C# 人脸识别库 0.1

长春吉大小天鹅吕璇璞 發表於 2020-6-24 10:52:00

<h1>.NET 人脸识别库 ViewFaceCore</h1>
这是基于 SeetaFace6 人脸识别开发的 .NET 平台下的人脸识别库 这是一个使用超简单的人脸识别库 这是一个基于 .NET Standard 2.0 开发的库 这个库已经发布到 NuGet ，你可以一键集成到你的项目 此项目可以免费商业使用
<h2>⭐、开源</h2>
开源协议：Apache-2.0 GitHub地址： ViewFaceCore 十分感谢您的小星星
<h2>一、示例</h2>
示例项目地址：WinForm 摄像头人脸检测 示例项目效果：
<img src="https://img2020.cnblogs.com/blog/1188429/202006/1188429-20200624091353655-1553363960.png">
 
<h2>二、使用</h2>
一分钟在你的项目里集成人脸识别
1. 创建你的 .NET 应用
.NET Standard >= 2.0 .NET Core >= 2.0 .NET Framework >= 4.6.1^2
 2. 使用 Nuget 安装 ViewFaceCore
<ul>
<li>Author : View</li>
<li>Version >= 0.1.1</li>

</ul>
此 Nuget 包会自动添加依赖的 C++ 库，以及最精简的识别模型。 如果需要其它场景的识别模型，请下载 SeetaFace6 模型文件。
3. 在项目中编写你的代码
<ul>
<li>按照说明自己编写</li>
<li>或者参考以下代码</li>

</ul>
简单的调用示例
<div class="cnblogs_code"><img id="code_img_closed_1e32d281-1a0a-40a7-b9f8-d8a5e65b470a" class="code_img_closed lazyload" data-src="http://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif"><img id="code_img_opened_1e32d281-1a0a-40a7-b9f8-d8a5e65b470a" class="code_img_opened lazyload" style="display: none" data-src="http://images.cnblogs.com/OutliningIndicators/ExpandedBlockStart.gif">
<div id="cnblogs_code_open_1e32d281-1a0a-40a7-b9f8-d8a5e65b470a" class="cnblogs_code_hide">
<pre> 1 static void Main()
 2 {
 3 ViewFace viewFace = new ViewFace((str) => { Debug.WriteLine(str); }); // 初始化人脸识别类，并设置日志回调函数
 4 viewFace.DetectorSetting = new DetectorSetting() { FaceSize = 20, MaxWidth = 2000, MaxHeight = 2000, Threshold = 0.5 };
 5
 6 // 系统默认使用的轻量级识别模型。如果对精度有要求，请切换到 Normal 模式；并下载需要模型文件放入生成目录的 model 文件夹中
 7 viewFace.FaceType = FaceType.Normal;
 8 // 系统默认使用5个人脸关键点。//不建议改动，除非是使用口罩模型。
 9 viewFace.MarkType = MarkType.Light;
10
11 #region 识别老照片
12 float[] oldEigenValues;
13 Bitmap oldImg = (Bitmap)Image.FromFile(@"C:\Users\yangw\OneDrive\图片\Camera Roll\IMG_20181103_142707.jpg"/*老图片路径*/); // 从文件中加载照片 // 或者视频帧等
14 var oldFaces = viewFace.FaceDetector(oldImg); // 检测图片中包含的人脸信息。(置信度、位置、大小)
15 if (oldFaces.Length > 0) //识别到人脸
16 {
17 { // 打印人脸信息
18 Console.WriteLine($"识别到的人脸数量：{oldFaces.Length} 。人脸信息：\n");
19 Console.WriteLine($"序号\t人脸置信度\t位置X\t位置Y\t宽度\t高度");
20 for (int i = 0; i < oldFaces.Length; i++)
21 {
22 Console.WriteLine($"{i + 1}\t{oldFaces.Score}\t{oldFaces.Location.X}\t{oldFaces.Location.Y}\t{oldFaces.Location.Width}\t{oldFaces.Location.Height}");
23 }
24 Console.WriteLine();
25 }
26 var oldPoints = viewFace.FaceMark(oldImg, oldFaces[0]); // 获取第一个人脸的识别关键点。(人脸识别的关键点数据)
27 oldEigenValues = viewFace.Extract(oldImg, oldPoints); // 获取指定的关键点的特征值。
28 }
29 else { oldEigenValues = new float[0]; /*未识别到人脸*/ }
30 #endregion
31
32 #region 识别新照片
33 float[] newEigenValues;
34 Bitmap newImg = (Bitmap)Image.FromFile(@"C:\Users\yangw\OneDrive\图片\Camera Roll\IMG_20181129_224339.jpg"/*新图片路径*/); // 从文件中加载照片 // 或者视频帧等
35 var newFaces = viewFace.FaceDetector(newImg); // 检测图片中包含的人脸信息。(置信度、位置、大小)
36 if (newFaces.Length > 0) //识别到人脸
37 {
38 { // 打印人脸信息
39 Console.WriteLine($"识别到的人脸数量：{newFaces.Length} 。人脸信息：\n");
40 Console.WriteLine($"序号\t人脸置信度\t位置X\t位置Y\t宽度\t高度");
41 for (int i = 0; i < newFaces.Length; i++)
42 {
43 Console.WriteLine($"{i + 1}\t{newFaces.Score}\t{newFaces.Location.X}\t{newFaces.Location.Y}\t{newFaces.Location.Width}\t{newFaces.Location.Height}");
44 }
45 Console.WriteLine();
46 }
47 var newPoints = viewFace.FaceMark(newImg, newFaces[0]); // 获取第一个人脸的识别关键点。(人脸识别的关键点数据)
48 newEigenValues = viewFace.Extract(newImg, newPoints); // 获取指定的关键点的特征值。
49 }
50 else { newEigenValues = new float[0]; /*未识别到人脸*/ }
51 #endregion
52
53 try
54 {
55 float similarity = viewFace.Similarity(oldEigenValues, newEigenValues); // 对比两张照片上的数据，确认是否是同一个人。
56 Console.WriteLine($"阈值 = {Face.Threshold}\t相似度 = {similarity}");
57 Console.WriteLine($"是否是同一个人：{viewFace.IsSelf(similarity)}");
58 }
59 catch (Exception e)
60 { Console.WriteLine(e); }
61
62 Console.ReadKey();
63 }</pre>
</div>
ViewFaceCore 使用示例</div>
 
