公司需要在项目中使用人脸识别SDK,并且对信息安全的要求非常高,在详细了解市场上几个主流人脸识别SDK后,综合来看虹软的Arcface SDK比较符合我们的需求,它提供了免费版本,并且可以在离线环境下使用,这一点非常符合我们对安全性的要求。
但有个遗憾的事情,我们的项目主要使用了Python语言,虹软官方并没有提供Python版本的SDK,因此我自己使用Python封装了Arcface C++ SDK,便于在项目中使用,这里将主要过程写出来供大家探讨下。
1. 环境说明
a. 注意Win64环境的Python必须使用ArcFace C++(Win64) SDK,如果平台不一致, 否则可能会出现以下错误。
-
OSError: [WinError 193] %1 不是有效的 Win32 应用程序
b. 由于SDK中涉及到内存操作,本文使用了ctypes包和cdll包提供的以下几种方式
-
c_ubyte_p = POINTER(c_ubyte) memcpy = cdll.msvcrt.memcpy malloc = cdll.msvcrt.malloc malloc.restype = c_void_p free = cdll.msvcrt.free
2.Arcface SDK基本数据结构封装
在封装数据结构时,一定要注意参数类型,否则可能会导致程序出错。
-
class MRECT(Structure): # 人脸框
-
_fields_ = [(u'left', c_int32),
-
(u'top', c_int32),
-
(u'right', c_int32),
-
(u'bottom', c_int32)] class ASFVersion(Structure): # 版本信息 版本号 构建日期 版权说明
-
_fields_ = [ ('Version', c_char_p),
-
('BuildDate', c_char_p),
-
('CopyRight', c_char_p)] class ASFSingleFaceInfo(Structure): # 单人脸信息 人脸框 人脸角度
-
_fields_ = [ ('faceRect', MRECT),
-
('faceOrient', c_int32)] class ASFMultiFaceInfo(Structure): # 多人脸信息 人脸框数组 人脸角度数组 人脸数
-
_fields_ = [ (u'faceRect', POINTER(MRECT)),
-
(u'faceOrient', POINTER(c_int32)),
-
(u'faceNum', c_int32)] class ASFFaceFeature(Structure): # 人脸特征 人脸特征 人脸特征长度
-
_fields_ = [ ('feature', c_void_p),
-
('featureSize', c_int32)] class ASFFace3DAngle(Structure): # 人脸角度信息
-
_fields_ = [ ('roll', c_void_p),
-
('yaw', c_void_p),
-
('pitch', c_void_p),
-
('status', c_void_p),
-
('num', c_int32)] class ASFAgeInfo(Structure): # 年龄
-
_fields_ = [ (u'ageArray', c_void_p),
-
(u'num', c_int32)] class ASFGenderInfo(Structure): # 性别
-
_fields_ = [ (u'genderArray', c_void_p),
-
(u'num', c_int32)] class ASFLivenessThreshold(Structure): # 活体阈值
-
_fields_ = [ (u'thresholdmodel_BGR', c_float),
-
(u'thresholdmodel_IR', c_int32)] class ASFLivenessInfo(Structure): # 活体信息
-
_fields_ = [ (u'isLive', c_void_p),
-
(u'num', c_int32)]
3.Arcface SDK接口封装
a. 接口封装之前需要加载dll库,Arcface SDK 提供的dll都需要加载。
b. 本文中图片格式使用了ASVL_PAF_RGB24_B8G8R8。
c. 每个接口都需要定义返回值以及参数类型,某些参数类型依赖前文所述的基本数据结构。
-
from arcsoft_face_struct import * from ctypes import * from enum import Enum
-
-
face_dll = CDLL("libarcsoft_face.dll")
-
face_engine_dll = CDLL("libarcsoft_face_engine.dll")
-
-
ASF_DETECT_MODE_VIDEO = 0x00000000
-
ASF_DETECT_MODE_IMAGE = 0xFFFFFFFF ASF_NONE = 0x00000000
-
ASF_FACE_DETECT = 0x00000001 ASF_FACE_RECOGNITION = 0x00000004
-
ASF_AGE = 0x00000008
-
ASF_GENDER = 0x00000010
-
ASF_FACE3DANGLE = 0x00000020
-
ASF_LIVENESS = 0x00000080
-
ASF_IR_LIVENESS = 0x00000400
-
ASVL_PAF_RGB24_B8G8R8 = 0x201
-
-
class ArcSoftFaceOrientPriority(Enum):
-
ASF_OP_0_ONLY = 0x1,
-
