Development of ANPR Framework for Pakistani Vehicle Number Plates Using Object Detection and OCR

The metropolis of the future demands an efficient Automatic Number Plate Recognition (ANPR) system. Since every region has a distinct number plate format and style, an unconstrained ANPR system is still not available. There is not much work done on Pakistani number plates because of the unavailability of the data and heterogeneous plate formations. Addressing this issue, we have collected a Pakistani vehicle dataset having various plate configurations and developed a novel ANPR framework using the dataset. The proposed framework localizes the number plate region using the YOLO (You Only Look Once) object detection model, applies robust preprocessing techniques on the extracted plate region, and finally recognizes the plate label using OCR (optical character recognition) Tesseract. The obtained mAP score of the YOLOv3 is 94.3% and the YOLOv4 model is 99.5% on the 0.50 threshold, whereas the average accuracy score of our framework is found to be 73%. For comparison and validation, we implemented a LeNet Convolutional Neural Network (CNN) architecture which uses the segmented image as an input. The comparative analysis shows that the proposed ANPR framework comprising the YOLOv4 and OCR Tesseract has good accuracy and inference time for a wide variation of illumination and style of Pakistani number plates and can be used to develop a real-time system. The proposed ANPR framework will be helpful for researchers developing ANPR for countries having similar challenging vehicle number plate formats and styles.

Measuring orthotropic bending stiffness components of Pinus pinaster by the virtual fields method

Orthotropic stiffness components of Pinus pinaster Ait. wood are simultaneously determined by means of a heterogeneous plate bending test. The proposed inverse identification approach couples full-field slope measurements provided by deflectometry with the virtual fields methods. Wooden plates oriented in the longitudinal–radial and longitudinal–tangential material planes were manufactured. A procedure was implemented to allow suitable specular reflective coating of the wooden plates, required in the deflectometry technique. Reconstructed curvature fields, applied load and plate dimensions were input in virtual fields methods for material parameter identification, assuming Kirchhoff–Love classical plate theory. Several virtual fields and load cases were analysed to address the identifiability of the method. The values of the orthotropic elastic constants obtained from the proposed approach were found in good agreement with regard to reference ones for the same species and determined from classical tensile, compression and shear mechanical tests.