License plate character segmentation based on stroke width transform

Automatic License Plate Recognition (ALPR) has been the focus of many\nresearches in the past years. In general, ALPR is divided into the following\nproblems: detection of on-track vehicles, license plates detection, segmention\nof license plate characters and optical character recognition (OCR). Even\nthough commercial solutions are available for controlled acquisition\nconditions, e.g., the entrance of a parking lot, ALPR is still an open problem\nwhen dealing with data acquired from uncontrolled environments, such as roads\nand highways when relying only on imaging sensors. Due to the multiple\norientations and scales of the license plates captured by the camera, a very\nchallenging task of the ALPR is the License Plate Character Segmentation (LPCS)\nstep, which effectiveness is required to be (near) optimal to achieve a high\nrecognition rate by the OCR. To tackle the LPCS problem, this work proposes a\nnovel benchmark composed of a dataset designed to focus specifically on the\ncharacter segmentation step of the ALPR within an evaluation protocol.\nFurthermore, we propose the Jaccard-Centroid coefficient, a new evaluation\nmeasure more suitable than the Jaccard coefficient regarding the location of\nthe bounding box within the ground-truth annotation. The dataset is composed of\n2,000 Brazilian license plates consisting of 14,000 alphanumeric symbols and\ntheir corresponding bounding box annotations. We also present a new\nstraightforward approach to perform LPCS efficiently. Finally, we provide an\nexperimental evaluation for the dataset based on four LPCS approaches and\ndemonstrate the importance of character segmentation for achieving an accurate\nOCR.\n

Image processing-based vehicle recognition is one of the important research fields in ITS. The existing methods are all based on license plate recognition and car shape recognition. Their common problem is algorithm stability. And the license plates are easy to be changed. All information about vehicles should be used to recognize them reliably. A problem to be solved is to find a method to recognize vehicles besides license plate recognition and vehicle model recognition. Vehicle license plate location and character segmentation are critical steps in the license plate recognition system, and yet there are difficult problems to be solved. Kernel density estimation and Mean Shift theory

The intent of this research is to design a license plate recognition (LPR) system in the domain of Bangla language for smart vehicle management. The proposed system is designed on the basis of computer vision tools and deep supervised machine learning model. The system has three modules: license plate detection, character segmentation and recognition of the characters of the License Plate (LP). The goal of detection is to localize the plate area from the vehicle image and to crop region of interest (LP). It is executed by applying following process: preprocessing the image, conversion to binary image, contour detection and filtering the contours to get the LP's character contours, tilt correction and cropping the plate area from the image. Then, the cropped LP is segmented to extract the characters from the plate. Finally, the recognition step classifies the characters by means of deep convolution neural network where the features of the character are crafted and learned by the convolution layers of the networks. The system is implemented in Python OpenCV environment for offline car license plates images which are taken in different illuminations, road scenarios and colored cars. The system performance is evaluated in terms of detection rate, segmentation rate, recognition rate and execution time. The results illustrate that the performance of the system is remarkable.

In this paper, we present a robust Chinese license plate recognition system. The system consists of three modules: license plate localization, character segmentation and character recognition. In the license plate localization module, Color point pairs are searched to produce the plate region candidates coarsely, and the shape, texture features are used to refine the candidate. In character segmentation module, skew Correction, Character Segmentation and Thinning Processing is employed to improve the segmentation performance. In the character recognition module, SVM classifiers are used to generate effective result. Experimental result shows that License plate localization achieved accuracy of 94.19% and character recognition 94.51%.

As the difference of gray value between the numbers and letters on the license plate and the license plate background is very big. We first use region growing algorithm based on the gray value to separate each number and letter into different area. Secondly, we search for the bounding rectangles of all regions and find some rectangular sequences that meet a special condition. Thirdly, calculate the horizon bias for all rectangles according to the coordination of the up-right point in the rectangle, adjust and get the precise location of each rectangle. Forth, we get the binary image which can separate the numbers and letters on the license plates and the license plate background by the dynamic threshold algorithm. The relation of the maximum width of various license plate numbers and letters and its bounding rectangles helps to count the direction of the vertical bias, then the bias is adjusted. At last we statistic the foreground vertical histogram of the previous results, and get the result of precise vertical position and character segmentation. The experimental results show that this algorithm performs well for location of multi-national license plates.

In this paper, we propose a novel image segmentation algorithm for license plate recognition (LPR) in video based traffic surveillance system. The license plate character segmentation is most important procedure in LPR system. However, in real situation, the character segmentation algorithms are challenged by drastic performance decrease due to sudden local illumination changes, especially when the color of characters is similar to that of background in LP. To mitigate this problem, we introduce a novel LP character segmentation algorithm by employing an adaptive binarization method using super-pixel based degeneracy factor. The proposed method demonstrates a significant improvement over conventional methods.

License plate recognition (LPR) technology is a currently more popular pattern recognition processing technology, which has broad application prospects. In this chapter, based on the original LPR technology, a novel method of LPR based on the Sobel operator is presented. We improve the accuracy of LPR by establishing an eight-direction template, and the test results show that our improved algorithm is effective. Then we use the k-means algorithm for character segmentation of license plate to get the better license plate image segmentation.

Automatic License Plate Recognition (ALPR) is a growing research area as with the increase in the number of vehicles, requirements for high accuracy ALPR systems are increasing as it has been extensively used for automatic road tax collection, monitor unlike activities etc. Character segmentation is a major step in the ALPR system. This paper includes the use of image pre-processing techniques, K-means clustering, Otsu and Niblack method and Connected Component Analysis (CCA) to perform character segmentation. Unlike existing works which are based on license plates of other countries and therefore may not perform well on Indian license plates, in this work we have dealt with Indian license plates. Many of the existing works are based on license plates that are captured from a straight angle and good illumination and hence may not perform well if the images of license plates have noises or are captured at different angles. Therefore, in this work we have used license plates which are at different angles with different lighting conditions.