ASF_OP_90_ONLY = 0x2,
-
ASF_OP_270_ONLY = 0x3,
-
ASF_OP_180_ONLY = 0x4,
-
ASF_OP_0_HIGHER_EXT = 0x5,
-
-
activate = face_engine_dll.ASFActivation
-
activate.restype = c_int32
-
activate.argtypes = (c_char_p, c_char_p)
-
-
init_engine = face_engine_dll.ASFInitEngine
-
init_engine.restype = c_int32
-
init_engine.argtypes = (c_long, c_int32, c_int32, c_int32, c_int32, POINTER(c_void_p))
-
-
detect_face = face_engine_dll.ASFDetectFaces
-
detect_face.restype = c_int32
-
detect_face.argtypes = (c_void_p, c_int32, c_int32, c_int32, POINTER(c_ubyte), POINTER(ASFMultiFaceInfo))
-
-
extract_feature = face_engine_dll.ASFFaceFeatureExtract
-
extract_feature.restype = c_int32
-
extract_feature.argtypes = (c_void_p, c_int32, c_int32, c_int32, POINTER(c_ubyte),
-
POINTER(ASFSingleFaceInfo), POINTER(ASFFaceFeature))
-
-
compare_feature = face_engine_dll.ASFFaceFeature
-
Compare compare_feature.restype = c_int32
-
compare_feature.argtypes = (c_void_p, POINTER(ASFFaceFeature), POINTER(ASFFaceFeature), POINTER(c_float))
-
-
set_liveness_param = face_engine_dll.ASFSetLivenessParam
-
set_liveness_param.restype = c_int32
-
set_liveness_param.argtypes = (c_void_p, POINTER(ASFLivenessThreshold))
-
-
process = face_engine_dll.ASFProcess process.restype =
-
c_int32 process.argtypes = (c_void_p, c_int32, c_int32, c_int32, POINTER(c_ubyte),
-
POINTER(ASFMultiFaceInfo), c_int32)
-
-
get_age = face_engine_dll.ASFGetAge
-
get_age.restype = c_int32
-
get_age.argtypes = (c_void_p, POINTER(ASFAgeInfo))
-
-
get_gender = face_engine_dll.ASFGetGender
-
get_gender.restype = c_int32
-
get_gender.argtypes = (c_void_p, POINTER(ASFGenderInfo))
-
-
get_3d_angle = face_engine_dll.ASFGetFace3DAngle
-
get_3d_angle.restype = c_int32
-
get_3d_angle.argtypes = (c_void_p, POINTER(ASFFace3DAngle))
-
-
get_liveness_info = face_engine_dll.ASFGetLivenessScore
-
get_liveness_info.restype = c_int32
-
get_liveness_info.argtypes = (c_void_p, POINTER(ASFLivenessInfo))
4.封装接口调用
接下来按照下面的流程图介绍接口调用(此图使用 Microsoft Visio 2016自动生成)。
下图是按照此流程处理得到的效果图,由于画面有限,只显示了年龄、性别、活体信息。
a. 激活
需要注意app_id和sdk_key需要使用字节类型。
-
app_id = b""
-
sdk_key = b""
-
ret = arcsoft_face_func.activate(app_id, sdk_key) # 激活
-
if ret == 0 or ret == 90114:
-
print("激活成功")
-
else:
-
print("激活失败:", ret)
b. 初始化
初始化需要将所有需要的功能参数一次性传入,本文使用了人脸检测、特征提取等功能。
-
mask = arcsoft_face_func.ASF_FACE_DETECT | \
-
arcsoft_face_func.ASF_FACE_RECOGNITION | \
-
arcsoft_face_func.ASF_AGE | \
-
arcsoft_face_func.ASF_GENDER | \
-
arcsoft_face_func.ASF_FACE3DANGLE |\
-
arcsoft_face_func.ASF_LIVENESS
-
-
engine = c_void_p()
-
ret = arcsoft_face_func.init_engine(arcsoft_face_func.ASF_DETECT_MODE_IMAGE,
