# Author:KuoYuan Li
[](https://sites.google.com/ms2.ccsh.tn.edu.tw/pclearn0915)
本程式簡單地結合dlib,opencv 測試過在windows作業系統底下可正常運行且另外提供colab版本
讓不懂機器學習的朋友可以軟簡單地操作人臉辨識,
程式需另外安裝 dlib
搜尋關鍵字：whl dlib cp*** ***代表python版本 ex:cp310代表 python 3.10
dlib whl 安裝包下載網站: (https://github.com/Murtaza-Saeed/dlib/tree/master)
- 本套工具主要針對windows使用者設計，相依之 package 及相容性問題需自行排除
- dlib whl 安裝包下載後必需由檔案離線安裝 pip install ...
- opencv whl 下載點:請下載合適的opencv版本<br>
(https://pypi.tuna.tsinghua.edu.cn/simple/opencv-contrib-python/)
- Note: opencv 安裝的路徑上如果有中文會導致運作不正常，建議使用者名稱不要使用中文，或是先確認python有裝在沒有中文的路徑底下
- 安裝 mediapipe 會順便自動安裝 opencv ，可以直接先安裝 mediapipe
```
pip install mediapipe
```
※PS:
2022/11/24 使用 python3.10 搭配
dlib-19.22.99-cp310-cp310-win_amd64.whl 試用成功
2023/4/2
調整函式，適配 colab
(https://colab.research.google.com/drive/1ou7nWLQGl8uYLR_jUDyush9-D8ToTe8P?usp=sharing)
移除不常用之影像檔處理函式
新增直接和 opencv 協作模式
2023/11/4
發現的某些 windows 作業系統如果灌
python3.10 搭配
dlib-19.22.99-cp310-cp310-win_amd64.whl
會產生下列錯誤：
from _dlib_pybin11 import * ImportError: DLL load failed: 找不到指定的程序
※解決方案：
新安裝一組 python3.11(64bit)
(https://www.python.org/ftp/python/3.11.6/python-3.11.6-amd64.exe)
搭配dlib-19.24.1-cp311-cp311-win_amd64.whl
```
pip install https://github.com/Murtaza-Saeed/dlib/raw/master/dlib-19.24.1-cp311-cp311-win_amd64.whl
```
Thonny的使用者可至 工具>>選項>>直譯器>... 修改python.exe之位置，變成合適的python版本
vscode的使用者可按ctrl+shift+p 於上方輸入 >python:Select Interpreter 選擇合適的python版本
##### Download the samples to 'train' folder(下載各種照片樣本至train資料夾)
```
import pyFaceTrace as ft
ft.downloadImageSamples()
```
##### work with opencv webcam process (detail)
```
import pyFaceTrace as ft
import cv2
from PIL import ImageFont
#至train資料夾載入樣本,欲辨識之目標圖片可放入 train資料夾
ft.loadDB()
#設定文字物件
FONT = ImageFont.truetype("kaiu.ttf",50,index=0)
#webcamd 影像處理迴圈
cap = cv2.VideoCapture(0,cv2.CAP_DSHOW)
while True:
ret, img = cap.read()
if not ret : continue
#取得 img 中所有人臉之矩型區域，放入rects
rects=ft.detector(img,1)
for rect in rects:
#取得webcam img 中人臉之特徵向量
fv=ft.getFeatureVector(img,rect)
#將特徵向量和 ft.DB 中之人特徵向量做比對，找到距離最短的(dist)當作辨識結果(tag)
tag,dist = ft.predictFromDB(fv)
#將辨識結果顯示在 img 上
cv2.rectangle(img,(rect.left(),rect.top()),(rect.right(),rect.bottom()),(0,0,255),3)
img=ft.addText2Img_cv2(img,tag,FONT,position=(rect.left(),rect.top()-FONT.size-1))
if cv2.waitKey(10) == 27: break
# 將 img show在視窗中
cv2.imshow('press esc to exit...', img)
cap.release()
cv2.destroyAllWindows()
```
##### work with opencv webcam process (esay)
```
import pyFaceTrace as ft
import cv2
ft.loadDB()
cap = cv2.VideoCapture(0,cv2.CAP_DSHOW)
while(True):
ret, img = cap.read()
if not ret:continue
#img=cv2.flip(img,1)
tags,dists,rects,img = ft.predictImage(img)
cv2.imshow('press esc to exit...', img)
if cv2.waitKey(10) == 27: break
