【手写数字识别】SVM手写数字识别【含GUI Matlab源码 676期】

最新推荐文章于 2024-07-22 14:53:15 发布

Matlab武动乾坤

最新推荐文章于 2024-07-22 14:53:15 发布

阅读量865

点赞数 15

分类专栏： Matlab图像处理（进阶版）文章标签： matlab

本文链接：https://blog.csdn.net/KeepingMatlab/article/details/135836897

版权

Matlab图像处理（进阶版）专栏收录该内容

842 篇文章 18 订阅

订阅专栏

✅博主简介：热爱科研的Matlab仿真开发者，修心和技术同步精进，Matlab项目合作可私信。
🍎个人主页：海神之光
🏆代码获取方式：
海神之光Matlab王者学习之路—代码获取方式
⛳️座右铭：行百里者，半于九十。

⛄一、 SVM简介

支持向量机(Support Vector Machine)是Cortes和Vapnik于1995年首先提出的，它在解决小样本、非线性及高维模式识别中表现出许多特有的优势，并能够推广应用到函数拟合等其他机器学习问题中。
1 数学部分
1.1 二维空间
在这里插入图片描述

2 算法部分

⛄二、部分源代码

function varargout = DigitClassifyUI(varargin)
%

% DIGITCLASSIFYUI MATLAB code for DigitClassifyUI.fig
% DIGITCLASSIFYUI, by itself, creates a new DIGITCLASSIFYUI or raises the existing
% singleton*.
%
% H = DIGITCLASSIFYUI returns the handle to a new DIGITCLASSIFYUI or the handle to
% the existing singleton*.
%
% DIGITCLASSIFYUI(‘CALLBACK’,hObject,eventData,handles,…) calls the local
% function named CALLBACK in DIGITCLASSIFYUI.M with the given input arguments.
%
% DIGITCLASSIFYUI(‘Property’,‘Value’,…) creates a new DIGITCLASSIFYUI or raises the
% existing singleton*. Starting from the left, property value pairs are
% applied to the GUI before DigitClassifyUI_OpeningFcn gets called. An
% unrecognized property name or invalid value makes property application
% stop. All inputs are passed to DigitClassifyUI_OpeningFcn via varargin.
%
% *See GUI Options on GUIDE’s Tools menu. Choose “GUI allows only one
% instance to run (singleton)”.
%
% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help DigitClassifyUI

% Last Modified by GUIDE v2.5 10-Feb-2021 18:44:08

% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct(‘gui_Name’, mfilename, …
‘gui_Singleton’, gui_Singleton, …
‘gui_OpeningFcn’, @DigitClassifyUI_OpeningFcn, …
‘gui_OutputFcn’, @DigitClassifyUI_OutputFcn, …
‘gui_LayoutFcn’, [] , …
‘gui_Callback’, []);
if nargin && ischar(varargin{1})
gui_State.gui_Callback = str2func(varargin{1});
end

if nargout
[varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT

% — Executes just before DigitClassifyUI is made visible.
function DigitClassifyUI_OpeningFcn(hObject, eventdata, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% varargin command line arguments to DigitClassifyUI (see VARARGIN)

% Choose default command line output for DigitClassifyUI
handles.output = hObject;

% Update handles structure
guidata(hObject, handles);

% UIWAIT makes DigitClassifyUI wait for user response (see UIRESUME)
% uiwait(handles.figure1);
global FigHandle AxesHandle RectHandle;
FigHandle = handles.output;
AxesHandle = handles.axes_write;
MouseDraw();
axis(handles.axes_write,[1 400 1 400]); % 设定图轴范围
RectHandle = rectangle(handles.axes_write,‘Position’,[80,66,240,268],‘LineStyle’,‘–’,‘EdgeColor’,‘#a9a9a9’);

% — Outputs from this function are returned to the command line.
function varargout = DigitClassifyUI_OutputFcn(hObject, eventdata, handles)
% varargout cell array for returning output args (see VARARGOUT);
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure
varargout{1} = handles.output;

% — Executes on button press in pushbutton1.
function pushbutton1_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)

