The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo apresenta um método de extração de placas de automóveis capturadas em direções arbitrárias usando recursos de simetria. A transformada de simetria generalizada (GST) produz características contínuas de simetria entre dois pontos combinando restrição de localidade e simetria reflexiva, mas sua complexidade de tempo de GST é aumentada pela segunda potência do raio de uma janela de busca. Para obter uma redução considerável desta complexidade de tempo, propomos um GST baseado em linha de varredura (SLGST) que calcula a simetria entre um par de pixels de borda ao longo das linhas de varredura. Em vez de calcular a simetria global de uma placa, atribuímos a contribuição de simetria adquirida do SLGST ao ponto de canto estimado a partir de dois pontos de borda e suas orientações de gradiente. O SLGST ajustado em ângulo reto (RATSLGST) foi recentemente proposto para detectar os cantos em ângulo reto de forma mais eficaz. A normalização de imagem por distorção de imagem é adotada para facilitar muito a segmentação da placa e posterior identificação. Também adotamos o verificador que avalia uma placa candidata para aumentar a taxa de extração. Nossos experimentos mostram que o método proposto para extrair placas distorcidas em perspectiva é bastante confiável.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Dong-Su KIM, Il CHOI, Sung-Il CHIEN, "Correction and Extraction of Perspectively Distorted License Plates Using Scan Line Based Generalized Symmetry Transform" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 11, pp. 1776-1783, November 2002, doi: .
Abstract: This paper presents a method of extracting car license plates captured from the arbitrary directions by using symmetry features. The generalized symmetry transform (GST) produces continuous features of symmetry between two points by combining locality constraint and reflectional symmetry, but its time complexity of GST is increased by the second power of the radius of a searching window. To achieve considerable reduction of this time complexity, we propose a scan line based GST (SLGST) which calculates the symmetry between a pair of edge pixels along the scan lines. Instead of calculating the global symmetry of a license plate, we assign the symmetry contribution acquired from SLGST to the corner point estimated from two edge points and their gradient orientations. The right angle tuned SLGST (RATSLGST) is newly proposed to detect the right angle corners more effectively. Image normalization by image warping is adopted to make such segmentation of license plate and later identification much easier. We also adopt the verifier that evaluates a candidate license plate to enhance extraction rate. Our experiments show that the proposed method for extracting perspectively distorted license plates is fairly reliable.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_11_1776/_p
Copiar
@ARTICLE{e85-d_11_1776,
author={Dong-Su KIM, Il CHOI, Sung-Il CHIEN, },
journal={IEICE TRANSACTIONS on Information},
title={Correction and Extraction of Perspectively Distorted License Plates Using Scan Line Based Generalized Symmetry Transform},
year={2002},
volume={E85-D},
number={11},
pages={1776-1783},
abstract={This paper presents a method of extracting car license plates captured from the arbitrary directions by using symmetry features. The generalized symmetry transform (GST) produces continuous features of symmetry between two points by combining locality constraint and reflectional symmetry, but its time complexity of GST is increased by the second power of the radius of a searching window. To achieve considerable reduction of this time complexity, we propose a scan line based GST (SLGST) which calculates the symmetry between a pair of edge pixels along the scan lines. Instead of calculating the global symmetry of a license plate, we assign the symmetry contribution acquired from SLGST to the corner point estimated from two edge points and their gradient orientations. The right angle tuned SLGST (RATSLGST) is newly proposed to detect the right angle corners more effectively. Image normalization by image warping is adopted to make such segmentation of license plate and later identification much easier. We also adopt the verifier that evaluates a candidate license plate to enhance extraction rate. Our experiments show that the proposed method for extracting perspectively distorted license plates is fairly reliable.},
keywords={},
doi={},
ISSN={},
month={November},}
Copiar
TY - JOUR
TI - Correction and Extraction of Perspectively Distorted License Plates Using Scan Line Based Generalized Symmetry Transform
T2 - IEICE TRANSACTIONS on Information
SP - 1776
EP - 1783
AU - Dong-Su KIM
AU - Il CHOI
AU - Sung-Il CHIEN
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2002
AB - This paper presents a method of extracting car license plates captured from the arbitrary directions by using symmetry features. The generalized symmetry transform (GST) produces continuous features of symmetry between two points by combining locality constraint and reflectional symmetry, but its time complexity of GST is increased by the second power of the radius of a searching window. To achieve considerable reduction of this time complexity, we propose a scan line based GST (SLGST) which calculates the symmetry between a pair of edge pixels along the scan lines. Instead of calculating the global symmetry of a license plate, we assign the symmetry contribution acquired from SLGST to the corner point estimated from two edge points and their gradient orientations. The right angle tuned SLGST (RATSLGST) is newly proposed to detect the right angle corners more effectively. Image normalization by image warping is adopted to make such segmentation of license plate and later identification much easier. We also adopt the verifier that evaluates a candidate license plate to enhance extraction rate. Our experiments show that the proposed method for extracting perspectively distorted license plates is fairly reliable.
ER -