基于感知哈希的图像内容鉴别性能分析

感知哈希能有效地区分不同内容的图像,常用于检测盗版或重复的图像内容鉴别应用中.针对已有的对感知哈希的图像内容鉴别应用研究主要集中在算法设计上,缺少对其性能评价的理论方法的问题,提出从理论上评价内容鉴别性能的方法.该方法基于一类图像感知哈希算法的抗碰撞特性建立了内容鉴别的判定模型,并定义内容鉴别的性能公式,最后推导出统计学上的函数作为性能评价指标.实验结果表明,文中方法能很好地估计感知哈希在内容鉴别应用中的性能.     

Supervised polarimetric SAR classification method based on Fisher linear discriminant

A supervised polarimetric SAR land cover classification method was proposed based on the Fisher linear discriminant.The feature parameters used in this classification method could be selected flexibly according to land covers to be classified.Polarimetric and texture feature parameters extracted from co-registered multifrequency and multi-temporal polarimetric SAR data could be combined together for classification use,without consideration of the dimension difference of each feature parameter and the joint probability density function of those parameters.Experimental result with AGRSAR L/C-band full polarimetric SAR data showed that a total classification accuracy of 94.33% was achieved by combining the polarimetric with texture feature parameters extracted from L/C dual band SAR data,demonstrating the effectiveness of this method.     

基于TM影像的衡阳市城区扩展趋势研究

城镇化是我国经济发展必然产物,城市扩展是城镇化进程的一个重要指标。遥感技术具有快捷、便利、大面积同步观测等特征,已经广泛应用于对城市扩展的监测。以衡阳市为研究对象,选取该区域1989年、2006年和2010年的Landsat TM遥感影像作为数据源,利用植被、水体和建筑物指数特征和监督分类方法提取3 a （年）中衡阳市城区边界信息,最后采用GIS的空间分析技术,从扩展强度、扩展方向2个方面来讨论衡阳市城区的扩展空间特征。     

SSCDenseNet:一种空-谱卷积稠密网络的高光谱图像分类算法

基于深度学习的高光谱遥感图像地物分类是目前研究的热点.但由于其参数规模大以及结构复杂,深度网络通常需要大量训练样本和较长训练时间,如何在小规模样本下建立深度学习监督分类模型是需要解决的关键问题.本文提出了一种小规模样本下高光谱图像分类的空-谱卷积稠密网络算法,称为SSCDenseNet,其包含三种新颖的架构策略：（1）空-谱分离卷积,即采取光谱维一维卷积和空间维二维卷积的分离卷积结构构成隐层单元,并通过多个隐层单元堆叠构造深度网络;（2）隐层单元中使用批归一化,减少数据协方差漂移及加速网络训练;（3）隐层单元间构建稠密连接,缓解梯度消失问题并实现特征复用.通过Indian Pines、Pavia University与Salinas数据集进行综合测评,表明该方法优于若干最新深度学习方法,特别在小规模样本下具有优异的分类性能.     

Encrypted image retrieval in multi-key settings based on edge computing

Aiming at the fact that the existing encrypted image retrieval schemes do not consider different keys to encrypt images,a multi-key encrypted image retrieval system based on edge computing (including basic scheme and enhanced scheme) based on local sensitive hashing,secure nearest neighbor and proxy re-encryption technologies was proposed.The retrieval efficiency and accuracy were improved and the extra computational cost of query users was reduced.Security analysis shows that the basic scheme can only resist the known ciphertext attack,while the enhanced scheme can resist the known background attack.The experimental performance test based on the real-world dataset shows that the proposed schemes are feasible in practical application scenarios.     

基于双线性迭代量化的哈希图像检索方法

针对迭代量化哈希算法未考虑高维图像描述符中呈现出的自然矩阵结构,当视觉描述符由高维特征向量表示并且分配长二进制码时,投影矩阵需要昂贵的空间和时间复杂度的问题,提出一种基于双线性迭代量化的哈希图像检索方法。该方法使用紧凑的双线性投影而不是单个大型投影矩阵将高维数据映射到两个较小的投影矩阵中;然后使用迭代量化的方法最小化量化误差并生成有效的哈希码。在CIFAR-10和Caltech256两个数据集上进行实验,实现了与最先进的8种哈希方法相媲美的性能,同时具有更快的线性扫描时间和更小的内存占用量。结果表明,该方法可以减轻数据的高维性带来的影响,从而提高ITQ的性能,可广泛服务于高维数据长编码位的哈希图像检索应用。     

Supervised‐learning‐based algorithm for color image compression

A correlation exists between luminance samples and chrominance samples of a color image. It is beneficial to exploit such interchannel redundancy for color image compression. We propose an algorithm that predicts chrominance components Cb and Cr from the luminance component Y. The prediction model is trained by supervised learning with Laplacian‐regularized least squares to minimize the total prediction error. Kernel principal component analysis mapping, which reduces computational complexity, is implemented on the same point set at both the encoder and decoder to ensure that predictions are identical at both the ends without signaling extra location information. In addition, chrominance subsampling and entropy coding for model parameters are adopted to further reduce the bit rate. Finally, luminance information and model parameters are stored for image reconstruction. Experimental results show the performance superiority of the proposed algorithm over its predecessor and JPEG, and even over JPEG‐XR. The compensation version with the chrominance difference of the proposed algorithm performs close to and even better than JPEG2000 in some cases.     

Variable selection for collaborative filtering with market basket data

The market basket data in the form of a binary user–item matrix or a binary item–user matrix can be modeled as a binary classification problem, which actually tackles collaborative filtering (CF) as well as target marketing. Effective variable selection (VS) can increase the prediction accuracy as well as identify important users or items in CF as well as target marketing. Therefore, we propose two new VS approaches: a Pearson correlation‐based approach and a forward random forests regression‐based approach, comparing the performance in a variety of experimental settings. The experimental results show that the proposed VS approaches outperform the conventional approaches in the examples. Furthermore, the experimental results are more reasonable and informative than the previous experimental results because the binary misclassification error and Top‐N accuracy for the user CF, the item CF, the user modeling, and the item modeling are all considered in this paper.     

利用分块相似系数构造感知图像Hash

提出一种基于图像分块相似系数的感知稳健图像Hash.先对图像预处理,再进行重叠分块,在密钥控制下,利用高斯低通滤波器生成伪随机参考图像块,分别计算每个分块与参考图像块的相关系数得到图像特征序列.依此将相邻两个分块特征值合并以缩短Hash长度,同时对压缩后的特征序列进行重排,进一步提高图像Hash的安全性.最后对归一化特征值进行量化,并运用Huffman方法对其编码,进一步压缩Hash长度.理论分析和实验结果表明,该图像Hash方法对JPEG压缩、适度的噪声干扰、水印嵌入、图像缩放以及高斯低通滤波等常见图像处理有较好的鲁棒性,能有效区分不同图像,冲突概率低,可用于图像篡改检测.     

一种多项式光滑的半监督支持向量机分类算法

为了处理半监督支持向量机优化中的非凸非光滑问题,引入一个多项式光滑函数来逼近非凸的目标函数,给出的多项式函数在样本的高密度区逼近精度高,逼近精度低时出现在样本的低密度区.采用共轭梯度法求解模型.在人工数据和UCI数据库中的4个数据集上的实验结果显示,算法不仅能保证标号数据很少时的分类精度,而且不因标号数据的增多而明显提高分类性能,因此给出的分类器性能是稳定的.