ARM架构下计算机图像并行化处理技术研究  

Computer Image Parallelization Processing Technology in ARM Architecture

作　　者：张鑫 

机构地区：[1]青海民族大学计算机学院,西宁810007

出　　处：《计算机测量与控制》2017年第12期237-239,250,共4页Computer Measurement &Control

摘　　要：为在图像处理与分析时具备良好的视觉效果,提高图像处理的速度,需要对ARM架构下计算机图像并行化处理技术进行研究;当前采用的方法是对各种变换频域图像特征提取与计算机图像集合特征的提取进行相结合,克服了当前对图像进行提取时存在图像形状描述的缺陷,提取图像特征向量维数相对较低;实验表明,通过对图像进行特征提取能很好地对图像效果进行展示,将图像的纹理特征进行详细的表述,将该方法应用到图像处理技术当中,具有良好的去噪效果及扩展性,该方法过程简单,但存在图像视觉效果较差的问题;为此,提出一种ARM架构下计算机图像并行化处理技术研究方法;该方法首先利用非局部均值去噪算法对图像进行去噪处理,然后结合图像去噪的结果利用小波变换对去噪图像进行边缘检测,最后采用非线性增强算法对图像进行增强完成对ARM架构下计算机图像并行化处理技术研究;实验结果表明,所提方法不仅提高图像处理速度,还提高图像视觉效果,具有广泛的应用价值。In order to have good visual effects and improve the speed of image processing in image processing and analysis, it is necessary to study the parallel processing technology of computer image under ARM architecture. The current method is used to extract and transform domain image feature with computer image collection characteristics combined to overcome the current extraction of image defects of image shape description and extraction of image feature vector dimension is relatively low. Experimental results show that the good display effect through the image to extract the features of the images, the image texture features were detailed description, the method is applied to image processing technology, has good denoising effect and expansibility, the process is simple, but has poor visual effect of image problem. There- fore, a method of parallel processing of computer image under ARM architecture is proposed. This method uses the non local mean denoising algorithm for image denoising, and then combined with the results of image denoising using wavelet transform to detect the edge of image de- noising, the nonlinear enhancement algorithm to enhance the completion of the parallel ARM architecture of computer image processing tech- nology research on image. The experimental results show that the proposed method can not only improve the image processing speed, but al- so improve the visual effects of the image. It has a wide range of practical value.

关 键 词：ARM架构 图像并行化处理 非局部均值算法 小波变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]