<h2>三、说明</h2>
命名空间：ViewFaceCore.Sharp : 人脸识别类所在的命名空间
<ul>
<li>属性说明：</li>
<li>方法说明：</li>
</ul>
<table style="height: 124px; float: left; width: 866px" border="1" align="center"><caption> </caption>
<tbody>
<tr>
<td>属性名称</td>
<td>类型</td>
<td>说明</td>
<td>默认值</td>
</tr>
<tr>
<td>ModelPath</td>
<td>string</td>
<td>获取或设置模型路径 [ 如非必要，请勿修改 ]</td>
<td>./model/</td>
</tr>
<tr>
<td>FaceType</td>
<td>FaceType</td>
<td>获取或设置人脸类型</td>
<td>FaceType.Light</td>
</tr>
<tr>
<td>MarkType</td>
<td>MarkType</td>
<td>获取或设置人脸关键点类型</td>
<td>MarkType.Light</td>
</tr>
<tr>
<td>DetectorSetting</td>
<td>DetectorSetting</td>
<td>获取或设置人脸检测器设置</td>
<td>new DetectorSetting()</td>
</tr>
</tbody>
</table>
 
 
 
 
 
 
 
<div class="cnblogs_code">
<pre> 1 using System.Drawing;
 2 using ViewFaceCore.Sharp;
 3 using ViewFaceCore.Sharp.Model;
 4
 5 // 识别 bitmap 中的人脸，并返回人脸的信息。
 6 FaceInfo[] FaceDetector(Bitmap);
 7
 8 // 识别 bitmap 中指定的人脸信息 info 的关键点坐标。
 9 FaceMarkPoint[] FaceMark(Bitmap, FaceInfo);
10
11 // 提取人脸特征值。
12 float[] Extract(Bitmap, FaceMarkPoint[]);
13
14 // 计算特征值相似度。
15 float Similarity(float[], float[]);
16
17 // 判断相似度是否为同一个人。
18 bool IsSelf(float);</pre>
</div>
<h2>四、实现</h2>
此项目受到了 SeetaFaceEngine.NET 项目的启发
这个项目本质上来说还是调用了 SeetaFace 的 C++ 类库来实现的人脸识别功能。针对本人遇到过的相关的类库的使用都不太方便，而且使用的 SeetaFace 的版本较老，故萌生了自己重新开发的想法。
本项目在开发完成之后为了方便调用，采用了 Nuget 包的形式，将所有需要的依赖以及最小识别模型一起打包。在使用时非常简单，只需要 nuget 安装，编写代码，运行即可，不需要多余的操作。
首先查看 SeetaFace ，已经更新到了v3(v6即v3)(上面前辈的项目是基于v1开发的)，最新版本暂时没有开源，但是可以免费商用。然后是根据以前的经验和 SeetaFace6 文档的指导，以及前辈的项目，做了以下操作。
1.对SeetaFace6 的接口进行了 C++ 形式的封装。
目前主要实现了人脸检测，关键点提取，特征值提取，特征值对比几个人脸识别中的基础接口。有了这几个接口，可以完整的实现一套人脸识别和验证的流程。
<ul>
<li>c++封装的接口代码如下：</li>
</ul>
<div class="cnblogs_code"><img id="code_img_closed_eaf465ba-5fd4-43ed-b2b4-e2b1097b3220" class="code_img_closed lazyload" data-src="http://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif"><img id="code_img_opened_eaf465ba-5fd4-43ed-b2b4-e2b1097b3220" class="code_img_opened lazyload" style="display: none" data-src="http://images.cnblogs.com/OutliningIndicators/ExpandedBlockStart.gif">
<div id="cnblogs_code_open_eaf465ba-5fd4-43ed-b2b4-e2b1097b3220" class="cnblogs_code_hide">
<pre>1 #include "seeta/FaceDetector.h"
2 #include "seeta/FaceLandmarker.h"
3 #include "seeta/FaceRecognizer.h"
4
5 #include <time.h>
6
7 #define View_Api extern "C" __declspec(dllexport)
8
9 using namespace std;
 10
 11 typedef void(_stdcall* LogCallBack)(const char* logText);
 12
 13 string modelPath = "./model/"; // 模型所在路径
 14 LogCallBack logger = NULL; // 日志回调函数
 15
 16 // 打印日志
 17 void WriteLog(string str) { if (logger != NULL) { logger(str.c_str()); } }
 18
 19 void WriteMessage(string fanctionName, string message) { WriteLog(fanctionName + "\t Message:" + message); }
 20 void WriteModelName(string fanctionName, string modelName) { WriteLog(fanctionName + "\t Model.Name:" + modelName); }
 21 void WriteRunTime(string fanctionName, int start) { WriteLog(fanctionName + "\t Run.Time:" + to_string(clock() - start) + " ms"); }
 22 void WriteError(string fanctionName, const std::exception& e) { WriteLog(fanctionName + "\t Error:" + e.what()); }
 23
 24 // 注册日志回调函数
 25 View_Api void V_SetLogFunction(LogCallBack writeLog)
 26 {
 27 logger = writeLog;
 28 WriteMessage(__FUNCDNAME__, "Successed.");
 29 }
 30
 31 // 设置人脸模型目录
 32 View_Api void V_SetModelPath(const char* path)
 33 {
 34 modelPath = path;
 35 WriteMessage(__FUNCDNAME__, "Model.Path:" + modelPath);
 36 }
 37 // 获取人脸模型目录
 38 View_Api bool V_GetModelPath(char** path)
 39 {
 40 try
 41 {
 42 #pragma warning(disable:4996)
 43 strcpy(*path, modelPath.c_str());
 44
 45 return true;
 46 }
 47 catch (const std::exception& e)
 48 {
 49 WriteError(__FUNCDNAME__, e);
 50 return false;
 51 }
 52 }
 53
 54 seeta::FaceDetector* v_faceDetector = NULL;
 55
 56 // 人脸检测结果
 57 static SeetaFaceInfoArray detectorInfos;
 58 // 人脸数量检测器
 59 View_Api int V_DetectorSize(unsigned char* imgData, int width, int height, int channels, double faceSize = 20, double threshold = 0.9, double maxWidth = 2000, double maxHeight = 2000, int type = 0)
 60 {
 61 try {
 62 clock_t start = clock();
