A Method for Extraction and Recognition of Isolated License Plate Characters - Computer Science > Computer Vision and Pattern RecognitionReport as inadecuate




A Method for Extraction and Recognition of Isolated License Plate Characters - Computer Science > Computer Vision and Pattern Recognition - Download this document for free, or read online. Document in PDF available to download.

Abstract: A method to extract and recognize isolated characters in license plates isproposed. In extraction stage, the proposed method detects isolated charactersby using Difference-of-Gaussian DOG function, The DOG function, similar toLaplacian of Gaussian function, was proven to produce the most stable imagefeatures compared to a range of other possible image functions. The candidatecharacters are extracted by doing connected component analysis on differentscale DOG images. In recognition stage, a novel feature vector namedaccumulated gradient projection vector AGPV is used to compare the candidatecharacter with the standard ones. The AGPV is calculated by first projectingpixels of similar gradient orientations onto specific axes, and thenaccumulates the projected gradient magnitudes by each axis. In the experiments,the AGPVs are proven to be invariant from image scaling and rotation, androbust to noise and illumination change.



Author: Yon Ping Chen, Tien Der Yeh

Source: https://arxiv.org/



DOWNLOAD PDF




Related documents