基于全局拼接的航拍图像拼接算法研究

研究航拍图像的拼接问题,提高图像拼接的准确度。由于当通过航拍获取的图像中部分图像相互存在重叠区域的比例不大时,造成拼接不准确。传统的区域的图像拼接算法无法将具有较小重叠区域的图像准确拼接。为了提高航拍图像拼接的准确率,提出一种全局的图像拼接算法,通过使用SIFT算法提取图像的SIFT特征点,根据位置误差最小的原则完成两幅图像的SIFT特征点匹配,最后利用整体最优化方法对拼接结果进行优化,采用全局特征点的拼接方法,可避免传统方法只利用重叠区域灰度特征而不能准确拼接低重叠度图像的问题。实验证明,改进方法利用图像的全局信息,准确地实现图像的拼接,取得了满意的结果。     

基于梯度的多曝光图像融合

针对运动场景拍摄的不同曝光度的图像序列,提出基于梯度的多曝光图像融合方法,将不同曝光度的图像细节呈现到同一张普通图像上。该方法是直接加权融合的方法,先用梯度信息来定义权值,然后用多分辨率加权融合。实验表明,本文的方法取得较好实验结果,消除运动物体对图像融合产生的影响,同时增强了图像的细节表现能力,具有较好的实用价值。     

指纹图像分割方法的研究

本文在研究和分析方差法和方向图法的基础上,提出了一种基于最大类间方差的指纹图像分割方法,即采用最大类间方差与图像分块处理相结合的方法来分割指纹图像。实验结果表明,该方法无论是对高对比度的指纹图像还是对低对比度的指纹图像均有良好的分割效果;相对于传统的指纹图像分割方法,本文的方法不仅具有无需根据经验来选择阈值的优点,而且该方法在运算速度上比传统方法更快,更适合于实时处理。     

SAR图像边缘检测方法综述

边缘检测是SAR图像解译的基本问题之一。固有的乘性噪声特性使得经典的梯度边缘检测方法并不适用于SAR图像,因此研究针对SAR图像的边缘检测方法具有重要的意义。本文对SAR图像边缘检测问题进行了系统的研究,简单描述了SAR图像边缘检测问题,讨论了现有的SAR图像边缘检测方法,总结了SAR图像边缘检测中存在的两个问题——边缘细化和边缘定位,对检测结果的性能评估方法也进行了概括。最后在总结现有研究成果的基础上展望了SAR图像边缘检测的发展方向。     

基于边缘算子的车牌图像二值化方法

提出一种基于Canny边缘算子的车牌图像二值化方法。该方法综合考虑了边缘信息和灰度信息,根据与边缘像素点相邻的像素点的灰度值变化特点,得到图像的高、低阈值,综合利用高、低阈值对原灰度图像进行二值化。实验表明,此方法对于车牌图像的二值化处理有令人满意的效果。     

Hiding a halftone secret image in two camouflaged halftone images

In this paper, we shall propose a method to hide a halftone secret image into two other camouflaged halftone images. In our method, we adjust the gray-level image pixel value to fit the pixel values of the secret image and two camouflaged images. Then, we use the halftone technique to transform the secret image into a secret halftone image. After that, we make two camouflaged halftone images at the same time out of the two camouflaged images and the secret halftone image. After overlaying the two camouflaged halftone images, the secret halftone image can be revealed by using our eyes. The experimental results included in this paper show that our method is very practicable. The text was submitted by the authors in English. Wei-Liang Tai received his BS degree in Computer Science in 2002 from Tamkang University, Tamsui, Taiwan, and his MS degree in Computer Science and Information Engineering in 2004 from National Chung Cheng University, Chiayi, Taiwan. He is currently a PhD student of Computer Science and Information Engineering at National Chung Cheng University. His research fields are image hiding, digital watermarking, and image compression. Chi-Shiang Chan received his BS degree in Computer Science in 1999 from National Cheng Chi University, Taipei, Taiwan, and his MS degree in Computer Science and Information Engineering in 2001 from National Chung Cheng University, Chiayi, Taiwan. He is currently a PhD student of Computer Science and Information Engineering at National Chung Cheng University. His research fields are image hiding and image compression. Chin-Chen Chang received his BS degree in Applied Mathematics in 1977 and his MS degree in Computer and Decision Sciences in 1979, both from National Tsing Hua University, Hsinchu, Taiwan. He received his PhD in Computer Engineering in 1982 from National Chiao Tung University, Hsinchu, Taiwan. During the academic years of 1980–1983, he was on the faculty of the Department of Computer Engineering at National Chiao Tung University. From 1983–1989, he was on the faculty of the Institute of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan. From 1989 to 2004, he has worked as a professor in the Institute of Computer Science and Information Engineering at National Chung Cheng University, Chiayi, Taiwan. Since 2005, he has worked as a professor in the Department of Information Engineering and Computer Science at Feng Chia University, Taichung, Taiwan. Dr. Chang is a fellow of the IEEE, a fellow of the IEE, and a member of the Chinese Language Computer Society, the Chinese Institute of Engineers of the Republic of China, and the Phi Tau Phi Society of the Republic of China. His research interests include computer cryptography, data engineering, and image compression.     