 63
 64 SeetaImageData img = { width, height, channels, imgData };
 65 if (v_faceDetector == NULL) {
 66 seeta::ModelSetting setting;
 67 setting.set_device(SEETA_DEVICE_CPU);
 68 string modelName = "face_detector.csta";
 69 switch (type)
 70 {
 71 case 1: modelName = "mask_detector.csta"; break;
 72 }
 73 setting.append(modelPath + modelName);
 74 WriteModelName(__FUNCDNAME__, modelName);
 75 v_faceDetector = new seeta::FaceDetector(setting);
 76 }
 77
 78 if (faceSize != 20) { v_faceDetector->set(seeta::FaceDetector::Property::PROPERTY_MIN_FACE_SIZE, faceSize); }
 79 if (threshold != 0.9) { v_faceDetector->set(seeta::FaceDetector::Property::PROPERTY_THRESHOLD, threshold); }
 80 if (maxWidth != 2000) { v_faceDetector->set(seeta::FaceDetector::Property::PROPERTY_MAX_IMAGE_WIDTH, maxWidth); }
 81 if (maxHeight != 2000) { v_faceDetector->set(seeta::FaceDetector::Property::PROPERTY_MAX_IMAGE_HEIGHT, maxHeight); }
 82
 83 auto infos = v_faceDetector->detect(img);
 84 detectorInfos = infos;
 85
 86 WriteRunTime("V_Detector", start); // 此方法已经是人脸检测的全过程，故计时器显示为人脸识别方法
 87 return infos.size;
 88 }
 89 catch (const std::exception& e)
 90 {
 91 WriteError(__FUNCDNAME__, e);
 92 return -1;
 93 }
 94 }
 95 // 人脸检测器
 96 View_Api bool V_Detector(float* score, int* x, int* y, int* width, int* height)
 97 {
 98 try
 99 {
100 //clock_t start = clock();
101
102 for (int i = 0; i < detectorInfos.size; i++, detectorInfos.data++)
103 {
104 *score = detectorInfos.data->score;
105 *x = detectorInfos.data->pos.x;
106 *y = detectorInfos.data->pos.y;
107 *width = detectorInfos.data->pos.width;
108 *height = detectorInfos.data->pos.height;
109 score++, x++, y++, width++, height++;
110 }
111 detectorInfos.data = NULL;
112 detectorInfos.size = NULL;
113
114 //WriteRunTime(__FUNCDNAME__, start); // 此方法只是将人脸数量检测器获取到的数据赋值传递，并不耗时。故不显示此方法的调用时间
115 return true;
116 }
117 catch (const std::exception& e)
118 {
119 WriteError(__FUNCDNAME__, e);
120 return false;
121 }
122 }
123
124
125 seeta::FaceLandmarker* v_faceLandmarker = NULL;
126 // 人脸关键点数量
127 View_Api int V_FaceMarkSize(int type = 0)
128 {
129 try
130 {
131 clock_t start = clock();
132
133 if (v_faceLandmarker == NULL) {
134 seeta::ModelSetting setting;
135 setting.set_device(SEETA_DEVICE_CPU);
136 string modelName = "face_landmarker_pts68.csta";
137 switch (type)
138 {
139 case 1: modelName = "face_landmarker_mask_pts5.csta"; break;
140 case 2: modelName = "face_landmarker_pts5.csta"; break;
141 }
142 setting.append(modelPath + modelName);
143 WriteModelName(__FUNCDNAME__, modelName);
144 v_faceLandmarker = new seeta::FaceLandmarker(setting);
145 }
146 int size = v_faceLandmarker->number();
147
148 WriteRunTime(__FUNCDNAME__, start);
149 return size;
150 }
151 catch (const std::exception& e)
152 {
153 WriteError(__FUNCDNAME__, e);
154 return -1;
155 }
156 }
157 // 人脸关键点
158 View_Api bool V_FaceMark(unsigned char* imgData, int width, int height, int channels, int x, int y, int fWidth, int fHeight, double* pointX, double* pointY, int type = 0)
159 {
160 try
161 {
162 clock_t start = clock();
163
164 SeetaImageData img = { width, height, channels, imgData };
165 SeetaRect face = { x, y, fWidth, fHeight };
166 if (v_faceLandmarker == NULL) {
167 seeta::ModelSetting setting;
168 setting.set_device(SEETA_DEVICE_CPU);
169 string modelName = "face_landmarker_pts68.csta";
170 switch (type)
171 {
172 case 1: modelName = "face_landmarker_mask_pts5.csta"; break;
173 case 2: modelName = "face_landmarker_pts5.csta"; break;
174 }
175 setting.append(modelPath + modelName);
176 WriteModelName(__FUNCDNAME__, modelName);
177 v_faceLandmarker = new seeta::FaceLandmarker(setting);
178 }
179 std::vector<SeetaPointF> _points = v_faceLandmarker->mark(img, face);
180
181 if (!_points.empty()) {
182 for (auto iter = _points.begin(); iter != _points.end(); iter++)
183 {
184 *pointX = (*iter).x;
185 *pointY = (*iter).y;
186 pointX++;
187 pointY++;
188 }
189
190 WriteRunTime(__FUNCDNAME__, start);
191 return true;
192 }
193 else { return false; }
194 }
195 catch (const std::exception& e)
196 {
