Image series segmentation and improved MC algorithm

A semiautomatic segmentation method based on active contour is proposed for computed tomography （CT） image series. First, to get initial contour, one image slice was segmented exactly by C-V method based on Mumford-Shah model. Next, the computer will segment the nearby slice automatically using the snake model one by one. During segmenting of image slices, former slice boundary, as next slice initial contour, may cross over next slice real boundary and never return to right position. To avoid contour skipping over, the distance variance between two slices is evaluated by an threshold, which decides whether to initiate again. Moreover, a new improved marching cubes （MC） algorithm based on 2D images series segmentation boundary is given for 3D image reconstruction. Compared with the standard method, the proposed algorithm reduces detecting time and needs less storing memory. The effectiveness and capabilities of the algorithm were illustrated by ,experimental results.     

隧道检测裂缝的图像处理研究

裂缝是隧道衬砌最常见的病害之一,基于近几年快速发展的工程检测系统与图像处理算法的研究,提出基于CCD相机的衬砌裂缝检测系统来采集裂缝图像。通过比较均值滤波、中值滤波、维纳滤波、自适应中值滤波和加权邻域滤波比较,选择自适应中值滤波进行图像增强。结合直方图阈值分割法、Otsu最大类间方差阈值和局部阈值分割法,对增强后图像进行二值化处理比较,Otsu法较好地保留了裂缝的边缘信息,证明了该算法的有效性,为后续裂缝信息的提取奠定了基础。     

一种基于遗传算法和小波分解的刚性图像配准方法

为了实现快速、高精度的自动图像配准,提出了基于遗传算法和小波分解的图像配准方法。此方法在小波分解的基础上,以互信息为相似性测度利用遗传算法为搜索算法对图像进行一次配准,然后以特定步长在小范围内对配准参数进行修正,对图像进行二次配准。该方法实验结果表明该方法具有较快的速度且显著的改善了配准精度。     

小波变换和梯度对多聚焦图像的多分辨率融合

提出一种结合Roberts梯度和小波变换的图像融合方法.该方法对低频分量采用加权平均,对高频分量采用结合梯度平均值的规则.实验结果表明,该方法能够提高多分辨率图像融合方法的效果.     

A semi-fragile wavelet transform watermarking scheme for content authentication of images

A novel semi-fragile watermarking scheme for the content authentication of images using wavelet transform (WT) is presented in this paper. It is tolerant to the embedded wavelet image compression methods based on WT such as embedded zerotree wavelet (EZW), set partitioning in hierarchical trees (SPIHT) and embedded block coding with optimized truncation (EBCOT) in JPEG2000 to a pre-determined bit-plane, but is sensitive to all other malicious attacks. The image features are generated from the lowest-frequency (LF) subband of the original image as the embedded watermark. The watermark is embedded into the pre-determined bit-plane by adjusting the corresponding values in the given subband. In the process of watermarking authentication, we compare the image features generated from the LF subband of the received image with the embedded watermarking information (the image features of the original image) extracted from the pre-determined bit-plane in the given subband of the received image to decide whether the image is attacked maliciously or processed acceptably (the embedded wavelet compression). The most important advantage of our watermarking scheme is that the watermark information can be extracted from the watermarked image when detecting watermark, so the received image authentication needs no information about the original image or watermark. Experimental results prove the effectiveness of our proposed watermarking scheme.     

基于图像熵的火灾烟雾识别

提出了一种基于图像熵的烟雾运动模式识别方法,用来实现对火灾烟雾的探测.通过对烟雾自由扩散模型的理论分析,得出了烟雾扩散熵增运动的特征.通过引入信号学中"图像熵"的理论,用来捕捉烟雾运动造成的熵变特征,进而实现火灾烟雾的检测.经过实验的验证和分析,并对图像熵值的变化进行傅立叶变换,得出了干扰运动和烟雾运动具有不同特征信号的结论,从而实现了烟雾的识别.与以往研究者通过研究视频烟雾的图像特征出发不同,文中从烟雾的热力学的性质和它在流体力学方面的运动特征,得出它与一般的刚体具有截然不同的运动模式的理论,以图像熵作为核心参量,得出一种实用高效的火灾烟雾检测算法.实验表明:这种检测算法受到环境的干扰较小,特别适合复杂环境的烟雾检测,并可以用于对火灾环境的评估.     

基于PM方程的指纹扫描仪图像增强算法研究

为降低产品成本,在采用低端CMOS图像传感器的指纹扫描仪中,采集的图像易出现通道不均衡、清晰度不高、噪声大等缺点,为了提高图像质量,提出了基于PM偏微分方程的增强指纹图像的综合算法,通过USM锐化算法和偏微分方程噪声滤波算法的有效结合,同时对USM算法和偏微分噪声滤波算法进行了优化,能显著改善图像质量,通过标准测试程序检测达到国际通用的认证标准。     

沥青混凝土数字图像集料粘连效应分割方法研究

根据沥青混凝土切片图像的灰度分布特点,探讨了沥青混凝土数字图像处理的流程与方法.针对集料图像粘连问题,采用分水岭分割方法对粘连集料进行分割,验证了该方法的有效性;并且借助分割后的二值图像对集料的就位方向进行统计,明确了集料就位方向与集料扁平程度的相关性.研究结果表明分水岭分割方法具有良好的适用性,集料的就位方向明显受到集料扁平程度的影响,集料越扁平其就位方向越集中.     

独立分量分析在含有多种噪声的图像去噪中的应用

提出一种基于负熵的分数低阶独立分量分析(ICA)算法,为使算法更好的适用于实际环境,结合当下较为新颖的Volterra滤波方法——VLMS算法,该算法对高斯噪声有良好的去除效果.仿真结果表明,算法对于含有两种噪声的混合图像具有良好的分离特性及实际意义.