摘要
研究提出了一种应用于车型识别系统中的基于序列图像的图像处理方法。该方法对采集的彩色序列图像进行灰度化、平滑去噪、序列图像差分、Sobel边缘检测、横/纵向填充、图像修正、边缘提取等一系列的图像处理,并最终识别车型。其中,与传统的车型背景分离法相比,序列图像差分对汽车从实际背景中分离出来起着重要的作用,达到了很好的分离效果。通过利用Matlab进行了实际检验,结果表明,该一系列的车型识别方法是可行的,并对低质量和背景复杂图像有着良好的处理效果。
This paper is researching on vehicle type recognition based on sequence images in the vehicle type automatic recognition system. There are several continuous ways for it： color image gray - scale processing, image smoothing and denoising, sequence image differencing, Sobel edge detecting, horizontal and vertical filling, image correcting, feature extracting and vehicle type recognizing. Meanwhile, comparing the traditional background image segmentation, sequence image difference plays an important role in the background image segmentation, and it reaches a very fine effect. Through the Mat.lab simulating results, the algorithm based on image difference is good for the background image segmentation, and also can commendably keep edge character of the original image and have a good effect in low - quality or complex background images.
出处
《惠州学院学报》
2009年第3期47-51,共5页
Journal of Huizhou University
基金
惠州学院科研基金项目(C206.0212)
关键词
图像处理
序列图像
图像差分
边缘检测
车型识别
image processing
sequence image
image difference
edge detection
vehicle type recognition