197 WriteError(__FUNCDNAME__, e);
198 return false;
199 }
200 }
201
202 seeta::FaceRecognizer* v_faceRecognizer = NULL;
203 // 获取人脸特征值长度
204 View_Api int V_ExtractSize(int type = 0)
205 {
206 try
207 {
208 clock_t start = clock();
209
210 if (v_faceRecognizer == NULL) {
211 seeta::ModelSetting setting;
212 setting.set_id(0);
213 setting.set_device(SEETA_DEVICE_CPU);
214 string modelName = "face_recognizer.csta";
215 switch (type)
216 {
217 case 1: modelName = "face_recognizer_mask.csta"; break;
218 case 2: modelName = "face_recognizer_light.csta"; break;
219 }
220 setting.append(modelPath + modelName);
221 WriteModelName(__FUNCDNAME__, modelName);
222 v_faceRecognizer = new seeta::FaceRecognizer(setting);
223 }
224 int length = v_faceRecognizer->GetExtractFeatureSize();
225
226 WriteRunTime(__FUNCDNAME__, start);
227 return length;
228 }
229 catch (const std::exception& e)
230 {
231 WriteError(__FUNCDNAME__, e);
232 return -1;
233 }
234 }
235 // 提取人脸特征值
236 View_Api bool V_Extract(unsigned char* imgData, int width, int height, int channels, SeetaPointF* points, float* features, int type = 0)
237 {
238 try
239 {
240 clock_t start = clock();
241
242 SeetaImageData img = { width, height, channels, imgData };
243 if (v_faceRecognizer == NULL) {
244 seeta::ModelSetting setting;
245 setting.set_id(0);
246 setting.set_device(SEETA_DEVICE_CPU);
247 string modelName = "face_recognizer.csta";
248 switch (type)
249 {
250 case 1: modelName = "face_recognizer_mask.csta"; break;
251 case 2: modelName = "face_recognizer_light.csta"; break;
252 }
253 setting.append(modelPath + modelName);
254 WriteModelName(__FUNCDNAME__, modelName);
255 v_faceRecognizer = new seeta::FaceRecognizer(setting);
256 }
257 int length = v_faceRecognizer->GetExtractFeatureSize();
258 std::shared_ptr<float> _features(new float, std::default_delete<float[]>());
259 v_faceRecognizer->Extract(img, points, _features.get());
260
261 for (int i = 0; i < length; i++)
262 {
263 *features = _features.get();
264 features++;
265 }
266
267 WriteRunTime(__FUNCDNAME__, start);
268 return true;
269
270 }
271 catch (const std::exception& e)
272 {
273 WriteError(__FUNCDNAME__, e);
274 return false;
275 }
276 }
277 // 人脸特征值相似度计算
278 View_Api float V_CalculateSimilarity(float* leftFeatures, float* rightFeatures, int type = 0)
279 {
280 try
281 {
282 clock_t start = clock();
283
284 if (v_faceRecognizer == NULL) {
285 seeta::ModelSetting setting;
286 setting.set_id(0);
287 setting.set_device(SEETA_DEVICE_CPU);
288 string modelName = "face_recognizer.csta";
289 switch (type)
290 {
291 case 1: modelName = "face_recognizer_mask.csta"; break;
292 case 2: modelName = "face_recognizer_light.csta"; break;
293 }
294 setting.append(modelPath + modelName);
295 WriteModelName(__FUNCDNAME__, modelName);
296 v_faceRecognizer = new seeta::FaceRecognizer(setting);
297 }
298
299 auto similarity = v_faceRecognizer->CalculateSimilarity(leftFeatures, rightFeatures);
300 WriteMessage(__FUNCDNAME__, "Similarity = " + to_string(similarity));
301 WriteRunTime(__FUNCDNAME__, start);
302 return similarity;
303 }
304 catch (const std::exception& e)
305 {
306 WriteError(__FUNCDNAME__, e);
307 return -1;
308 }
309 }
310
311 // 释放资源
312 View_Api void V_Dispose()
313 {
314 if (v_faceDetector != NULL) delete v_faceDetector;
315 if (v_faceLandmarker != NULL) delete v_faceLandmarker;
316 if (v_faceRecognizer != NULL) delete v_faceRecognizer;
317 }</pre>
</div>
C++ 封装层</div>
2.采用 C# 对上诉接口进行了导入。
因为C++的项目测CPU架构区分x86和x64，所以C# 层也需要区分架构封装
<div class="cnblogs_code"><img id="code_img_closed_9bbb6485-019d-474e-ba74-eb434b364457" class="code_img_closed lazyload" data-src="http://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif"><img id="code_img_opened_9bbb6485-019d-474e-ba74-eb434b364457" class="code_img_opened lazyload" style="display: none" data-src="http://images.cnblogs.com/OutliningIndicators/ExpandedBlockStart.gif">
<div id="cnblogs_code_open_9bbb6485-019d-474e-ba74-eb434b364457" class="cnblogs_code_hide">
<pre>using System.Runtime.InteropServices;
using System.Text;
using ViewFaceCore.Sharp.Model;

