搜索资源列表
bp神经网络的车辆分类
- c语言编写的基于BP神经网络的对图像车辆分类，其中图像特征提取是用图像不变矩，给出了图像不变矩的样本数据和验证数据。-based BP neural network image of the vehicle classification, Feature Extraction which is the same image moments, the image is unchanged Moments sample data and test data.
HUCentralMoment.rar
- HU不变矩程序代码很多，但是没找到一个完整准确的代码。本人对其中的某些代码修正后，和matlab计算结果进行比较，结果是一致的。本程序没有利用Opencv计算Hu矩的函数，好像opencv计算的M03和M30应该对调，否则，和matlab计算不一样！对旋转、缩放的图像进行测试，HU矩也是一样的，不信可以利用提供的图片对比一下。由于HU矩比较小，程序对HU矩取对数便于查看比较。总之，程序绝对安全可靠，可直接调用。,HU moment invariants code a lot, but could
JAVA
- 基于JAVA实现的图像特征提取源代码 图像特征提取的源代码，使用sobel算子提取图像边缘，使用hu矩提取图像形状特征，使用颜色中心矩提取图像颜色特征，请使用eclipes导入该工程并运行test文件（可将test文件中去掉一些注释部分运行更多功能）。-JAVA based on the realization of the image feature extraction image feature extraction source code source code, use the sob
wyZerMoment
- 计算Zernike矩，对图像进行了平移，尺度归一化-Computing Zernike moments, the image of the translation, scaling normalization
Invar_Moment
- 该代码为利用几何不变矩提取图像几何特征的代码，用matlab编写，提取7个Hu矩为特征向量。可以用于基于内容的图像检索-The code for the image using the geometric moment invariant geometric features extracted code, written with matlab to extract seven Hu moments as features. Can be used for content-based imag
invariant-moments
- 自己编写的Hu不变矩c++计算程序，可对图像进行二值化后，搜索二值化图像中的高亮目标并进行数字标注，同时查看搜索到的每个目标的七阶不变矩-The Hu invariant moments to write your own calculation program, the image can be binary, the search in the binary image digital mark targets and highlight the same time, view the se
image-retrieval-source-program
- 该源代码包含图像10个不变矩的图像检索，小波模极大值法边缘检测，结合颜色特征与不变矩的图像检索源程序-The source code includes images of invariant moments 10 image retrieval, wavelet modulus maximum edge detection method, combining color characteristics and the moment invariants image retrieval sourc
jutezheng
- 提取图像矩特征，实现程序时放在vc6.0下运行~-Extraction of image moments characteristics, implementation process on the run ~ vc6.0
ActivityRecognition
- Activity recognition program using Motion History Image s 7 Hu moments. The program compare the Mahalanobis distance of the Hu moments of the video input with the reference and find out the activities.
Normal_Central_Moments
- Set of functions to calculate the centroid, central moments and normalised moments of a binary image. Easy to understand, implemented in matlab
MomentbyRS
- fast calculation of image moments based on Fluss and Tuk s method described in "On the Calculation of Moments"
ImageCaptureANDDriver
- 通过CCD拍摄工作台图片，然后经过图像处理，提取图像矩特征，然后通过相关算法，求出工作台移动的距离-CCD image taken through the table, and then through image processing, extraction of the characteristics of image moments, and then through the relevant algorithms, to derive the distance between mobil
3D_Moment_Invariant
- Hu的七个不变矩在图像匹配检索中适用广泛。本代码仅计算图像间Hu的七个矩的D2大小，直观的了解Hu矩的应用-seven moment invariants in image retrieval in the application of broad match. Only the calculation of the code between the image of the seven Hu moments D2 size, intuitive understanding of the app
zernik_moment
- Calculation of zernike moments from binary image BW
image
- 高阶矩在颜色传输中的应用,利用matlab进行的高阶矩阵处理。-High-order moments in the application of the color transmission using matlab to handle high-level matrix.
HuMoment
- 修改后的计算Hu归一化中心距的代码，与matlab程序计算结果一致，并附带测试对比图片，通过对放大前后两张图像的Hu计算，发现结果是一样的，证明了Hu矩在图像尺寸变化时保持不变，旋转、平移情况自己做吧-The revised calculation of Hu normalized center distance of the code results are consistent with the matlab program to calculate and compare with tes
moments_used_in_image_processing
- 矩是一种在图像处理和模式识别中，广泛应用的方法。这篇文章简单介绍了矩的概念。-Moment is a kind of image processing and pattern recognition, the widely used method. This article briefly introduced the concept of moments.
image-mmoment-function
- 本书主要讨论了图像的各类矩函数（几何矩、复数矩、Legendre矩、Zernike矩、小波矩等）的定义、性质和快速算法，以及它们的不变量函数。并就它在图像处理和识别，计算机视觉以及其它方面的应用作了必要的介绍。 -This book discusses the various types of image moment function (geometric moments, complex moments, Legendre moments, Zernike moments, wavel
centralmoments
- image processing central moments also called as Hu s moments and zigzag scan program
image recognition
- 分别采用有边缘和无边缘两类图像作为样本库，使用用Hu不变矩对图像进行特征提取，并使用K近邻分类法进行分类和识别。(Two types of images with edges and no edges are used as the sample library, the images are extracted using Hu invariant moments, and the images are classified and identified by K nearest neighb