找回密码
 注册
关于网站域名变更的通知
查看: 559|回复: 4
打印 上一主题 下一主题

基于matlab GUI不变矩验证码识别

[复制链接]

该用户从未签到

跳转到指定楼层
1#
发表于 2021-5-24 14:41 | 只看该作者 |只看大图 回帖奖励 |倒序浏览 |阅读模式

EDA365欢迎您登录!

您需要 登录 才可以下载或查看,没有帐号?注册

x
& S" y; m4 O0 J( z
一、简介
% k4 b8 _6 y5 D5 ?" G3 l1 背景意义
& {  R& n9 m3 l) P; ~验证码具有多变性特点,而当前的识别系统往往具有很强的针对性, 只能够识别某种类型的验证码。随着网络安全技术及验证码生成技术的不断发展,已经出现了更加复杂的验证码生成方法,如基于动态图像的验证码系统等。运用计算机视觉、模式识别等相关理论对多种不同类型的验证码进行识别研究。矩特征主要表征了图像区域的几何特征,又称为几何矩, 由于其具有旋转、平移、尺度等特性的不变特征,所以又称其为不变矩。
& Z" u2 a0 `: U0 j* D; ]7 K+ M. u) c5 r
2 理论基础7 J; b$ A- l, L9 ?( H
本案例提出了以处理颜色加噪的数字字符为理论研究素材, 将模板匹配作为基本框架的验证码识别系统。本系统的优点在于能够对特定类型的数字验证码进行精确识别,实验中识别准确率可达到95%以上,并提供动态更新样本库的功能,可根据实际运行的环境提高验证码的识别率。
" G& H5 f! y" k. {( K) K本案例选择了经典的数字验证码识别作为识别的对象。验证码的识别涉及图像预处理、分割、特征提取、识别等相关技术,本案例通过对彩色验证码图像进行灰度化、二值化、去噪和归一化等步骤来进行预处理,通过建立模板库的动态更新机制来提高系统的兼容性,进一步提升验证码识别的效率和准确性。' z$ H) Q; n% `. t- F" {4 F
流程图如下:5 O! q0 _  s9 x6 j

; x+ J* R. A# l5 S% Y
4 c# z) c/ ?2 L# i) D, H3 算法流程
% s7 f3 M* E; `  k% {8 i为了进行验证码识别, 建立模板库建立动态模板库,加入自动更新的功能提高对数字验证码的识别率。数字验证码待识别对象即数字0 ~ 9,调用mkdir 函数来自动建立模板数据库文件夹。
$ c- z1 O" m: t3 g7 O" t9 r. Y由于图中有类似于椒盐噪声的带有颜色的噪声,数字验证码中的数字个数保持常量并且分布均匀、易于分割。因此,为了进行下一步的数字分割操作,需要先进行验证码图像去噪步骤。本案例采用颜色空间转换到hsv 的方式,用阈值过滤的手段进行去噪。进行图像去噪之后,可以发现验证码图像中的数字呈现分布均匀的状态,并且未明显受到倾斜、形变等因素的影响。借用数字图像二值化、积分投影的方式可对数字进行定位。在实际处理过程中,为了保证分割有效,加入了区域面积滤波操作,将剩余的噪声点进行滤除。为了进行下一步的识别操作,需要将分割结果进行归一化处理, 整合成固定维数的数字集合。数字图像分割完成后,通过提取数字图像的不变矩特征信息,与模板库中的数字图像
& W0 D% e5 r! d9 e; r# l进行对比,得到识别结果。6 F# t' C* h  c0 o