namespace ViewFaceCore.Plus
{
/// <summary>
/// 日志回调函数
/// </summary>
/// <param name="logText"></param>
public delegate void LogCallBack(string logText);

class ViewFacePlus64
{
 const string LibraryPath = @"FaceLibraries\x64\ViewFace.dll";
 /// <summary>
 /// 设置日志回调函数(用于日志打印)
 /// </summary>
 /// <param name="writeLog"></param>

 public static extern void SetLogFunction(LogCallBack writeLog);

 /// <summary>
 /// 设置人脸模型的目录
 /// </summary>
 /// <param name="path"></param>

 private extern static void SetModelPath(byte[] path);
 /// <summary>
 /// 设置人脸模型的目录
 /// </summary>
 /// <param name="path"></param>
 public static void SetModelPath(string path) => SetModelPath(Encoding.UTF8.GetBytes(path));

 /// <summary>
 /// 释放使用的资源
 /// </summary>

 public extern static void ViewDispose();

 /// <summary>
 /// 获取人脸模型的目录
 /// </summary>
 /// <param name="path"></param>

 private extern static bool GetModelPathEx(ref string path);
 /// <summary>
 /// 获取人脸模型的目录
 /// </summary>
 public static string GetModelPath() { string path = string.Empty; GetModelPathEx(ref path); return path; }

 /// <summary>
 /// 人脸检测器检测到的人脸数量
 /// </summary>
 /// <param name="imgData"></param>
 /// <param name="width"></param>
 /// <param name="height"></param>
 /// <param name="channels"></param>
 /// <param name="faceSize">最小人脸是人脸检测器常用的一个概念，默认值为20，单位像素。
 /// <para>最小人脸和检测器性能息息相关。主要方面是速度，使用建议上，我们建议在应用范围内，这个值设定的越大越好。SeetaFace采用的是BindingBox Regresion的方式训练的检测器。如果最小人脸参数设置为80的话，从检测能力上，可以将原图缩小的原来的1/4，这样从计算复杂度上，能够比最小人脸设置为20时，提速到16倍。</para>
 /// </param>
 /// <param name="threshold">检测器阈值默认值是0.9，合理范围为。这个值一般不进行调整，除了用来处理一些极端情况。这个值设置的越小，漏检的概率越小，同时误检的概率会提高</param>
 /// <param name="maxWidth">可检测的图像最大宽度。默认值2000。</param>
 /// <param name="maxHeight">可检测的图像最大高度。默认值2000。</param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static int DetectorSize(byte[] imgData, int width, int height, int channels, double faceSize = 20, double threshold = 0.9, double maxWidth = 2000, double maxHeight = 2000, int type = 0);
 /// <summary>
 /// 人脸检测器
 /// <para>调用此方法前必须先调用 <see cref="DetectorSize(byte[], int, int, int, double, double, double, double, int)"/></para>
 /// </summary>
 /// <param name="score">人脸置信度集合</param>
 /// <param name="x">人脸位置集合</param>
 /// <param name="y">人脸位置集合</param>
 /// <param name="width">人脸大小集合</param>
 /// <param name="height">人脸大小集合</param>
 /// <returns></returns>

 public extern static bool Detector(float[] score, int[] x, int[] y, int[] width, int[] height);

 /// <summary>
 /// 人脸关键点数量
 /// </summary>
 /// <returns></returns>

 public extern static int FaceMarkSize(int type = 0);
 /// <summary>
 /// 人脸关键点
 /// </summary>
 /// <param name="imgData"></param>
 /// <param name="width"></param>
 /// <param name="height"></param>
 /// <param name="channels"></param>
 /// <param name="x"></param>
 /// <param name="y"></param>
 /// <param name="fWidth"></param>
 /// <param name="fHeight"></param>
 /// <param name="pointX"></param>
 /// <param name="pointY"></param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static bool FaceMark(byte[] imgData, int width, int height, int channels, int x, int y, int fWidth, int fHeight, double[] pointX, double[] pointY, int type = 0);

 /// <summary>
 /// 提取特征值
 /// </summary>
 /// <param name="imgData"></param>
 /// <param name="width"></param>
 /// <param name="height"></param>
 /// <param name="channels"></param>
 /// <param name="points"></param>
 /// <param name="features"></param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static bool Extract(byte[] imgData, int width, int height, int channels, FaceMarkPoint[] points, float[] features, int type = 0);
 /// <summary>
 /// 特征值大小
 /// </summary>
 /// <returns></returns>

 public extern static int ExtractSize(int type = 0);

 /// <summary>
 /// 计算相似度
 /// </summary>
 /// <param name="leftFeatures"></param>
 /// <param name="rightFeatures"></param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static float Similarity(float[] leftFeatures, float[] rightFeatures, int type = 0);
}
class ViewFacePlus32
{
 const string LibraryPath = @"FaceLibraries\x86\ViewFace.dll";
 /// <summary>
 /// 设置日志回调函数(用于日志打印)
 /// </summary>
 /// <param name="writeLog"></param>

 public static extern void SetLogFunction(LogCallBack writeLog);

