论文部分内容阅读
在矿用钢丝绳芯输送带X光图像采集过程中,由于点光源到线阵探测器的各像素点的距离不同,以及每一像素点的物理特性存在差异,造成图像不均匀。采用Butterworth低通滤波器对X光图像滤波,经过去噪、平滑处理,得到去除噪声后的图像;结合Retinex理论建立了基于基函数的不均匀光照背景估计模型,利用该模型对去除噪声后的图像灰度校正,得到校正后的图像;利用拉伸图像对比度的方法增强校正后的图像对比度,从而去除原始图像的不均匀光照的影响,得到增强后的图像。试验结果表明,该算法能有效校正不均匀X光图像,提高了图像对比度,为进一步矿用输送带的检测和图像处理奠定了基础。
In the process of X-ray image acquisition of mining steel cord conveyor belt, the image is not uniform due to the different distances between the point light source and the line detector and the physical characteristics of each pixel point. The Butterworth low-pass filter is used to filter the X-ray image, and the image after noise removal is smoothed to obtain the image with no noise. Based on the theory of Retinex, a non-uniform illumination background estimation model based on basis function is established. With this model, The image is corrected by the gray level to obtain a corrected image. The contrast of the image is enhanced to enhance the contrast of the corrected image, thereby removing the influence of the uneven illumination of the original image to obtain an enhanced image. The experimental results show that this algorithm can effectively correct the non-uniform X-ray images and improve the image contrast, which lays the foundation for the further detection and image processing of mining conveyor belt.