% — Executes on button press in pushbutton_loadImage.
function pushbutton_loadImage_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton_loadImage (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global RectHandle;
cla(handles.axes_write, ‘reset’)
set(handles.axes_write, ‘Visible’,‘off’);

set(handles.output, ‘Pointer’, ‘arrow’);
axis(handles.axes_write,[1 400 1 400]); % 设定图轴范围
RectHandle = rectangle(handles.axes_write,‘Position’,[80,66,240,268],‘LineStyle’,‘–’,‘EdgeColor’,‘#a9a9a9’);

% 弹出文件选择框，选择一张图片
[file,path] = uigetfile({‘.jpg;.jpeg;.png;.bmp;.tif’,…
'图片文件 (.jpg,.jpeg,.png,.bmp,.tif)’},‘选择一张图片’);
if isequal(file,0) % 若文件不存在
set(handles.edit_imagePath, ‘String’,‘请选择一张图片’);
else
fileName= fullfile(path, file); % 选择的图片绝对路径
set(handles.edit_imagePath, ‘String’, fileName); % 显示选择的图片路径
InputImage = imread(fileName);
image(handles.axes_raw, InputImage);
set(handles.axes_raw, ‘Visible’,‘off’);

set(gcf, 'Pointer', 'arrow');
set(gcf, 'WindowButtonMotionFcn', '')
set(gcf, 'WindowButtonUpFcn', '')


% 开始执行预处理
if numel(size(InputImage))==3
    InputImage = rgb2gray(InputImage);   % 灰度化图片
    axes(handles.axes_gray);
    imshow(InputImage);
else
    axes(handles.axes_gray);
    imshow(InputImage);
end
% 二值化
InputImage = imbinarize(InputImage);
axes(handles.axes_binary);
imshow(InputImage);

% 特征提取
InputImage = imresize(InputImage, [28, 28]);
cellSize = [4 4];
[~, vis4x4] = extractHOGFeatures(InputImage,'CellSize',[4 4]);
axes(handles.axes_features);
plot(vis4x4);

load('trainedSvmModel.mat','classifier');
features(1, :) = extractHOGFeatures(InputImage,'CellSize',cellSize);
predictedLabel = predict(classifier, features);
str = string(predictedLabel);
set(handles.text_result, 'String', str);

end
axes(handles.axes_write);
MouseDraw();
% set(gcf, ‘WindowButtonDownFcn’, ‘’);

% — Executes on button press in pushbutton_load.
function pushbutton_load_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton_load (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global RectHandle;
axis(handles.axes_write,[1 400 1 400]); % 设定图轴范围
set(handles.edit_imagePath, ‘String’,‘请选择一张图片’);
delete(RectHandle);
h=getframe(handles.axes_write);
imwrite(h.cdata,‘writedImage.jpg’);

InputImage = imread(‘writedImage.jpg’);
% InputImage = cat(3, InputImage,InputImage,InputImage);
image(handles.axes_raw,InputImage);
set(handles.axes_raw, ‘Visible’,‘off’);
axis(handles.axes_write,[1 400 1 400]); % 设定图轴范围
RectHandle = rectangle(handles.axes_write,‘Position’,[80,66,240,268],‘LineStyle’,‘–’,‘EdgeColor’,‘#a9a9a9’);
global FigHandle
set(FigHandle, ‘Pointer’, ‘arrow’);
set(FigHandle, ‘WindowButtonMotionFcn’, ‘’)
set(FigHandle, ‘WindowButtonUpFcn’, ‘’)
set(FigHandle, ‘WindowButtonDownFcn’, ‘’);

% 开始执行预处理
if numel(size(InputImage))==3
InputImage = rgb2gray(InputImage); % 灰度化图片
axes(handles.axes_gray);
imshow(InputImage);
else
axes(handles.axes_gray);
imshow(InputImage);
end
% 二值化
InputImage = imbinarize(InputImage);
axes(handles.axes_binary);
imshow(InputImage);

% 特征提取
InputImage = imresize(InputImage, [28, 28]);
cellSize = [4 4];
[~, vis4x4] = extractHOGFeatures(InputImage,‘CellSize’,[4 4]);
axes(handles.axes_features);
plot(vis4x4);

load(‘trainedSvmModel.mat’,‘classifier’);
features(1, 😃 = extractHOGFeatures(InputImage,‘CellSize’,cellSize);
predictedLabel = predict(classifier, features);
str = string(predictedLabel);
set(handles.text_result, ‘String’, str);
MouseDraw();