 /// <summary>
 /// 设置人脸模型的目录
 /// </summary>
 /// <param name="path"></param>

 private extern static void SetModelPath(byte[] path);
 /// <summary>
 /// 设置人脸模型的目录
 /// </summary>
 /// <param name="path"></param>
 public static void SetModelPath(string path) => SetModelPath(Encoding.UTF8.GetBytes(path));

 /// <summary>
 /// 释放使用的资源
 /// </summary>

 public extern static void ViewDispose();

 /// <summary>
 /// 获取人脸模型的目录
 /// </summary>
 /// <param name="path"></param>

 private extern static bool GetModelPathEx(ref string path);
 /// <summary>
 /// 获取人脸模型的目录
 /// </summary>
 public static string GetModelPath() { string path = string.Empty; GetModelPathEx(ref path); return path; }

 /// <summary>
 /// 人脸检测器检测到的人脸数量
 /// </summary>
 /// <param name="imgData"></param>
 /// <param name="width"></param>
 /// <param name="height"></param>
 /// <param name="channels"></param>
 /// <param name="faceSize">最小人脸是人脸检测器常用的一个概念，默认值为20，单位像素。
 /// <para>最小人脸和检测器性能息息相关。主要方面是速度，使用建议上，我们建议在应用范围内，这个值设定的越大越好。SeetaFace采用的是BindingBox Regresion的方式训练的检测器。如果最小人脸参数设置为80的话，从检测能力上，可以将原图缩小的原来的1/4，这样从计算复杂度上，能够比最小人脸设置为20时，提速到16倍。</para>
 /// </param>
 /// <param name="threshold">检测器阈值默认值是0.9，合理范围为。这个值一般不进行调整，除了用来处理一些极端情况。这个值设置的越小，漏检的概率越小，同时误检的概率会提高</param>
 /// <param name="maxWidth">可检测的图像最大宽度。默认值2000。</param>
 /// <param name="maxHeight">可检测的图像最大高度。默认值2000。</param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static int DetectorSize(byte[] imgData, int width, int height, int channels, double faceSize = 20, double threshold = 0.9, double maxWidth = 2000, double maxHeight = 2000, int type = 0);
 /// <summary>
 /// 人脸检测器
 /// <para>调用此方法前必须先调用 <see cref="DetectorSize(byte[], int, int, int, double, double, double, double, int)"/></para>
 /// </summary>
 /// <param name="score">人脸置信度集合</param>
 /// <param name="x">人脸位置集合</param>
 /// <param name="y">人脸位置集合</param>
 /// <param name="width">人脸大小集合</param>
 /// <param name="height">人脸大小集合</param>
 /// <returns></returns>

 public extern static bool Detector(float[] score, int[] x, int[] y, int[] width, int[] height);

 /// <summary>
 /// 人脸关键点数量
 /// </summary>
 /// <returns></returns>

 public extern static int FaceMarkSize(int type = 0);
 /// <summary>
 /// 人脸关键点
 /// </summary>
 /// <param name="imgData"></param>
 /// <param name="width"></param>
 /// <param name="height"></param>
 /// <param name="channels"></param>
 /// <param name="x"></param>
 /// <param name="y"></param>
 /// <param name="fWidth"></param>
 /// <param name="fHeight"></param>
 /// <param name="pointX"></param>
 /// <param name="pointY"></param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static bool FaceMark(byte[] imgData, int width, int height, int channels, int x, int y, int fWidth, int fHeight, double[] pointX, double[] pointY, int type = 0);

 /// <summary>
 /// 提取特征值
 /// </summary>
 /// <param name="imgData"></param>
 /// <param name="width"></param>
 /// <param name="height"></param>
 /// <param name="channels"></param>
 /// <param name="points"></param>
 /// <param name="features"></param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static bool Extract(byte[] imgData, int width, int height, int channels, FaceMarkPoint[] points, float[] features, int type = 0);
 /// <summary>
 /// 特征值大小
 /// </summary>
 /// <returns></returns>

 public extern static int ExtractSize(int type = 0);

 /// <summary>
 /// 计算相似度
 /// </summary>
 /// <param name="leftFeatures"></param>
 /// <param name="rightFeatures"></param>
 /// <param name="type"></param>
 /// <returns></returns>

