资源简介
国外一个课程资料,包含了AAM和ASM的使用例子以及算法实现文档!还是很实用的!算法使用的图片里面都有!是AAM和ASM使用的必备教程!
代码片段和文件信息
% This script shows an example of a working basic Active Appearance Model (AAM)
% with a few hand pictures.
%
% Literature used:
% - T.F. Cootes G.J Edwards and CJ. Taylor “Active Appearance Models“
% Proc. European Conference on Computer Vision 1998
% - T.F. Cootes G.J Edwards and CJ. Taylor “Active Appearance Models“
% IEEE Transactions on Pattern Analysis and Machine Intelligence 2001
%
% Functions are written by D.Kroon University of Twente (March 2010)
%Add functions path to matlab search path
functionname=‘AAM_example.m‘; functiondir=which(functionname);
functiondir=functiondir(1:end-length(functionname));
addpath([functiondir ‘/AAM Functions‘])
addpath([functiondir ‘/Functions‘])
%% Set options
% Number of contour points interpolated between the major landmarks.
options.ni=20;
% Set normal appearance/contour limit to +- m*sqrt( eigenvalue )
options.m=3;
% Size of texture appereance image
options.texturesize=[100 100];
% If verbose is true all debug images will be shown.
options.verbose=true;
% Number of image scales
options.nscales=4;
% Number of search itterations
options.nsearch=15;
%% Load training data
% First Load the Hand Training DataSets (Contour and Image)
% The LoadDataSetNiceContour not only reads the contour points but
% also resamples them to get a nice uniform spacing between the important
% landmark contour points.
TrainingData=struct;
if(options.verbose) figure end
for i=1:10
is=num2str(i); number = ‘000‘; number(end-length(is)+1:end)=is;
filename=[‘Fotos/train‘ number ‘.mat‘];
% Load the trianing data
[TrainingData(i).xTrainingData(i).yTrainingData(i).I]=LoadDataSetNiceContour(filenameoptions.nioptions.verbose);
% Replace the grey level photo by color photo
TrainingData(i).I=im2double(imread([filename(1:end-4) ‘.jpg‘]));
end
% The Active Appearance Model is constructed for multiple image scales.
% During search first the coarse scale is used to detect the object
% followed by the finer scales (larger images). This makes the model robust
% against initial location and local minima
% The structure which will contain the AAM model for 4 image scales
Data=cell(14);
for scale=1:options.nscales
%% Shape Model %%
% Make the Shape model which finds the variations between contours
% in the training data sets. And makes a PCA model describing normal
% contours
[ShapeDataTrainingData] = AAM_MakeShapeModel(TrainingData);
% Show some eigenvector variations
if(options.verbose)
figure
for i=1:6
xtest = ShapeData.x_mean + ShapeData.Evectors(:i)*sqrt(ShapeData.Evalues(i))*3;
subplot(23i) hold on;
plot(xtest(end/2+1:end)xtest(1:end/2)‘r‘);
plot(ShapeData.x_mean(end/2+1:end)ShapeData.x_mean(1:end/2)‘b‘);
end
end
%% Appearance model %%
% Piecewise linear image transformation is used to align a
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
文件 984 2010-03-17 14:49 ASM\AAM Functions\AAM_align_data.m
文件 404 2010-03-17 14:49 ASM\AAM Functions\AAM_align_data_inverse.m
文件 1216 2010-03-19 14:25 ASM\AAM Functions\AAM_Appearance2Vector.m
文件 7841 2010-03-19 14:47 ASM\AAM Functions\AAM_ApplyModel.m
文件 1331 2010-03-17 14:57 ASM\AAM Functions\AAM_CombineShapeAppearance.m
文件 1908 2010-03-19 14:24 ASM\AAM Functions\AAM_MakeAppearanceModel.m
文件 6181 2010-03-17 15:34 ASM\AAM Functions\AAM_MakeSearchModel.m
文件 1285 2010-03-17 14:47 ASM\AAM Functions\AAM_MakeShapeModel.m
文件 155 2010-03-17 14:49 ASM\AAM Functions\AAM_NormalizeAppearance.m
文件 618 2010-03-19 14:34 ASM\AAM Functions\AAM_Vector2Appearance.m
文件 2350 2010-03-17 14:59 ASM\AAM Functions\AAM_Weights.m
文件 8099 2010-03-22 10:49 ASM\AAM_example.m
文件 668 2011-04-07 13:57 ASM\ASM Functions\ASM_align_data.m
文件 232 2010-03-17 14:50 ASM\ASM Functions\ASM_align_data_inverse.m
文件 5652 2011-04-09 17:42 ASM\ASM Functions\ASM_ApplyModel.m
文件 612 2011-04-09 15:01 ASM\ASM Functions\ASM_GetContourNormals.m
文件 1560 2011-04-07 17:20 ASM\ASM Functions\ASM_getProfileAndDerivatives.m
文件 3654 2011-04-08 08:52 ASM\ASM Functions\ASM_MakeAppearanceModel.m
文件 1079 2011-04-07 15:40 ASM\ASM Functions\ASM_MakeShapeModel.m
文件 4656 2011-04-15 22:10 ASM\ASM_example.m
文件 23898 2010-02-11 20:48 ASM\Fotos\test001.jpg
文件 21022 2010-02-10 16:38 ASM\Fotos\train001.jpg
文件 792862 2010-02-12 17:03 ASM\Fotos\train001.mat
文件 32785 2010-02-10 16:38 ASM\Fotos\train002.jpg
文件 1240485 2010-02-12 17:01 ASM\Fotos\train002.mat
文件 25816 2010-02-10 16:38 ASM\Fotos\train003.jpg
文件 935188 2010-02-12 17:03 ASM\Fotos\train003.mat
文件 31684 2010-02-10 16:38 ASM\Fotos\train004.jpg
文件 1277713 2010-02-12 17:03 ASM\Fotos\train004.mat
文件 32044 2010-02-10 16:38 ASM\Fotos\train005.jpg
............此处省略27个文件信息
- 上一篇:三星手机固件 Tar 打包工具
- 下一篇:导弹制导和控制系统的分析与设计.pdf
相关资源
- Win32ASM Tutorial Resource Kit v1.00
- Win7(64位)下使用MASM和DEBUG方法.rar
- x86-x64体系探索及编程-随书代码.rar
- Wava 6000 (内有comp86编译器,comp51编译
- Intouch modbus驱动DASMBTCP1.1
- 安卓xmpp客户端基于asmack+openfire
- nasmide(x86汇编语言从实模式到保护模
- asm算法 opencv实现
- 初学者必看!ASM如何转换为HEX文件.
- Surface Plasmons
- 汇编MASM6.15官方原版
- DOSBOX和部分工具
- Specair 3.0
- masmplus+dosbox完美运行于64位win7(无需
- NASM中文手册.pdf
- ASM 人脸特征点提取
- Gaussian Processes for Machine Learning - Rasm
- 8086汇编工作环境
- 汇编 dosbox课程上机使用
-
汇编工具(DEBUG+MASM+EDIT+li
nk+DOSBOX) - 汇编开发工具 MASM 5.0
- fasm_未来汇编器
- WIN7 64位 MASM 汇编工具包含debug,edit等
- 内含MASM 6.15完整版和DOSBOX(WIN7 64位下
- masm5.0+Dosbox
- nasm-2.13.03.tar.gz安装包
- ASME-B16.10-2017中文版阀门结构长度
- MASM For Windows 集成开发环境
- DASMBSerial_2.0
- SASM -- 调试、运行MASM、GAS、NASM、FAS
评论
共有 条评论