基于SOM神经网络聚类的车牌号码倾斜校正算法

经过摄像机摄入的图像会发生倾斜,给车牌的准确识别带来了困难.针对此问题,利用SOM神经网络良好的聚类性能,在水平倾斜校正时,把车牌号码图像中的像素坐标聚成两类,拟合成一条直线,计算出该直线倾斜角,完成水平校正;按照以上同样方法进行垂直倾斜校正.实验结果表明,该方法能准确获取车牌号码的倾斜角,算法结构简单,抗干扰能力较强,符合汽车牌照图像的特点,具有较好的处理效果.     

基于局部投影方差的快速车牌校正方法

车牌倾斜与错切校正作为车牌识别的重要环节,虽已提出不少方法,但仍存在准确度低、效率低等不足。鉴于现有方法的不足提出一种高效的车牌倾斜与错切校正方法。首先,根据车牌图像的投影方差存在着明显的局部性规律,提取车牌的局部特征图像用于角度检测。并提出一种基于坐标旋转的最大投影方差获取方法,快速得到车牌水平倾斜角度和垂直错切角度。此外,针对字符本身的结构对于垂直错切角度检测的影响,提出相应的解决策略。最终使用3000张情况各异的车牌进行实验。实验结果表明,在正确率比现有传统方法略高的情况下,算法效率也得到大幅提升。     

一种新的车牌定位与倾斜校正方法

为了在不同条件下对车牌进行定位与倾斜校正,提出了一种基于字符特征匹配的车牌定位与倾斜校正方法。该方法考虑到我国车牌首位字符为汉字的显著特征,利用标准车牌汉字库,采用特征匹配对车牌中的汉字进行定位。由于汉字在我国车牌中的位置严格固定,因此,对汉字的成功定位,也就实现了对整个车牌的定位与倾斜校正。对不同背景、不同光照条件下的车牌进行大量实验,结果表明该方法能够准确地进行车牌定位与倾斜校正,具有良好的鲁棒性。     

一种新的基于Radon变换的车牌倾斜校正方法

车牌的倾斜给车牌字符分割与识别带来不利的影响。基于Radon变换,提出了一种新的车牌倾斜校正方法。对车牌图像在[-20°,20°]范围内进行Radon变换,并对变换后的结果求一阶导数绝对值的累加和,将累加和的最大值所对应的Radon变换的角度作为倾斜角度。对水平倾斜的车牌进行双线性插值旋转校正,对垂直倾斜的车牌进行双线性插值错位偏移校正。实验结果证明,该方法简单实用,对光照、污迹等不敏感,抗干扰能力强。     

一种车牌识别系统中的混合车牌定位方法

提出了一种新的粗定位和精细定位相结合的车牌定位方法.首先采用一种基于垂直边缘和车牌句法的车牌粗定位算法,确定车牌候选区域,剔除伪区域,粗定位可以快速地将车牌从原始车辆图像中截取出来,同时精确确定车牌的上下边界.然后再进行基于旋转差分投影的车牌水平精确定位与倾斜校正,由于水平定位和倾斜校正同时进行,提高了水平分割的精度并降低了定位时间.实验表明该混合方法能快速、精确地进行车牌定位,有效地解决了复杂背景下的车牌定位精度不高的问题,同时对模糊车牌具有很强的抗干扰性.     

基于水平垂直灰度开运算的车牌字符分割算法

采用Hough变换检测车牌的倾斜角度进行车牌的矫正。提出了一种基于水平垂直结构元素开运算的数学形态学方法,对字符分割前的车牌进行预处理。该方法能够在车牌定位不精确的情况下有效地去除车牌边框、铆钉及其他噪声,消除干扰突出字符。运用传统的投影法以及车牌的先验知识进行字符间的分割,有效地提高了字符分割的效果。实验结果证明,该方法有效可行。     