 public extern static float Similarity(float[] leftFeatures, float[] rightFeatures, int type = 0);
}
}</pre>
</div>
C# 导入层</div>
3.采用 C# 的面向对象的封装
因为C#的项目默认都是 AnyCPU，所以为了简化调用，在这一层封装的时候增加了架构判断，当在你的项目中引用的时候，不用做任何修改。
且因为C++的C#导入方法在和原生的C#写法略有差异，且数据的转换和传递比较麻烦，所以类库中对外隐藏了 C# 导入层。并使用大家都更熟悉的C#的面向对象的方式进行进一步的封装和简化。
<div class="cnblogs_code"><img id="code_img_closed_8a137109-953a-4572-a8e4-98b021abbbed" class="code_img_closed lazyload" data-src="http://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif"><img id="code_img_opened_8a137109-953a-4572-a8e4-98b021abbbed" class="code_img_opened lazyload" style="display: none" data-src="http://images.cnblogs.com/OutliningIndicators/ExpandedBlockStart.gif">
<div id="cnblogs_code_open_8a137109-953a-4572-a8e4-98b021abbbed" class="cnblogs_code_hide">
<pre>1 /// <summary>
2 /// 人脸识别类
3 /// </summary>
4 public class ViewFace
5 {
6 bool Platform64 { get; set; } = false;
7 // <para>需要模型：<see langword=""/></para>
8
9 // ctor
 10 /// <summary>
 11 /// 使用默认的模型目录初始化人脸识别类
 12 /// </summary>
 13 public ViewFace() : this("./model/") { }
 14 /// <summary>
 15 /// 使用指定的模型目录初始化人脸识别类
 16 /// </summary>
 17 /// <param name="modelPath">模型目录</param>
 18 public ViewFace(string modelPath)
 19 {
 20 Platform64 = IntPtr.Size == 8;
 21 if (Platform64)
 22 { ViewFacePlus64.SetModelPath(modelPath); }
 23 else
 24 { ViewFacePlus32.SetModelPath(modelPath); }
 25 }
 26 /// <summary>
 27 /// 使用指定的日志回调函数初始化人脸识别类
 28 /// </summary>
 29 /// <param name="action">日志回调函数</param>
 30 public ViewFace(LogCallBack action) : this("./model/", action) { }
 31 /// <summary>
 32 /// 使用指定的模型目录、日志回调函数初始化人脸识别类
 33 /// </summary>
 34 /// <param name="modelPath">模型目录</param>
 35 /// <param name="action">日志回调函数</param>
 36 public ViewFace(string modelPath, LogCallBack action) : this(modelPath)
 37 {
 38 if (Platform64)
 39 { ViewFacePlus64.SetLogFunction(action); }
 40 else
 41 { ViewFacePlus32.SetLogFunction(action); }
 42 }
 43
 44 // public property
 45 /// <summary>
 46 /// 获取或设置模型路径
 47 /// </summary>
 48 public string ModelPath
 49 {
 50 get
 51 {
 52 if (Platform64)
 53 { return ViewFacePlus64.GetModelPath(); }
 54 else
 55 { return ViewFacePlus32.GetModelPath(); }
 56 }
 57 set
 58 {
 59 if (Platform64)
 60 { ViewFacePlus64.SetModelPath(value); }
 61 else
 62 { ViewFacePlus32.SetModelPath(value); }
 63 }
 64 }
 65 /// <summary>
 66 /// 获取或设置人脸类型
 67 /// <para>
 68 /// <listheader>此属性可影响到以下方法：</listheader> 
 69 /// • <c><see cref="FaceDetector(Bitmap)"/></c> 
 70 /// • <c><see cref="Extract(Bitmap, FaceMarkPoint[])"/></c> 
 71 /// • <c><see cref="Similarity(float[], float[])"/></c> 
 72 /// </para>
 73 /// </summary>
 74 public FaceType FaceType { get; set; } = FaceType.Light;
 75 /// <summary>
 76 /// 获取或设置人脸关键点类型
 77 /// <para>
 78 /// <listheader>此属性可影响到以下方法：</listheader> 
 79 /// • <c><see cref="FaceMark(Bitmap, FaceInfo)"/></c> 
 80 /// </para>
 81 /// </summary>
 82 public MarkType MarkType { get; set; } = MarkType.Light;
 83 /// <summary>
 84 /// 获取或设置人脸检测器设置
 85 /// </summary>
 86 public DetectorSetting DetectorSetting { get; set; } = new DetectorSetting();
 87
 88
 89 // public method
 90 /// <summary>
 91 /// 识别 <paramref name="bitmap"/> 中的人脸，并返回人脸的信息。
 92 /// <para>
 93 /// 当 <c><see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Normal"/> <see langword="||"/> <see cref="FaceType.Light"/></c> 时，需要模型：<see langword="face_detector.csta"/> 
 94 /// 当 <c><see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Mask"/></c> 时，需要模型：<see langword="mask_detector.csta"/> 
 95 /// </para>
 96 /// </summary>
 97 /// <param name="bitmap">包含人脸的图片</param>
 98 /// <returns></returns>
 99 public FaceInfo[] FaceDetector(Bitmap bitmap)
100 {
101 byte[] bgr = ImageSet.Get24BGRFromBitmap(bitmap, out int width, out int height, out int channels);
102 int size;
103 if (Platform64)
104 { size = ViewFacePlus64.DetectorSize(bgr, width, height, channels, DetectorSetting.FaceSize, DetectorSetting.Threshold, DetectorSetting.MaxWidth, DetectorSetting.MaxHeight, (int)FaceType); }
105 else
106 { size = ViewFacePlus32.DetectorSize(bgr, width, height, channels, DetectorSetting.FaceSize, DetectorSetting.Threshold, DetectorSetting.MaxWidth, DetectorSetting.MaxHeight, (int)FaceType); }
107 float[] _socre = new float;
108 int[] _x = new int;
109 int[] _y = new int;
110 int[] _width = new int;
111 int[] _height = new int;
112 if (Platform64)
113 { _ = ViewFacePlus64.Detector(_socre, _x, _y, _width, _height); }
114 else
115 { _ = ViewFacePlus32.Detector(_socre, _x, _y, _width, _height); }
116 List<FaceInfo> infos = new List<FaceInfo>();
117 for (int i = 0; i < size; i++)
118 {
119 infos.Add(new FaceInfo() { Score = _socre, Location = new FaceRect() { X = _x, Y = _y, Width = _width, Height = _height } });
120 }