基于颜色衰减的自适应去雾算法

雾霾使室外拍摄的图像、视频画质退化严重,给室外安防和交通监控等系统的正常运行带来困难。去雾算法旨在恢复图像质量,增强图像对比度和清晰度。本文提出了一种结合大气散射模型与颜色衰减先验的去雾复原模型,并以新增可见边比为评价标准,给出了模型参数的自适应求取方法,并采用引导滤波对透射率进行优化,从而较好地恢复出无雾图像。对有雾图像分别采用本文方法和三种现有去雾算法进行对比实验,从实验结果看,基于颜色衰减的自适应去雾算法可使图像清晰度、对比度得到较大的提高,与其他算法相比,在实时性和清晰度方面有一定优势。     

Processing Sparse Panoramic Images via Space Variant Operators

The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision. We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.

一种多传感器图像的彩色融合系统

针对像素及多传感器图像的融合问题,设计了一种多传感器图像的彩色融合系统。该系统首先采用Laplacian金字塔变换算法得到灰度融合图像,然后产生共有图像、差异图像和细节增强图像,最后将灰度融合图像、细节增强图像,分别送入RGB通道得到彩色融合图像。实验结果表明,本系统可以有效地对多传感器图像进行彩色融合。根据熵和颜色丰富度两个客观评价指标,本系统的彩色融合图像更清晰,更容易识别目标,包含更多的细节信息,图像信息也更加丰富。     

Generalised residual images’ effect on illumination artifact removal for correspondence algorithms

The intensity (grey value) consistency of image pixels in a sequence or stereo camera setup is of central importance to numerous computer vision applications. Most stereo matching and optical flow algorithms minimise an energy function composed of a data term and a regularity or smoothing term. To date, well performing methods rely on the intensity consistency of the image pixel values to model the data term. Such a simple model fails if the illumination is (even slightly) different between the input images. Amongst other situations, this may happen due to background illumination change over the sequence, different reflectivity of a surface, vignetting, or shading effects.In this paper, we investigate the removal of illumination artifacts and show that generalised residual images substantially improve the accuracy of correspondence algorithms. In particular, we motivate the concept of residual images and show two evaluation approaches using either ground truth correspondence fields (for stereo matching and optical flow algorithms) or errors based on a predicted view (for stereo matching algorithms).     

基于分存的多幅图像信息隐藏方案*

在秘密图像分存的基础上,提出一种多幅图像进行信息隐藏的算法。首先把秘密图像分存到指定的两个毫无关系的图像中,然后在公开图像的奇数行（列）嵌入第一幅图像,在偶数行（列）嵌入第二幅图像,从而实现多幅图像在一幅公开图像中的隐藏。给出了两幅图像嵌入一幅图像的实验,并对隐藏性能作了分析与比较。该算法原理简单有效,编程容易,信息的嵌入与提取速度快,并且这种多幅图像进行信息隐藏的方法可以嵌套于目前的大多数算法,有很强的推广性。     

An efficient color and texture based iris image retrieval technique

This paper proposes a hierarchical approach to retrieve an iris image efficiently from for a large iris database. This approach is a combination of both iris color and texture. Iris color is used for indexing and texture is used for retrieval of iris images from the indexed iris database. An index which is determined from the iris color is used to filter out the images that are not similar to the query image in color. Further, iris texture features of those filtered images, are used to determine the images which are similar to the query image. The iris color information helps to design an efficient indexing scheme based on color indices. The color indices are computed by averaging the intensity values of all red and blue color pixels. Kd-tree is used for real-time indexing based on color indices. The iris texture features are obtained through Speeded Up Robust Features (SURF) algorithm. These features are used to get the query’s corresponding image at the top best match. The performance of the proposed indexing scheme is compared with two well known iris indexing schemes ( [Mehrotra et al., 2010] and [Puhan and Sudha, 2008]) on UPOL (Dobeš, Machala, Tichavský, & Posp?´šil, 2004) and UBIRIS (Proencca & Alexandre, 2005) iris databases. It is observed that combination of iris color and texture improves the performance of iris recognition system.     

