二值图像

一种基于二维Logistic映射的二值图像加密方案

A Binary Image Encryption Algorithm Based on Coupled Logistic Chaotic Map

对于二值图像，提出了类似于数学形态学腐蚀、膨胀的CA布尔逻辑规则；

For binary image , the CA-based erosion and dilation rules like morphology are found .

改进后的算法在二值图像线特征提取及CT图像边缘检测上获得满意效果。

This improved method achieves effective result in line feature extraction for binary image and edge detection for CT image .

基于RS码的二值图像认证及篡改定位算法

Binary Image Authentication and Tamper Localization Based on RS Codes

用Matlab的二值图像形态滤波函数处理扫描工程图

Using Morphological Filtering Function of Matlab 's Binary Images to Deal With the Background Noises in Scanning Engineering Drafting

基于DCT域的加密二值图像数字水印新算法

An Encrypted Binary Image Digital Watermarking Algorithm Based on DCT

对于多值图像，采用坐标逻辑运算把图像分解成多个二值图像后用CA并行处理。

However , multi-value image is decomposed to several binary images with coordinate logic , and then be processing with CA.

基于Arnold变换和双混沌序列的二值图像置乱算法

Binary Image Scrambling Scheme Based on Arnold Transformation and Two Chaotic Sequences

煤矸石二值图像的Roberts快速边缘检测法

A Fast Edge Detection Roberts Algorithm of Coal Gangue Binary Image

提出一种基于DWT和DCT域的有意义二值图像数字水印算法；

A novel meaning binary image digital watermarking algorithm based on DWT and DCT is proposed .

研究了JPEG压缩标准和数字水印模型，提出一种基于JPEG压缩的二值图像水印算法。

It studies JPEG model and watermarking model and proposes an algorithm of watermark in compression domain .

基于Legendre矩的多阈值二值图像重构算法

Multi-threshold Reconstruction of Binary Image Using the Legendre Orthogonal Moments

对n×n二值图像，算法的运行时间是O（n2logn）的。

The algorithm runs in O ( n 2logn ) time , where n × n is the size of the binary image .

基于Legendre正交矩的配准方法及其在二值图像配准中的应用

A New Way of Linear Registration Using the Legendre Orthogonal Moment and Application in 2 Value Image Data

然后将目标二值图像映射到灰度图像，使用共生矩阵与Gabor小波对灰度图像提取纹理特征。

After the target binary image is mapped to gray-scale image , we extracted the co-occurrence matrix and Gabor wavelet texture features from the gray-scale image .

以化学浸泡后304不锈钢腐蚀二值图像的特征值一腐蚀率及蚀孔密度作为输入因子，建立了基于BP神经网络的孔蚀速率诊断模型。

A 2-5-1 BP neural network model is developed for the prediction of pitting corrosion rate of 304 stainless steel by using the obtained data of the corrosion ratio and pits density obtained by chemical immerse experiments .

用HSV颜色模型的H和S分量，通过一种基于二值图像分割的快速聚类算法，从环境中分离出具有某种特定颜色的目标物。

Using the H and S weight of the HSV color model , separate the target from the environment with a certain color , by a fast clustering algorithm for two-value image segmentation .

首先对原始图像进行采样，并把图像分成两组，采用两种不同的调制方式，即抖动调制和基于选择块的DCT系数调制嵌入有意义的二值图像水印。

The original image is first sub-sampled , and the sub-images are separated into two groups . Then binary watermark images are embedded by utilizing two kinds of modulations , i. e.

提出了一种适合于对线状结构的条形纹线二值图像进行压缩的最优化Freeman链码压缩算法&Freeman差分链码Huffman编码。

An optimized compression algorithm for linear structure stripe image was discussed in this paper , which is Freeman differential chain code Huffman coding .

然后利用MATLAB软件对图像进行了经遗传算法改进的阈值分割算法的仿真研究，对比几种常用的经遗传算法改进的分割算法，可以不失真的把灰度图像转换成二值图像。

Then using the matlab software to the image threshold value division algorithm to conduct the simulation research , contrasts several kinds commonly used the genetic algorithm improvement division algorithm , could convert gray image into binary image without distortion .

该算法选择一幅二值图像作为要嵌入的水印，为增加水印的安全性，对二值水印图像进行二维Arnold置乱。

A binary image is selected as the watermark . In order to increase the security of the watermark , we do two-dimensional Arnold scrambling to the binary image .

利用Gold码具有较多独立码的特性，以多位二进制信息为单位对置乱后的二值图像水印进行扩频调制，然后将调制信号自适应地加入到载体图像离散余弦变换域的低频分量系数中。

By exploiting the characteristics that Gold codes have more independent codes , the binary image watermark was modulated with multibit binary information regarded as an unit , and then was adaptively embedded into low frequency components of the scrambling image in discrete cosine transform domain .

提出了表示二值图像的模式四叉树（PQT）数据结构。

A pattern quadtree ( PQT ) data structure for representing binary images is presented .

对二值图像进行分块，利用STC编码，在载体块序列中选择一条信息嵌入的最佳修改路径，实现信息的嵌入。

The binary image is divided into blocks , and the STC ( Syndrome-trellis Codes ) encoding is used to choose the optimal path in the sequence of cover blocks for hiding message .

对于256级的灰度图像，可先用PCNN将原始的256级灰度图像分割为二值图像，接着再用该算法进行边缘检测。

For256-level image , first use PCNN to segment the original image into the binary image , and then use this approach to detect the edges .

积分投影&高斯曲线法将人脸二值图像分别在X、Y轴积分投影，根据投影曲线分别计算相应的高斯曲线，通过求解高斯方程快速得到较为准确的人脸区域。

In the approach of integral projection & Gaussian curves , two curves are obtained by integral projecting the binary-image to X and Y axes respectively , from which Gaussian curves are calculated and then , an accurate face region is found rapidly through the solution of Gaussian equation .

水印信号为二值图像，用不同相位的正弦信号将水印调制后嵌入到数字图像DWT变换系数中；

The watermark used is a binary image . In watermark embedding , the sine signals with different phase are used to modulate watermark bits and embedded in the host image wavelet coefficients that act as signal carrier .

实验中以经过旋转的二值图像直接作为BP网络的输入，略去了对图像进行特征提取选择的步骤，同时也是对BP网络能确保畸变不变性模式识别理论的验证。

In our experiments , rotated binary images are directly inputted into BP network . This method omits extracting and selecting original images ' characters . At the same time , it 's also the validation of the theory that BP neural network can insure pattern recognition 's distortion invariability .

原始二值图像水印经过置乱加密，并用均值为零、相互正交的两个伪随机序列扩频后，嵌入到绿色分量经两层DWT变换后的低频子带系数中。

The original binary watermark image was firstly encrypted through scrambling technique , and then spread with two orthogonal pseudo-random sequences whose means were equal to zero , finally embedded into the DWT low frequency sub-band of green components .

尤其是对带单一噪声的二值图像，得到了较为成功的应用，但MBAM对含有随机噪声的二值图像却无能为力。

MBAM circumvents these disadvantages and obtains the success in processing binary image with pure noise but not gray-scale images .