基于最小二乘和最小投影距离的车牌倾斜校正

在车牌图像的采集过程中,经常会有车牌倾斜的现象发生,这种倾斜给后续的字符分割和字符识别造成了很多不利影响。为此,文中提出了一种基于最小二乘和最小投影距离的车牌倾斜校正方法。该方法将车牌倾斜分成水平倾斜和垂直倾斜两部分:对于水平倾斜,首先对二值化后的车牌去边框和铆钉,再对车牌利用最小二乘拟合直线求取倾斜角;而对于垂直倾斜,则引入分块查找法来降低查找最小投影距离的执行次数,从而提高算法的执行效率。实验结果表明:该算法简单实用,能够准确地对车牌进行校正。     

A self-adaptive correction method for perspective distortions of image

Frequently, the shooting angles available to photograph an object are limited, and the resultant images contain perspective distortions. These distortions make more difficult to perform subsequent tasks like feature extraction and information identification. This paper suggested a perspective correction method that extracts automatically distortion features through edge detection. Results showed that this method is powerful in correcting images with perspective distortions. The corrected image has virtually little information missing, clear features and high recovery rate.     

基于自适应阈值投影的双行车牌分割方法

Aiming at the problem that there are few algorithms and low correct segmentation rate of double row license plate number in China, an adaptive projection method for double row license plate segmentation is proposed. Firstly, the image of license plate in HSV (Hue Saturation Value) space is binarized. Secondly, the double line license plate is segmented into a single line license plate by the adaptive projection method. Finally, the characters on the license plate number are segmented. Experiments show that this method can effectively segment the double line license plate with white characters on blue background, red characters on white background, black characters on green background, and black characters on yellow background, and the correct segmentation rate of the double line electric bicycle brand is higher. At the same time, this method overcomes the shortcomings of the deep learning method such as long training time and a large number of data sets. The proposal t is a simple and efficient segmentation method.     

一种车牌图像中的字符快速分割与识别方法

该文主要研究实时交通流的车牌识别问题,运用局部最小值方法完成车牌中的字符分割,应用轮廓特征解决字符的识别问题。开发出实用的算法。在实际的车牌识别中,算法具有速度快、识别能力强的优点。     

A configurable method for multi-style license plate recognition

Despite the success of license plate recognition (LPR) methods in the past decades, few of them can process multi-style license plates (LPs), especially LPs from different nations, effectively. In this paper, we propose a new method for multi-style LP recognition by representing the styles with quantitative parameters, i.e., plate rotation angle, plate line number, character type and format. In the recognition procedure these four parameters are managed by relevant algorithms, i.e., plate rotation, plate line segmentation, character recognition and format matching algorithm, respectively. To recognize special style LPs, users can configure the method by defining corresponding parameter values, which will be processed by the relevant algorithms. In addition, the probabilities of the occurrence of every LP style are calculated based on the previous LPR results, which will result in a faster and more precise recognition. Various LP images were used to test the proposed method and the results proved its effectiveness.     

彩色图像自微分车牌区域定位技术

车牌定位是实现智能交通系统的关键因素之一。在RGB色彩空间中,运Sl自微分技术实现了图像的二值化,利用水平膨胀、腐蚀技术完成了形态学处理。最后,通过由下向上扫描确定连通区域的矩形边界,结合车牌的几何尺寸,给出车牌区域的具体坐标。     

指针式仪表自动读数识别技术的研究现状与发展

指针式仪表自动判读技术是当前机器视觉研究的热点,也是模式识别领域一项重要的研究内容和前沿技术。在对指针式仪表识别技术进行了一般性概述之后,详细介绍了基于机器视觉的指针式仪表自动读数识别技术的基本概念、基本原理和主要研究内容,介绍了该技术在国内外的研究现状,同时重点介绍了图像校正、圆形表盘轮廓检测、指针线检测和角度计算等主要研究内容的最新进展,最后给出了指针式仪表自动读数识别涉及的关键技术和发展方向。     

Movement invariants-based algorithm for medical image tilt correction

In this paper, the edge detection for a medical image is performed based on Sobel operator, and the bounding box is obtained, by which the effective medical sub-image is extracted. Then, the centroid and the normalized central moments of the medical sub-image are calculated, and the rotation angle α is obtained by minimizing the second-order central moment based on its rotation invariance. Finally, the whole medical image is rotated around the centroid by -α to correct the tilted image. Furthermore, inspired by the uniformity degree of the image, the rotation angle α is revised, which achieves a better correction effect and performance. The experimental results show that the proposed algorithms are fairly reliable and accurate for the determination of tilt angles, and are practical and effective tilt correction techniques.     