( }6 [" J* e+ m; t, f" O二、源代码
( V  ~4 L2 ]7 E6 c1 t
  • function varargout = daunxujian1(varargin)
  • % DAUNXUJIAN1 MATLAB code for daunxujian1.fig
  • %      DAUNXUJIAN1, by itself, creates a new DAUNXUJIAN1 or raises the existing
  • %      singleton*.
  • %
  • %      H = DAUNXUJIAN1 returns the handle to a new DAUNXUJIAN1 or the handle to
  • %      the existing singleton*.
  • %
  • %      DAUNXUJIAN1('CALLBACK',hObject,eventData,handles,...) calls the local
  • %      function named CALLBACK in DAUNXUJIAN1.M with the given input arguments.
  • %
  • %      DAUNXUJIAN1('Property','Value',...) creates a new DAUNXUJIAN1 or raises the
  • %      existing singleton*.  Starting from the left, property value pairs are
  • %      applied to the GUI before daunxujian1_OpeningFcn gets called.  An
  • %      unrecognized property name or invalid value makes property application
  • %      stop.  All inputs are passed to daunxujian1_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 daunxujian1
  • % Last Modified by GUIDE v2.5 23-Oct-2020 21:52:34
  • % Begin initialization code - DO NOT EDIT
  • gui_Singleton = 1;
  • gui_State = struct('gui_Name',       mfilename, ...
  •                    'gui_Singleton',  gui_Singleton, ...
  •                    'gui_OpeningFcn', @daunxujian1_OpeningFcn, ...
  •                    'gui_OutputFcn',  @daunxujian1_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 daunxujian1 is made visible.
  • function daunxujian1_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 daunxujian1 (see VARARGIN)
  • % Choose default command line output for daunxujian1
  • handles.output = hObject;
  • handles.Result = [];
  • handles.File = [];
  • % Update handles structure
  • guidata(hObject, handles);
  • clc; warning off all;
  • InitAxes(handles);
  • % UIWAIT makes daunxujian1 wait for user response (see UIRESUME)
  • % uiwait(handles.figure1);
  • % --- Outputs from this function are returned to the command line.
  • function varargout = daunxujian1_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)
  • [filename, pathname] = uigetfile({'*.jpg;*.tif;*.png;*.gif','All Image Files';...
  •     '*.*','All Files' },'载入图像',...
  •     fullfile(pwd, 'images'));
  • I = imread(fullfile(pathname, filename));
  • Result = Process_Main(I);
  • handles.File = fullfile(pathname, filename);
  • handles.Result = Result;
  • guidata(hObject, handles);
  • InitAxes(handles)
  • axes(handles.axes1); imshow(handles.Result.Image); title('原图像');
  • % --- Executes on button press in pushbutton2.
  • function pushbutton2_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton2 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • if ~isempty(handles.Result)
  •     axes(handles.axes1); imshow(handles.Result.Image); title('原图像');
  •     axes(handles.axes2); imshow(handles.Result.Medfilt); title('中值滤波图像');
  • end
  • % --- Executes on button press in pushbutton3.
  • function pushbutton3_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton3 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • if ~isempty(handles.Result)
  •     axes(handles.axes1); imshow(handles.Result.Image); title('原图像');
  •     axes(handles.axes2); imshow(handles.Result.Medfilt); title('中值滤波图像');
  •     axes(handles.axes3); imshow(handles.Result.Normalize); title('归一化图像');
  • end
  • % --- Executes on button press in pushbutton4.
  • function pushbutton4_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton4 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • if ~isempty(handles.Result)
  •     axes(handles.axes1); imshow(handles.Result.Image); title('原图像');
  •     axes(handles.axes2); imshow(handles.Result.Medfilt); title('中值滤波图像');
  •     axes(handles.axes3); imshow(handles.Result.Normalize); title('归一化图像');
  •     axes(handles.axes4); imshow(handles.Result.Bww); title('二值化图像');
  • end
  • % --- Executes on button press in pushbutton6.
  • function pushbutton6_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton6 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • if ~isempty(handles.Result)
  •     axes(handles.axes1); imshow(handles.Result.Image); title('原图像');
  •     axes(handles.axes2); imshow(handles.Result.Medfilt); title('中值滤波图像');
  •     axes(handles.axes3); imshow(handles.Result.Normalize); title('归一化图像');
  •     axes(handles.axes4); imshow(handles.Result.Bww); title('二值化图像');
  •     axes(handles.axes6); imshow(handles.Result.Thin); title('细化处理');
  •     axes(handles.axes5); imshow(handles.Result.Bw); title('特征提取');
  •     hold on;
  •     h = [];
  •     for i = 1 : length(handles.Result.hs) %绘制水平线
  •         h = [h plot([1 handles.Result.sz(2)], [handles.Result.hs(i) handles.Result.hs(i)], 'r-')];
  •     end
  •     for i = 1 : length(handles.Result.vs)%绘制竖直线
  •         h = [h plot([handles.Result.vs(i) handles.Result.vs(i)], [1 handles.Result.sz(1)], 'g-')];
  •     end
  •     h = [h plot(handles.Result.x1, handles.Result.y1, 'y-')];%绘制左对角线
  •     h = [h plot(handles.Result.x2, handles.Result.y2, 'm-')];%绘制右对角线
  • end
  • % --- Executes on button press in pushbutton7.
  • function pushbutton7_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton7 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • [filename, pathname] = uiputfile({'*.jpg;*.tif;*.png;*.gif','All Image Files';...
  •     '*.*','All Files' },'Save Image',...
  •     fullfile(pwd, 'Result/result.png'));
  • if ~isequal(filename, 0)
  •     imwrite(handles.Result.label, fullfile(pathname, filename));
  •     msgbox('保存图像成功!', '信息提示框');
  • end
  • % --- Executes on button press in pushbutton9.
  • function pushbutton9_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton9 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • choice = questdlg('确定退出?', ...
  •     '退出', ...
  •     '是','否','否');
  • switch choice
  •     case '是'
  •         close;
  •     otherwise
  •         return;
  • end
  • function edit1_Callback(hObject, eventdata, handles)
  • % hObject    handle to edit1 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • % Hints: get(hObject,'String') returns contents of edit1 as text
  • %        str2double(get(hObject,'String')) returns contents of edit1 as a double
  • % --- Executes during object creation, after setting all properties.
  • function edit1_CreateFcn(hObject, eventdata, handles)
  • % hObject    handle to edit1 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    empty - handles not created until after all CreateFcns called
  • % Hint: edit controls usually have a white background on Windows.
  • %       See ISPC and COMPUTER.
  • if ispc && isequal(get(hObject,'BackgroundColor'), get(0,'defaultUicontrolBackgroundColor'))
  •     set(hObject,'BackgroundColor','white');
  • end
  • % --- Executes on button press in pushbutton8.
  • function pushbutton8_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton8 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • set(handles.edit1,'string',handles.Result.label);
  • % --- Executes on button press in pushbutton10.
  • function pushbutton10_Callback(hObject, eventdata, handles)
  • % hObject    handle to pushbutton10 (see GCBO)
  • % eventdata  reserved - to be defined in a future version of MATLAB
  • % handles    structure with handles and user data (see GUIDATA)
  • if ~isempty(handles.Result)
  •     axes(handles.axes1); imshow(handles.Result.Image); title('原图像');
  •     axes(handles.axes2); imshow(handles.Result.Medfilt); title('中值滤波图像');
  •     axes(handles.axes3); imshow(handles.Result.Normalize); title('归一化图像');
  •     axes(handles.axes4); imshow(handles.Result.Bww); title('二值化图像');
  •     axes(handles.axes6); imshow(handles.Result.Thin); title('细化处理');
  • end* z: N5 t' F+ d# ^
                              A' e4 j/ w5 E' h- k1 S