The aim of this research is to propose the method of license plate identification on Android platform and realized by using the open source visual library — OpenCV. First, introduce the process of license plate identification, then discuss the method of the realization of license plate location, license plate calibration, character segmentation and character identification. The identification of license plate is anti-interference, applicable to a variety of occasions and accuracy is relatively high according to the experiment results.

Automatic Identification of vehicles is a very challenging area, which is in contrast to the traditional practice of monitoring the vehicles manually. Automatic license plate (LP) recognition is one of the most promising aspects of applying computer vision techniques towards intelligent transportation system. In Location of the vehicle plate, a method of vehicle license plate character segmentation and extraction based on improved edge detection and Mathematical morphology was presented. In the first place, color images were changed into grey images, secondly through calculates the difference of each pixel and neighbourhood pixels to build up images edge and it can make the license plate stand out; Sobel operator is used to extract the edge of objects in image; then the algorithm applies the dilation and erosion mathematical morphology of binary images to get the image smooth contour. The segmentation result which is sent forward to LP recognition stage will improve further processing’s efficiency . Neural Network is used to recognize the license plate character. Because of the accuracy of the plate region extraction, the character can be extracted exactly from the plate region .

The rapid development of urban intelligence has turned intelligent transport system (ITS) development into a primary goal of traffic management. Automated license plate recognition (ALPR) for moving vehicles is a core aspect of ITS. Most ALPR systems send images back to a server for license plate recognition. To reduce delays and bandwidth use during image transmission, this study proposes an edge-AI-based real-time ALPR (ER-ALPR) system, in which an AGX XAVIER embedded system is embedded on the edge of a camera to achieve real-time image input to an AGX edge device and to enable real-time automatic license plate character recognition. To assess license plate characters and styles in a realistic setting, the proposed ER-ALPR system applies the following approaches: (1) image preprocessing; (2) You Only Look Once v4-Tiny (YOLOv4-Tiny) for license plate frame detection; (3) virtual judgment line for determining whether a license plate frame has passed; (4) the proposed modified YOLOv4 (M-YOLOv4) for license plate character recognition; and (5) a logic auxiliary judgment system for improving license plate recognition accuracy. We tested the proposed ER-ALPR system in selected real-life test environments in Taiwan. In experiments, the proposed ER-ALPR system achieved license plate character recognition rates of 97% and 95% in the day and at night, respectively. Through the AGX system, the proposed ER-ALPR system achieves a high recognition rate at a low computational cost.

The main principle of license plate recognition is to recognize the characters in the license plate which indicates the identity of the vehicle. This research will provide a system which can be implemented to the automatic payment in highway. Indonesian license plate consists of two parts, every of which has certain characters. These characters may become problem in the recognition process. Another problem is on the type of the license plate since Indonesia applies different color for every type of vehicle. In this research, different approaches are employed in the recognition of license plate; that is using character area as the feature value, also known as feature area, and K-Nearest Neighbor (KNN) as classification method. In addition, another method that has been used in our previous research is also employed to detect the character of license plate. The result shows very significant accuracy of 99.44%. In the process of recognition, scenario 1 gives the best accuracy at the K-1 value; that is 68.57% on the license plate and 92.72% on the characters of license plate. In the scenario 2 was obtained the license plate accuracy of 52% and license plate character accuracy of 89.36% with K-5. The system ran in a relatively short computational time.

In today's world automatic license plate recognition play an important role in monitoring and organizing vehicles. In this paper, we propose a method of detecting and recognizing the license plates of vehicles in an automatic way in our country. The system can be used to collect toll, in car parking and find stolen vehicles. We have used different image processing techniques like resizing image, image binarization, connected component analysis, image enhancement and noise filtering. Our system is composed of four main modules, such as detection of the license plate area, extraction of license plate. Then, segmentation of characters and words and finally recognition of the characters and words. As Bangladesh Road Transport Authority (BRTA) imposed a common standard for vehicle license plate, the size and aspect ratio of all license plates are same. We have used a threshold value to detect and extract the license plate based on our analysis. Afterward, for character segmentation, we used connected components. Later, we used deep learning tool ‘the Convolutional Neural Network’ for character recognition. Due to the lack of a standard data set, we have developed a customized dataset of Bangladeshi number plate for the implementation of our method. The accuracy of our proposed system is 95.42%.

At present, the clear license plate recognition algorithm has been mature, but for the blurred license plate which cannot be recognized by the human eye, the recognition rate of the traditional license plate recognition algorithm is too low. In view of this, a license plate character recognition algorithm based on convolutional neural network structure is proposed. In this study, a large number of training samples of fuzzy characters are constructed, and a convolutional neural network is trained for blind segmentation of fuzzy license plate characters. By calling the trained convolutional neural network, we can recognize the characters after blind segmentation. The experimental results show that the training set accuracy is close to 100%, and the accuracy of the test set is more than 93%. It can recognize the license plate characters which cannot be recognized by the human eye.

Character segmentation is a necessary preprocessing step for character recognition in many license plate recognition systems. It is important because incorrectly segmented characters are less likely to be recognized correctly. In this article segmentation scheme of Indian LP has been proposed with some unconventional and easy-to implement technique — The connected component analysis. In this paper the first part is taken into consideration some preprocessing operations and the second part is for connected component analysis by means of labelling algorithm, aspect ratio analysis and pixel count analysis. By using the corresponding co-ordinates, characters are extracted from the license plate. Results for this method are promising even in tough conditions.