基于SIFT特征的眼底图像自动拼接

针对眼底图像对比度低、不同视场的图像间存在几何畸变等特点,提出一种基于SIFT特征的眼底图像自动拼接算法。该算法分别提取待拼接眼底图像的SIFT特征点,并用向量进行描述,确定两幅图像特征点的匹配关系,使用MLESAC算法去除误匹配点对,提出对特征点对提纯的距离-斜率相似测度方法,计算匹配点之间的透视变换矩阵,最后进行图像配准和拼接。对实际眼底照相机获取的多幅图像拼接结果表明,该算法具有很好的鲁棒性和稳健性,可以实现眼底图像的高精度自动拼接。     

基于对比度视觉模型的多聚焦融合图像的精确重构

采用基于对比度视觉模型的图像融合最优分块搜索算法 ,对同一场景两幅严格配准的多聚焦图像的清晰恢复进行了深入研究 .结果表明 :应用二十多幅各种不同图像实例 ,该方法的评价指标 RMSE(均方根误差 )不仅远小于目前国内外文献中研究的数值 ,甚至在一些情况下达到 0 ,实现了多聚焦图像对原始图像的精确重构 .该算法亦具有简捷性和可扩展性 ,对于非严格配准的图像也能得到很大程度地再现     

基于残差网络编解码的磁共振图像修复算法

目前很多基于受损图像修复的算法应用在磁共振图像上效果不佳,严重降低该类图像的医学应用价值。为获得细节更加丰富的磁共振图像,提高其应用价值,提出一种基于深度残差网络编码-反卷积网络解码框架的算法。使用双三次插值算法对图像进行处理,将像素点取值归一化,用修改的深层残差网络提取图像特征,用反卷积恢复图像细节,完成图像重建工作。实验结果表明,该算法在磁共振图像的修复效果上相比其它算法表现更优。     

A secure Boolean-based multi-secret image sharing scheme

An (n, n) multi-secret image sharing scheme shares n secret images among n shared images. In this type of schemes, n shared images can be used to recover all n secret images, but the loss of any shared image prevents the recovery of any secret image. Among existing image sharing techniques, Boolean-based secret schemes have good performance because they only require XOR calculation. This study presents a secure Boolean-based secret image sharing scheme that uses a random image generating function to generate a random image from secret images or shared images. The proposed function efficiently increases the sharing capacity on free of sharing the random image. The use of a bit shift subfunction in the random image generating function produces a random image to meet the random requirement. Experimental results show that the proposed scheme requires minimal CPU computation time to share or recover secret images. The time required to share n secret images is nearly the time as that required to recover n secret images. The bit shift subfunction takes more computation load than the XOR subfunction needs.     

基于块效应网格偏移的重获取JPEG图像篡改检测

重获取图像是原始或篡改后的图像经过中间媒介的映射后再次拍摄获取的图像,一张高质量的重获取伪造图像很难通过人眼判别真伪。针对JPEG格式的重获取图像篡改操作,提出了一种重压缩块效应网格偏移的检测方法。重获取图像由于再获取过程会引入与原图不相关的背景信息,该图像进行多次压缩会产生块效应网格偏移,即重压缩产生的块效应网格会与原始的网格错匹配,利用图像的平均信息损失量进行块效应网格是否发生偏移来检测图像的原始性。实验表明,该方法比已有的重获取图像检测方法准确率更高,且平均检测时间更短。     

一种新的指纹脊线提取方法

本文提出一种新的指纹脊线提取方法。首先利用灰度形态学，结合条件模板进行滤波，然后用Ｏｔｓｕ方法分割得到二值图像，再将原图反相，进行上述同样处理，最后融合两次分割的结果，提取指纹脊线。实验结果证明本法具有抗噪性、旋转不变性。     

Geometry and construction of straight lines in log-polar images

This paper investigates, how straight lines are mapped to the non-Euclidean log-polar image plane and how their properties in log-polar coordinates can be used to perform two fundamental measurement operations: the construction of straight lines of given orientation angle and the measurement of distances along these lines. It is shown, how the two operations can be efficiently implemented for discrete log-polar images. The usefulness of the developed theory is demonstrated by applying it to different image processing tasks. As a first example, it is used for line and circle detection in log-polar sampled images. As a second example, it is used to construct epipolar lines and perform disparity estimation in log-polar images. Experiments with both synthetic and real images are presented, and the feature detection results are quantitatively evaluated.     

基于图像块能量梯度的多聚焦图像融合

针对多聚焦图像,提出一种基于图像分块的融合方法。将源图像分为大小相同数量相等的子块,采用能量梯度算子作为对焦评价函数,计算各个图像子块能量梯度匹配度,设置匹配度阈值分离出源图像中的清晰区域。源图像中的清晰区域直接作为融合图像相应的区域,其它区域的处理中,构造与相应子块能量梯度大小相关的图像序列,以及像素点到各个子块中心距离相关的融合函数,然后用融合函数对图像序列融合。实验结果表明该方法有效性和合理性。