Related Art Since barcode reader (BCR) cameras are capable of accurately recognizing a barcode even in high-speed conveyor environments, they may be utilized to automate logistics and enhance operational reliability. However, for accurate barcode recognition, high-resolution barcode images with minimal blurring are required. In general, pixels per module (PPM), which is required for barcode recognition, is an important indicator indicating the resolution of a barcode reader and refers to the number of pixels per barcode module. However, when blurring occurs in the barcode, barcode recognition becomes more difficult because it is difficult to distinguish the barcode modules, which are the widths of the smallest units that constitute the barcode. According to the related art, when it is assumed that a blur kernel existing in a barcode image is a camera blur that occurs only in a camera optical system or when motion blur is assumed, deconvolution is optimized through the difference in features between a clear barcode and a deblurred barcode. However, these techniques require a long time to estimate a blur kernel because an algorithm of repeatedly finding the blur kernel has to be performed so as to find an optimal blur kernel. In addition, a system is limited to a mobile terminal device and a fixed camera is not assumed. Therefore, blur kernel estimation is difficult because the speed of movement is not constant and the direction of movement has to account not only for the movement of the object but also for the movement of the camera. SUMMARY Provided are a barcode recognition method and a barcode reader (BCR) camera configured to implement the barcode recognition method. However, this is only an example and the scope of the disclosure is not limited thereto. Various aspects of the disclosure will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the presented embodiments of the disclosure. According to an aspect of the disclosure, a method of recognizing a barcode by using a BCR camera installed in a conveyor environment may include: obtaining, by using a BCR camera, a barcode image of a barcode on an object on a conveyor; obtaining a field of view of the BCR camera based on a conveyor environmental condition and a BCR camera setting condition; obtaining a moving distance of the object on the conveyor by using the field of view of the BCR camera, the conveyor environmental condition, and the BCR camera setting condition; generating a blur kernel of the barcode based on a moving direction of the object and the moving distance of the object; and deblurring the barcode image by using a pre-trained deblurring algorithm based on the blur kernel. The obtaining the field of view of the BCR camera may include: obtaining a horizontal viewing angle and a vertical viewing angle based on an installation height of the BCR camera with respect to the conveyor, a sensor size of the BCR camera, and a focal length of the BCR camera; and obtaining a horizontal field of view area and a vertical field of view area based on the horizontal viewing angle and the vertical viewing angle, respectively. The obtaining the moving distance may include: obtaining an actual moving distance of the object according to a single frame based on a speed of the conveyor and a shutter speed of the BCR camera; and converting the actual moving distance into a moving distance according to a single pixel. The generating the blur kernel may include: obtaining a motion vector based on the moving distance according to the single pixel and the moving direction of the object; and generating the blur kernel based on the motion vector. The deblurring may include deblurring the barcode image based on the blur kernel and the barcode image by using a Wiener filter algorithm. According to an aspect of the disclosure, a BCR camera installed in a conveyor environment may include; an image sensor configured to obtain a barcode image of a barcode on an object moving in a moving direction at a constant speed on a conveyor at a fixed distance from the BCR camera; and a processor configured to obtain a field of view of the BCR camera based on a conveyor environmental condition and a BCR camera setting condition, obtain a moving distance of the object on the conveyor by using the field of view of the BCR camera, the conveyor environmental condition, and the BCR camera setting condition, generate a blur kernel based on the moving direction of