A rapid detection method of express parcel barcode
A detection method and barcode technology, applied in the fields of image processing and deep learning, can solve the problems of barcode distortion, small barcode target, false detection and missed detection.
Active Publication Date: 2021-05-28
WAYZIM TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in reality, in the automatic sorting scenario of logistics parcels, due to the influence of lighting conditions and on-site environment, the quality of the collected pictures is uneven, such as drastic lighting changes, complex background interference, barcode distortion and deformation, and small barcode targets. Cause false detection and missed detection, resulting in increased difficulty in barcode detection
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0028] According to the special scene of parcel sorting and the particularity of the target barcode to be detected, the present invention uses a one-stage detector as the basic framework to design a lightweight cascaded multi-scale feature fusion network, which directly extracts features and classifies them through convolution. Returns the location barcode. The model structure and flowchart are as figure 1 As shown, the feature ex...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fast detection method for express parcel barcodes, comprising: constructing a cascaded multi-scale feature fusion network, the feature fusion network including a sequentially connected feature reduction network and a feature preservation network; inputting the express parcel barcode image into the feature The network is fused, and a feature map is obtained through convolution extraction; the feature map is input into a detection module, and the feature map is classified and coordinate regression is performed to obtain a detection result. The invention has obvious advantages in terms of accuracy and speed, and can better solve the problem of barcode detection in practical applications. In other practical application environments, the number of feature fusion layers in the feature reduction network and feature preservation network can be customized according to specific needs, which is universal.
Description
technical field [0001] The invention relates to the technical fields of deep learning and image processing, in particular to a fast detection method for express parcel barcodes. Background technique [0002] Image processing technology is an effective way to realize barcode detection. Traditional image algorithms require a relatively ideal physical environment, usually by extracting barcode edge texture feature information, or using morphological processing algorithms to corrode and expand to obtain barcode areas, or using Hough transform algorithms to detect barcode edge lines and other methods to achieve detection. Traditional image algorithms have high requirements on the detection environment, and often achieve better detection results in specific physical environments. However, in reality, in the automatic sorting scenario of logistics parcels, due to the influence of lighting conditions and on-site environment, the quality of the collected pictures is uneven, such as ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/253G06F18/24
Inventor 许绍云易帆李功燕
Owner WAYZIM TECH CO LTD