The study of license plate character segmentation algorithm based on vetical projection

Xia, Huadong; Liao, Dongchu

doi:10.1109/cecnet.2011.5768714

Cited by 26 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [4] character Segmentation is done using vertical projection method. The horizontal projection calculation, horizontal frame of license plate removal, vertical projection calculation and fining the edge of character all are under Segmentation process.…”

Section: Related Workmentioning

confidence: 99%

Automatic License Plate Recognition Technique using Convolutional Neural Network

Das¹,

Mukherjee²

2017

IJCA

View full text Add to dashboard Cite

This research work purposes an automated system for recognizing license plate technique using Convolutional Neural Network. On Indian roads there are variety of number plate format and variety of fonts are used in vehicles and the most common vehicle number plate used yellow or white as background and black used as foreground color. The proposed model can be partitioned into four parts-1) Digitization of image 2) character segmentation 3) Padding and Resize 4) Character Recognition. Here, Character Segmentation is done using connected component analysis. After that convolutional neural Network is used for recognition of characters. In the proposed system, Character segmentation and resize and padding of the image is done using MATLAB and Character Recognition part is done using PYTHON. The performance of the proposed algorithm has been tested on real car images. The proposed system is mainly applicable to West Bengal cars' license plates. Experimental verification is done using a dataset of 45 images in different environmental conditions. General TermsImage processing, convolutional neural network.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic License Plate Recognition Technique using Convolutional Neural Network

Das¹,

Mukherjee²

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Character segmentation is not a problem anymore since a lot of research have been done and shows promising results. However, it still poses a challenge for accurate character segmentation under the situation when the characters are connected together and plate boundaries connected to inside characters [1], [2], [7], [10]. Most existing methods uses prior knowledge for example the number of characters and the significant spacing interval between each character to segment the characters effectively but fails in this case.…”

Section: Reviews On Related Workmentioning

confidence: 99%

“…1. This paper presents a character segmentation method of car plates based on skew correction and mainly focuses on standard plates based on three assumptions: (1) the width of the characters is relatively stable except for character printed with '1', (2) the height of special character differs from normal character, and (3) the spacing between characters is the same.…”

Section: Introductionmentioning

confidence: 99%

A design method for Malaysian car plates character segmentation based on skew correction

Tan

Abu-Bakar

2012

2012 IEEE International Conference on Control System, Computing and Engineering

View full text Add to dashboard Cite

This paper presents a license plate character segmentation method in the context of Malaysian cars. First of all, pre-processing steps will enhance the image before Laplacian pyramid takes place. For a proper binarization, Laplacian pyramid which up-sampled the image from an image lower in the pyramid when the image is captured under low resolution. By using Sobel edge detector and then median filtering, circumscribe rectangle of minimum area is formed and the angle is calculated. At the same time, the area of characters is focussed. The characters are then selected based on connected component analysis after applying Niblack's threshold. Our goal is to segment the characters properly from the steps mentioned. Therefore, our algorithm tries to find the best point to segment the characters using little prior knowledge. Experimental shows promising results on the flexibility of the proposed design method.

show abstract

“…A study of the effectiveness of the CCA technique concluded that vertical projection can segment characters effectively. 17 The segmentation approach proposed by Shapiro & Gluhchev 8 utilizes an adaptive iterative thresholding approach to binarize the image and then segment the plate characters by employing a connected component analysis. Jagannathan et al 18 proposed a method that uses ten samples of the same plate, binarize them, select the best one and then segment it using vertical projections.…”

Section: License Plate Character Segmentationmentioning

confidence: 99%

Benchmark for license plate character segmentation

Gonçalves

Silva

Menotti

et al. 2016

J. Electron. Imaging

View full text Add to dashboard Cite

Abstract. Automatic License Plate Recognition (ALPR) has been the focus of many researches in the past years. In general, ALPR is divided into the following problems: detection of on-track vehicles, license plates detection, segmention of license plate characters and optical character recognition (OCR). Even though commercial solutions are available for controlled acquisition conditions, e.g., the entrance of a parking lot, ALPR is still an open problem when dealing with data acquired from uncontrolled environments, such as roads and highways when relying only on imaging sensors. Due to the multiple orientations and scales of the license plates captured by the camera, a very challenging task of the ALPR is the License Plate Character Segmentation (LPCS) step, which effectiveness is required to be (near) optimal to achieve a high recognition rate by the OCR. To tackle the LPCS problem, this work proposes a novel benchmark composed of a dataset designed to focus specifically on the character segmentation step of the ALPR within an evaluation protocol. Furthermore, we propose the Jaccard-Centroid coefficient, a new evaluation measure more suitable than the Jaccard coefficient regarding the location of the bounding box within the ground-truth annotation. The dataset is composed of 2,000 Brazilian license plates consisting of 14,000 alphanumeric symbols and their corresponding bounding box annotations. We also present a new straightforward approach to perform LPCS efficiently. Finally, we provide an experimental evaluation for the dataset based on five LPCS approaches and demonstrate the importance of character segmentation for achieving an accurate OCR.

show abstract

The study of license plate character segmentation algorithm based on vetical projection

Cited by 26 publications

References 6 publications

Automatic License Plate Recognition Technique using Convolutional Neural Network

Automatic License Plate Recognition Technique using Convolutional Neural Network

A design method for Malaysian car plates character segmentation based on skew correction

Benchmark for license plate character segmentation

Contact Info

Product

Resources

About