* _1 o: Q/ O. {( A- F& c三、运行结果/ d" A0 D! K& _3 A- a6 c1 K! j# e

9 x( q9 ~5 k1 p9 i- L
$ ?8 R1 ]0 u) k
# O8 \" ]/ Z( x9 W7 j. a2 w( ]) c

该用户从未签到

2#
发表于 2021-5-24 16:00 | 只看该作者
基于matlab GUI不变矩验证码识别
  • TA的每日心情

    2019-11-29 15:37
  • 签到天数: 1 天

    [LV.1]初来乍到

    3#
    发表于 2021-5-24 16:11 | 只看该作者
    基于matlab GUI不变矩验证码识别

    该用户从未签到

    4#
    发表于 2021-5-24 16:12 | 只看该作者
    基于matlab GUI不变矩验证码识别

    该用户从未签到

    5#
    发表于 2021-5-31 18:06 | 只看该作者
    矩特征主要表征了图像区域的几何特征,又称为几何矩, 由于其具有旋转、平移、尺度等特性的不变特征,所以又称其为不变矩
    * J; V% q' \) Y
    您需要登录后才可以回帖 登录 | 注册

    本版积分规则

    关闭

    推荐内容上一条 /1 下一条

    EDA365公众号

    关于我们|手机版|EDA365电子论坛网 ( 粤ICP备18020198号-1 )

    GMT+8, 2025-6-18 21:28 , Processed in 0.078125 second(s), 26 queries , Gzip On.

    深圳市墨知创新科技有限公司

    地址:深圳市南山区科技生态园2栋A座805 电话:19926409050

    快速回复 返回顶部 返回列表