121 return infos.ToArray();
122 }
123
124 /// <summary>
125 /// 识别 <paramref name="bitmap"/> 中指定的人脸信息 <paramref name="info"/> 的关键点坐标。
126 /// <para>
127 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Normal"/> 时，需要模型：<see langword="face_landmarker_pts68.csta"/> 
128 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Mask"/> 时，需要模型：<see langword="face_landmarker_mask_pts5.csta"/> 
129 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Light"/> 时，需要模型：<see langword="face_landmarker_pts5.csta"/> 
130 /// </para>
131 /// </summary>
132 /// <param name="bitmap">包含人脸的图片</param>
133 /// <param name="info">指定的人脸信息</param>
134 /// <returns></returns>
135 public FaceMarkPoint[] FaceMark(Bitmap bitmap, FaceInfo info)
136 {
137 byte[] bgr = ImageSet.Get24BGRFromBitmap(bitmap, out int width, out int height, out int channels);
138 int size;
139 if (Platform64)
140 { size = ViewFacePlus64.FaceMarkSize((int)MarkType); }
141 else
142 { size = ViewFacePlus32.FaceMarkSize((int)MarkType); }
143 double[] _pointX = new double;
144 double[] _pointY = new double;
145 bool val;
146 if (Platform64)
147 { val = ViewFacePlus64.FaceMark(bgr, width, height, channels, info.Location.X, info.Location.Y, info.Location.Width, info.Location.Height, _pointX, _pointY, (int)MarkType); }
148 else
149 { val = ViewFacePlus32.FaceMark(bgr, width, height, channels, info.Location.X, info.Location.Y, info.Location.Width, info.Location.Height, _pointX, _pointY, (int)MarkType); }
150 if (val)
151 {
152 List<FaceMarkPoint> points = new List<FaceMarkPoint>();
153 for (int i = 0; i < size; i++)
154 { points.Add(new FaceMarkPoint() { X = _pointX, Y = _pointY }); }
155 return points.ToArray();
156 }
157 else
158 { throw new Exception("人脸关键点获取失败"); }
159 }
160
161 /// <summary>
162 /// 提取人脸特征值。
163 /// <para>
164 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Normal"/> 时，需要模型：<see langword="face_recognizer.csta"/> 
165 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Mask"/> 时，需要模型：<see langword="face_recognizer_mask.csta"/> 
166 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Light"/> 时，需要模型：<see langword="face_recognizer_light.csta"/> 
167 /// </para>
168 /// </summary>
169 /// <param name="bitmap"></param>
170 /// <param name="points"></param>
171 /// <returns></returns>
172 public float[] Extract(Bitmap bitmap, FaceMarkPoint[] points)
173 {
174 byte[] bgr = ImageSet.Get24BGRFromBitmap(bitmap, out int width, out int height, out int channels);
175 float[] features;
176 if (Platform64)
177 { features = new float; }
178 else
179 { features = new float; }
180
181 if (Platform64)
182 { ViewFacePlus64.Extract(bgr, width, height, channels, points, features, (int)FaceType); }
183 else
184 { ViewFacePlus32.Extract(bgr, width, height, channels, points, features, (int)FaceType); }
185 return features;
186 }
187
188 /// <summary>
189 /// 计算特征值相似度。
190 /// <para>只能计算相同 <see cref="FaceType"/> 计算出的特征值</para>
191 /// <para>
192 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Normal"/> 时，需要模型：<see langword="face_recognizer.csta"/> 
193 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Mask"/> 时，需要模型：<see langword="face_recognizer_mask.csta"/> 
194 /// 当 <see cref="FaceType"/> <see langword="="/> <see cref="FaceType.Light"/> 时，需要模型：<see langword="face_recognizer_light.csta"/> 
195 /// </para>
196 /// </summary>
197 /// <exception cref="ArgumentException"/>
198 /// <exception cref="ArgumentNullException"/>
199 /// <param name="leftFeatures"></param>
200 /// <param name="rightFeatures"></param>
201 /// <returns></returns>
202 public float Similarity(float[] leftFeatures, float[] rightFeatures)
203 {
204 if (leftFeatures.Length == 0 || rightFeatures.Length == 0)
205 throw new ArgumentNullException("参数不能为空", nameof(leftFeatures));
206 if (leftFeatures.Length != rightFeatures.Length)
207 throw new ArgumentException("两个参数长度不一致");
208
209
210 if (Platform64)
211 { return ViewFacePlus64.Similarity(leftFeatures, rightFeatures, (int)FaceType); }
212 else
213 { return ViewFacePlus32.Similarity(leftFeatures, rightFeatures, (int)FaceType); }
214 }
215
216 /// <summary>
217 /// 判断相似度是否为同一个人。
218 /// </summary>
219 /// <param name="similarity">相似度</param>
220 /// <returns></returns>
221 public bool IsSelf(float similarity) => similarity > Face.Threshold;
222
223 /// <summary>
224 /// 释放资源
225 /// </summary>
226 ~ViewFace()
227 {
228 if (Platform64)
229 { ViewFacePlus64.ViewDispose(); }
230 else
231 { ViewFacePlus32.ViewDispose(); }
232 }
233 }</pre>
</div>
C# 面向对象层</div>
 
<h2>五、也许…</h2>
<ul>
<li>此项目还未实现 SeetaFace6 中的许多特性，也许：</li>
</ul>
　　　　想起 GitHub 密码，持续更新… 　　　　删除代码仓库跑路…
<ul>
<li>如果在使用过程中遇到问题，你也许可以：</li>

</ul>
　　　　在 GitHub 报告Bug… 　　　　向我发送邮件 
来源：https://www.cnblogs.com/view12138/p/ViewFaceCore.html

頁: [1]

琼殿技术论坛's Archiver

C# 人脸识别库 0.1