cap.release()
cv2.destroyAllWindows()
```
### Demo with webcam
```
import pyFaceTrace as ft
ft.loadDB(folder='train')
ft.predictCam()
```
##### 比對目前webcam擷取到的人臉和指定影像檔案並計算它們之間的距離
```
import pyFaceTrace as ft
im = ft.captureImageFromCam()
VTest = ft.getFeatureVector(im)
Vtrain = ft.loadFeatureFromPic('train\\李國源.jpg')
D=ft.dist(VTest,Vtrain)
print('距離=',D)
```
##### 載入train資料夾中所有jpg檔之特徵及tag並直接預測目前webcam擷取到的人臉對應的TAG
```
import pyFaceTrace as ft
ft.loadDB(folder='train')
im = ft.captureImageFromCam()
VTest = ft.getFeatureVector(im)
result = ft.predictFromDB(VTest)
print(result)
```
License
----
MIT
Raw data
{
"_id": null,
"home_page": "https://pypi.org/project/pyFaceTrace",
"name": "pyFaceTrace",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "Face recognition,Face Trace",
"author": "KuoYuan Li",
"author_email": "funny4875@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/82/4a/4b7a5afd2a9705e140d8737879b3f266ef8fa440ba653b2884efcf3315a8/pyFaceTrace-5.0.7.tar.gz",
"platform": null,
"description": "# Author:KuoYuan Li\n[](https://sites.google.com/ms2.ccsh.tn.edu.tw/pclearn0915) \n\u672c\u7a0b\u5f0f\u7c21\u55ae\u5730\u7d50\u5408dlib,opencv \u6e2c\u8a66\u904e\u5728windows\u4f5c\u696d\u7cfb\u7d71\u5e95\u4e0b\u53ef\u6b63\u5e38\u904b\u884c\u4e14\u53e6\u5916\u63d0\u4f9bcolab\u7248\u672c \n\u8b93\u4e0d\u61c2\u6a5f\u5668\u5b78\u7fd2\u7684\u670b\u53cb\u53ef\u4ee5\u8edf\u7c21\u55ae\u5730\u64cd\u4f5c\u4eba\u81c9\u8fa8\u8b58, \n\u7a0b\u5f0f\u9700\u53e6\u5916\u5b89\u88dd dlib \n\u641c\u5c0b\u95dc\u9375\u5b57\uff1awhl dlib cp*** ***\u4ee3\u8868python\u7248\u672c ex:cp310\u4ee3\u8868 python 3.10 \ndlib whl \u5b89\u88dd\u5305\u4e0b\u8f09\u7db2\u7ad9: (https://github.com/Murtaza-Saeed/dlib/tree/master)\n - \u672c\u5957\u5de5\u5177\u4e3b\u8981\u91dd\u5c0dwindows\u4f7f\u7528\u8005\u8a2d\u8a08\uff0c\u76f8\u4f9d\u4e4b package \u53ca\u76f8\u5bb9\u6027\u554f\u984c\u9700\u81ea\u884c\u6392\u9664 \n - dlib whl \u5b89\u88dd\u5305\u4e0b\u8f09\u5f8c\u5fc5\u9700\u7531\u6a94\u6848\u96e2\u7dda\u5b89\u88dd pip install ...\n - opencv whl \u4e0b\u8f09\u9ede:\u8acb\u4e0b\u8f09\u5408\u9069\u7684opencv\u7248\u672c<br>\n (https://pypi.tuna.tsinghua.edu.cn/simple/opencv-contrib-python/) \n - Note: opencv \u5b89\u88dd\u7684\u8def\u5f91\u4e0a\u5982\u679c\u6709\u4e2d\u6587\u6703\u5c0e\u81f4\u904b\u4f5c\u4e0d\u6b63\u5e38\uff0c\u5efa\u8b70\u4f7f\u7528\u8005\u540d\u7a31\u4e0d\u8981\u4f7f\u7528\u4e2d\u6587\uff0c\u6216\u662f\u5148\u78ba\u8a8dpython\u6709\u88dd\u5728\u6c92\u6709\u4e2d\u6587\u7684\u8def\u5f91\u5e95\u4e0b \n - \u5b89\u88dd mediapipe \u6703\u9806\u4fbf\u81ea\u52d5\u5b89\u88dd opencv \uff0c\u53ef\u4ee5\u76f4\u63a5\u5148\u5b89\u88dd mediapipe \n ```\n pip install mediapipe\n ```\n\u203bPS: \n2022/11/24 \u4f7f\u7528 python3.10 \u642d\u914d \n dlib-19.22.99-cp310-cp310-win_amd64.whl \u8a66\u7528\u6210\u529f \n \n2023/4/2 \n \u8abf\u6574\u51fd\u5f0f\uff0c\u9069\u914d colab \n (https://colab.research.google.com/drive/1ou7nWLQGl8uYLR_jUDyush9-D8ToTe8P?usp=sharing) \n \u79fb\u9664\u4e0d\u5e38\u7528\u4e4b\u5f71\u50cf\u6a94\u8655\u7406\u51fd\u5f0f \n \u65b0\u589e\u76f4\u63a5\u548c opencv \u5354\u4f5c\u6a21\u5f0f \n2023/11/4 \n \u767c\u73fe\u7684\u67d0\u4e9b windows \u4f5c\u696d\u7cfb\u7d71\u5982\u679c\u704c \n python3.10 \u642d\u914d \n dlib-19.22.99-cp310-cp310-win_amd64.whl \n \u6703\u7522\u751f\u4e0b\u5217\u932f\u8aa4\uff1a \n from _dlib_pybin11 import * ImportError: DLL load failed: \u627e\u4e0d\u5230\u6307\u5b9a\u7684\u7a0b\u5e8f \n \n \n \u203b\u89e3\u6c7a\u65b9\u6848\uff1a\n \u65b0\u5b89\u88dd\u4e00\u7d44 python3.11(64bit) \n (https://www.python.org/ftp/python/3.11.6/python-3.11.6-amd64.exe) \n \u642d\u914ddlib-19.24.1-cp311-cp311-win_amd64.whl \n ```\n pip install https://github.com/Murtaza-Saeed/dlib/raw/master/dlib-19.24.1-cp311-cp311-win_amd64.whl\n ```\n Thonny\u7684\u4f7f\u7528\u8005\u53ef\u81f3 \u5de5\u5177>>\u9078\u9805>>\u76f4\u8b6f\u5668>... \u4fee\u6539python.exe\u4e4b\u4f4d\u7f6e\uff0c\u8b8a\u6210\u5408\u9069\u7684python\u7248\u672c \n vscode\u7684\u4f7f\u7528\u8005\u53ef\u6309ctrl+shift+p \u65bc\u4e0a\u65b9\u8f38\u5165 >python:Select Interpreter \u9078\u64c7\u5408\u9069\u7684python\u7248\u672c \n \n\t\n\t\n##### Download the samples to 'train' folder(\u4e0b\u8f09\u5404\u7a2e\u7167\u7247\u6a23\u672c\u81f3train\u8cc7\u6599\u593e)\n```\nimport pyFaceTrace as ft \nft.downloadImageSamples() \n```\n##### work with opencv webcam process (detail) \n```\nimport pyFaceTrace as ft\nimport cv2\nfrom PIL import ImageFont\n#\u81f3train\u8cc7\u6599\u593e\u8f09\u5165\u6a23\u672c,\u6b32\u8fa8\u8b58\u4e4b\u76ee\u6a19\u5716\u7247\u53ef\u653e\u5165 train\u8cc7\u6599\u593e\nft.loadDB()\n#\u8a2d\u5b9a\u6587\u5b57\u7269\u4ef6\nFONT = ImageFont.truetype(\"kaiu.ttf\",50,index=0)\n#webcamd \u5f71\u50cf\u8655\u7406\u8ff4\u5708\ncap = cv2.VideoCapture(0,cv2.CAP_DSHOW)\nwhile True:\n ret, img = cap.read()\n if not ret : continue\n #\u53d6\u5f97 img \u4e2d\u6240\u6709\u4eba\u81c9\u4e4b\u77e9\u578b\u5340\u57df\uff0c\u653e\u5165rects\n rects=ft.detector(img,1)\n for rect in rects:\n #\u53d6\u5f97webcam img \u4e2d\u4eba\u81c9\u4e4b\u7279\u5fb5\u5411\u91cf\n fv=ft.getFeatureVector(img,rect)\n #\u5c07\u7279\u5fb5\u5411\u91cf\u548c ft.DB \u4e2d\u4e4b\u4eba\u7279\u5fb5\u5411\u91cf\u505a\u6bd4\u5c0d\uff0c\u627e\u5230\u8ddd\u96e2\u6700\u77ed\u7684(dist)\u7576\u4f5c\u8fa8\u8b58\u7d50\u679c(tag)\n tag,dist = ft.predictFromDB(fv)\n #\u5c07\u8fa8\u8b58\u7d50\u679c\u986f\u793a\u5728 img \u4e0a\n cv2.rectangle(img,(rect.left(),rect.top()),(rect.right(),rect.bottom()),(0,0,255),3)\n img=ft.addText2Img_cv2(img,tag,FONT,position=(rect.left(),rect.top()-FONT.size-1))\n if cv2.waitKey(10) == 27: break\n # \u5c07 img show\u5728\u8996\u7a97\u4e2d\n cv2.imshow('press esc to exit...', img)\ncap.release()\ncv2.destroyAllWindows()\n```\n##### work with opencv webcam process (esay)\n```\nimport pyFaceTrace as ft\nimport cv2\nft.loadDB()\ncap = cv2.VideoCapture(0,cv2.CAP_DSHOW)\nwhile(True): \n ret, img = cap.read()\n if not ret:continue\n #img=cv2.flip(img,1)\n tags,dists,rects,img = ft.predictImage(img) \n cv2.imshow('press esc to exit...', img)\n if cv2.waitKey(10) == 27: break\n \ncap.release()\ncv2.destroyAllWindows()\n```\n### Demo with webcam\n```\nimport pyFaceTrace as ft\nft.loadDB(folder='train')\nft.predictCam()\n```\n##### \u6bd4\u5c0d\u76ee\u524dwebcam\u64f7\u53d6\u5230\u7684\u4eba\u81c9\u548c\u6307\u5b9a\u5f71\u50cf\u6a94\u6848\u4e26\u8a08\u7b97\u5b83\u5011\u4e4b\u9593\u7684\u8ddd\u96e2\n```\nimport pyFaceTrace as ft \nim = ft.captureImageFromCam()\nVTest = ft.getFeatureVector(im)\nVtrain = ft.loadFeatureFromPic('train\\\\\u674e\u570b\u6e90.jpg')\nD=ft.dist(VTest,Vtrain)\nprint('\u8ddd\u96e2=',D)\n```\n##### \u8f09\u5165train\u8cc7\u6599\u593e\u4e2d\u6240\u6709jpg\u6a94\u4e4b\u7279\u5fb5\u53catag\u4e26\u76f4\u63a5\u9810\u6e2c\u76ee\u524dwebcam\u64f7\u53d6\u5230\u7684\u4eba\u81c9\u5c0d\u61c9\u7684TAG \n```\nimport pyFaceTrace as ft\nft.loadDB(folder='train')\nim = ft.captureImageFromCam()\nVTest = ft.getFeatureVector(im)\nresult = ft.predictFromDB(VTest)\nprint(result)\n```\n\n\n\nLicense\n----\n\nMIT",
"bugtrack_url": null,
"license": "",
"summary": "easy Face Recognition for python",
"version": "5.0.7",
"project_urls": {
"Homepage": "https://pypi.org/project/pyFaceTrace"
},
"split_keywords": [
"face recognition",
"face trace"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "824a4b7a5afd2a9705e140d8737879b3f266ef8fa440ba653b2884efcf3315a8",
"md5": "dbb842c78b6ab019f1b64fd78fbaa122",
"sha256": "d62e5d4e21a9e83e972e29b19332e49fc174ce1242faf2e3298bb7f1598ddf16"
},
"downloads": -1,
"filename": "pyFaceTrace-5.0.7.tar.gz",
"has_sig": false,
"md5_digest": "dbb842c78b6ab019f1b64fd78fbaa122",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 12345,
"upload_time": "2023-11-14T15:31:37",
"upload_time_iso_8601": "2023-11-14T15:31:37.629689Z",
"url": "https://files.pythonhosted.org/packages/82/4a/4b7a5afd2a9705e140d8737879b3f266ef8fa440ba653b2884efcf3315a8/pyFaceTrace-5.0.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-11-14 15:31:37",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "pyfacetrace"
}
JSON