A new and robust method for character segmentation and recognition in license plate images

This paper provides a new and fast method for segmentation and recognition of characters in license plate images. For this purpose, various methods have been proposed in literature. However, most of them suffer from: sensitivity to non-uniform illumination distribution, existence of shade in license plate, license plate color and the need for receiving an exact image of the license plate. In the proposed algorithm, non-uniform illumination and noise are reduced by a Gaussian lowpass filter and also by an innovational Laplacian-like transform and characters are segmented by a set of indigenous and relative features. To be prepared for recognition, the segmented characters are normalized by a local algorithm. Two feed-forward neural networks with back-propagation learning method are employed for character recognition. The principal component analysis (PCA) is used to decrease input data and, consequently, computational complexity. The proposed algorithm does not necessarily need an exact plate image and can receive a band from the vehicle original image as an input, which includes the plate. Our proposed method is completely robust to the disturbances such as non-uniform brightness distribution on the various positions of a license plate image and the plate color. In order to evaluate our algorithm, we applied it on a database including 120 vehicle images with different backgrounds, plate colors, brightness distributions, distances and viewing angles. The results confirm the robustness of the proposed method against severe imaging conditions.     

一种快速、高效的车牌定位方法

基于车牌区域丰富的边缘特征,本文提出了一种改进的车牌定位方法。首先增强原始图像,并对原始图像和增强图像分别进行边缘提取;然后基于车牌区域边缘均匀,长短有限等特征,滤除背景及噪声边缘点;最后通过投影搜索出车牌区域。对采集到的各种复杂背景、环境下的车辆图像进行了大量实验,实验结果证明算法准确率高、适应性强。     

基于FCM颜色聚类的车牌定位方法

提出了一种基于FCM颜色聚类的车牌定位方法。首先应用高斯差分算子对图像进行二值化;其次进行中值滤波;然后利用形态滤波,基于车牌的结构特征进行车牌的粗定位;最后基于FCM颜色聚类进行车牌的精定位。对各种条件下采集的250幅车辆图像进行实验,定位率在98%以上,同时该算法对光照影响有很好的鲁棒性。     

利用伴生与互补颜色特征的车牌定位新方法

车牌定位是车牌识别系统的关键技术,车牌定位的准确与否直接影响车牌识别的结果。车牌区域的颜色特征是车牌的重要信息,针对车牌区域的颜色特征,论文提出了一套利用车牌区域的伴生与互补特征进行定位的算法。该算法利用车牌区域的颜色特征,快速定位到与车牌颜色有关的区域;然后利用车牌区域伴生与互补特性快速去除具有与车牌区域相同颜色的其他非车牌区域;最后使用投影积分进行车牌的精确定位。通过对200幅从交通卡口获取的真实的彩色图像进行试验,准确定位率为98%。     

一种利用Hough变换和先验知识的车牌识别新方法

在车牌定位上,针对当前实际中存在的一些困难,结合先验知识,提出了一种Hough变换多线检测的由粗到精的定位算法.在字符分割中,通过合理改进,使投影法的准确性进一步得到提升.并在大量实验的基础上,将BP神经网络反复修正,使得系统理论识别率达到了91.00%,结果表明此方法是行之有效的.     

基于SIFT特征匹配的车牌识别方法

针对智能交通系统中基于视觉的车牌识别中存在的依赖于光学字符识别以及在复杂环境下准确率低的问题,提出了基于SIFT特征匹配的车牌识别方法。通过基于插值的超分辨率图像重建方法对车牌图像进行预处理,基于轮廓特征对车牌进行定位,通过SIFT特征匹配的方式,利用模板库中的车牌字符模板对车牌进行定位验证以及字符识别。实验结果表明该方法能有效提高车牌识别的效率。