% — Executes on button press in pushbutton_clear.
function pushbutton_clear_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton_clear (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global RectHandle;
global FigHandle
set(FigHandle, ‘Pointer’, ‘arrow’);
set(FigHandle, ‘WindowButtonMotionFcn’, ‘’)
set(FigHandle, ‘WindowButtonUpFcn’, ‘’)
set(FigHandle, ‘WindowButtonDownFcn’, ‘’);
set(handles.edit_imagePath, ‘String’,‘请选择一张图片’);
set(handles.text_result, ‘String’, ‘None’);
cla(handles.axes_write, ‘reset’)
set(handles.axes_write, ‘Visible’,‘off’);
cla(handles.axes_raw, ‘reset’)
set(handles.axes_raw, ‘Visible’,‘off’);
cla(handles.axes_gray, ‘reset’)
set(handles.axes_gray, ‘Visible’,‘off’);
cla(handles.axes_binary, ‘reset’)
set(handles.axes_binary, ‘Visible’,‘off’);
cla(handles.axes_features, ‘reset’)
set(handles.axes_features, ‘Visible’,‘off’);
set(handles.output, ‘Pointer’, ‘arrow’);

axis(handles.axes_write,[1 400 1 400]); % 设定图轴范围
RectHandle = rectangle(handles.axes_write,‘Position’,[80,66,240,268],‘LineStyle’,‘–’,‘EdgeColor’,‘#a9a9a9’);
MouseDraw();

⛄三、运行结果

在这里插入图片描述

⛄四、matlab版本及参考文献

1 matlab版本
2014a

2 参考文献
[1]张来君.基于SVM的手写数字识别[J].电子技术与软件工程. 2021,(23)

3 备注
简介此部分摘自互联网，仅供参考，若侵权，联系删除

🍅 仿真咨询
1 各类智能优化算法改进及应用
生产调度、经济调度、装配线调度、充电优化、车间调度、发车优化、水库调度、三维装箱、物流选址、货位优化、公交排班优化、充电桩布局优化、车间布局优化、集装箱船配载优化、水泵组合优化、解医疗资源分配优化、设施布局优化、可视域基站和无人机选址优化

2 机器学习和深度学习方面
卷积神经网络（CNN）、LSTM、支持向量机（SVM）、最小二乘支持向量机（LSSVM）、极限学习机（ELM）、核极限学习机（KELM）、BP、RBF、宽度学习、DBN、RF、RBF、DELM、XGBOOST、TCN实现风电预测、光伏预测、电池寿命预测、辐射源识别、交通流预测、负荷预测、股价预测、PM2.5浓度预测、电池健康状态预测、水体光学参数反演、NLOS信号识别、地铁停车精准预测、变压器故障诊断

3 图像处理方面
图像识别、图像分割、图像检测、图像隐藏、图像配准、图像拼接、图像融合、图像增强、图像压缩感知

4 路径规划方面
旅行商问题（TSP）、车辆路径问题（VRP、MVRP、CVRP、VRPTW等）、无人机三维路径规划、无人机协同、无人机编队、机器人路径规划、栅格地图路径规划、多式联运运输问题、车辆协同无人机路径规划、天线线性阵列分布优化、车间布局优化

5 无人机应用方面
无人机路径规划、无人机控制、无人机编队、无人机协同、无人机任务分配

6 无线传感器定位及布局方面
传感器部署优化、通信协议优化、路由优化、目标定位优化、Dv-Hop定位优化、Leach协议优化、WSN覆盖优化、组播优化、RSSI定位优化

7 信号处理方面
信号识别、信号加密、信号去噪、信号增强、雷达信号处理、信号水印嵌入提取、肌电信号、脑电信号、信号配时优化

8 电力系统方面
微电网优化、无功优化、配电网重构、储能配置

9 元胞自动机方面
交通流人群疏散病毒扩散晶体生长

10 雷达方面
卡尔曼滤波跟踪、航迹关联、航迹融合