With the popular application of direct part mark (DPM) technology, DPM code inspectionhas been a hot issue in the machine vision. It mainly consists of two steps, namely, localization anddecoding. DPM code localization is a key and complex step in the DPM code inspection. However, thetraditional localization methods suffer from complex imaging environment, involving various imagingbackground, illumination, imaging distance, and exposures. Furthermore, the target itself, i.e., the DPMcode, could be severely polluted or worn. Aiming at improving the performance and robustness of DPMcode localization, an efficient method with depthwise separable convolution is proposed in this paper. Theoptimized network model has the advantages of few parameters, high computational efficiency, highprecision localization, and good generalization ability. Meanwhile, the precision of DPM code region isimproved with the help of multi-scale prediction. The experiments on our DPM code localization databasedemonstrate the effectiveness and flexibility of the proposed method in comparison with the YOLOv3network and the Tiny_YOLO network. Furthermore, the proposed method can estimate the exposure levelof the DPM code region, which is benefiting to the DPM code recognition and enables the adaptive ability.
To View the Base Paper Abstract Contents
Now it is Your Time to Shine.
Great careers Start Here.
We Guide you to Every Step
Success! You're Awesome
Thank you for filling out your information!
We’ve sent you an email with your Final Year Project PPT file download link at the email address you provided. Please enjoy, and let us know if there’s anything else we can help you with.
To know more details Call 900 31 31 555
The WISEN Team