Car license plate recognition based on the combination of principal components analysis and radial basis function networks

Cheng, Yuehua; Lü, Jianming; Yahagi, Takashi

doi:10.1109/icosp.2004.1441601

Cited by 14 publications

(16 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2. Comparison among different types of recognition for Iraqi license plate System Total Recognition % Shihab [2] 97 Abbas [3] 98.245 Abed [4] 92 Tawfeeq [5] 93.33 Table 3.Comparison among different types of recognition for EU plate System Total Recognition % Janowski [10] 80 Li [11] 80 Zhu [12] 87.33 Sarfaz [13] 95 Donoser [14] 94 Abdulbaki [15] In [16][17][18][19][20][21][22][23][24][25][26][27] the license plate was projected vertically to define the boundaries of the characters, then horizontally to detect each character. One easily can recognize from Table 4 and above, that the process of segmentation in Iraq license plate should pass through three steps, first for Arabic characters, second for English characters, and third for car type, while in EU plate, only a single stage will needed.…”

Section: Figure 2 Proposal System For License Plate Recognition Systemmentioning

confidence: 99%

Comparative Study between Iraqi and EU Vehicles License Plates in view of Segmentation and Recognition

2019

JAUS

View full text Add to dashboard Cite

License Plate Recognition (LPR) system uses license plates to recognize vehicles by using image processing technology. After increasing the implementations and applications on the vision of vehicles license plates around the world, the design of the plate became an important issue, and the information held by the plate should be selected properly to avoid redundancy and to improve the detection system performance. In Iraq, the new license plate was established in 2012. The goal of this paper is to evaluate the new Iraqi license plate by comparing it with that used in the European Union. The study compares them in terms of accuracy, performance and complexity. The evaluation shows that there are many redundancies and not useful regions in the Iraqi license plate that make the decision in the segmentation and recognition process more difficult. Keywords: characters segmentation; Iraqi license plate; license plate recognition (LPR); plate design; vehicle plate detection. RESUMEN/ El sistema de reconocimiento de matrículas (LPR) utiliza placas para reconocer vehículos mediante el uso de tecnología de procesamiento de imágenes. Después de aumentar las implementaciones y aplicaciones sobre la visión de las placas de vehículos en todo el mundo, el diseño de la placa se convirtió en un tema importante, y la información contenida en la placa debería seleccionarse adecuadamente para evitar la redundancia y mejorar el rendimiento del sistema de detección. En Iraq, la nueva matrícula se estableció en 2012. El objetivo de este documento es evaluar la nueva matrícula iraquí comparándola con la utilizada en la Unión Europea. El estudio los compara en términos de precisión, rendimiento y complejidad. La evaluación muestra que hay muchas redundancias y regiones no útiles en la matrícula iraquí que dificultan la decisión en el proceso de segmentación y reconocimiento. Palabras clave: segmentación de caracteres; Matrícula iraquí; reconocimiento de matrículas (LPR); diseño de placa; detección de placa de vehículo

show abstract

Section: Figure 2 Proposal System For License Plate Recognition Systemmentioning

confidence: 99%

Comparative Study between Iraqi and EU Vehicles License Plates in view of Segmentation and Recognition

2019

JAUS

View full text Add to dashboard Cite

show abstract

“…Back Propagation NN, Multilayer NN) RBFNN is chosen because it provides better feed forward neural network model, better generalization ability and is less calculated. In one approach, image features from component analysis extraction method were then feed into RBFNN for recognition process [1]. It was shown that component analysis and RBF provided better success rate than component analysis + Back Propagation NN.…”

Section: Introduction (Heading 1)mentioning

confidence: 99%

Malaysia car plate recognition based on RBF Neural Network and Particle Swarm Optimization

Maruzuki

Ishak

Setumin

2012

2012 IEEE International Conference on Control System, Computing and Engineering

View full text Add to dashboard Cite

show abstract

“…Since characters and plates are of different colors for human beings to distinguish, they should be of different values in the binary image. Some methods as in [69]- [73] are proposed to project the extracted binary license plate vertically to determine the starting and ending positions of the characters and horizontally to determine the position of each one. In [70], character color information replaced binary information in the projection.…”

Section: B Using Projection Profilesmentioning

confidence: 99%

Vehicle license plate detection and recognition

Ning¹

View full text Add to dashboard Cite

Car license plate recognition based on the combination of principal components analysis and radial basis function networks

Cited by 14 publications

References 2 publications

Comparative Study between Iraqi and EU Vehicles License Plates in view of Segmentation and Recognition

Comparative Study between Iraqi and EU Vehicles License Plates in view of Segmentation and Recognition

Malaysia car plate recognition based on RBF Neural Network and Particle Swarm Optimization

Vehicle license plate detection and recognition

Contact Info

Product

Resources

About