-
arcsoft_face_func.ArcSoftFaceOrientPriority.ASF_OP_0_ONLY.value[0],
-
30, 10, mask, byref(engine))
-
if ret == 0:
-
print("初始化成功")
-
else:
-
print("初始化失败:", ret)
c. 人脸检测
本文使用了opencv读图,兼容性更好,并且自定义的数据结构记录图片信息,注意 ArcFace C++ SDK 要求传入的图像宽度需要是4的倍数,下面做了裁剪。
-
class Image:
-
def __init__(self):
-
self.width = 0
-
self.height = 0
-
self.imageData = None
-
-
def load_image(file_path):
-
img = cv2.imread(file_path)
-
sp = img.shape
-
img = cv2.resize(img, (sp[1]//4*4, sp[0]))# 四字节对齐
-
-
image = Image()
-
image.width = img.shape[1]
-
image.height = img.shape[0]
-
image.imageData = img
-
return image
-
###################### 人脸检测 ##################################
-
-
image1 = load_image(r"1.jpg")
-
image_bytes = bytes(image1.imageData)
-
image_ubytes = cast(image_bytes, c_ubyte_p)
-
-
detect_faces = ASFMultiFaceInfo()
-
ret = arcsoft_face_func.detect_face(
-
engine,
-
image1.width,
-
image1.height,
-
arcsoft_face_func.ASVL_PAF_RGB24_B8G8R8,
-
image_ubytes,
-
byref(detect_faces)
-
)
-
-
if ret == 0:
-
print("检测人脸成功")
-
else:
-
print("检测人脸失败:", ret)
d. 特征提取
特征提取只支持单人脸,因此做了人脸处理操作,并且需要及时将提取的人脸特征拷贝一份,否则会被覆盖。
-
single_face1 = ASFSingleFaceInfo()
-
single_face1.faceRect = detect_faces.faceRect[0]
-
single_face1.faceOrient = detect_faces.faceOrient[0]
-
-
face_feature = ASFFaceFeature()
-
ret = arcsoft_face_func.extract_feature(
-
engine,
-
image1.width,
-
image1.height,
-
arcsoft_face_func.ASVL_PAF_RGB24_B8G8R8,
-
image_ubytes,
-
single_face1,
-
byref(face_feature)
-
)
-
-
if ret == 0:
-
print("提取特征1成功")
-
else:
-
print("提取特征1失败:", ret)
-
-
feature1 = ASFFaceFeature()
-
feature1.featureSize = face_feature.featureSize
-
feature1.feature = malloc(feature1.featureSize)
-
memcpy(c_void_p(feature1.feature),
-
c_void_p(face_feature.feature),
-
feature1.featureSize)
e. 特征比对
按照前文所述再提取一张人脸的特征,即可以进行下面的人脸特征比对操作
-
compare_threshold = c_float()
-
ret = arcsoft_face_func.compare_feature(
-
engine, feature1, feature2, compare_threshold
-
)
-
-
free(c_void_p(feature1.feature))
-
free(c_void_p(feature2.feature))
-
-
if ret == 0:
-
print("特征比对成功,相似度:", compare_threshold.value)
-
else:
-
print("特征比对失败:", ret)
f. 年龄、性别、3D Angle
process接口目前提供了 年龄、性别、3D Angle、活体检测, 但年龄、性别、3D Angle支持多人脸,而活体只支持单人脸,因此下面分别处理。
-
process_mask = arcsoft_face_func.ASF_AGE | \
-
arcsoft_face_func.ASF_GENDER | \
-
arcsoft_face_func.ASF_FACE3DANGLE
-
-
ret = arcsoft_face_func.process(
-
engine,
-
image1.width,
-
image1.height,
-
arcsoft_face_func.ASVL_PAF_RGB24_B8G8R8,
-
image_ubytes,
-
byref(detect_faces),
-
c_int32(process_mask)
-
)
-
-
if ret == 0:
-
print("process成功")
-
else:
-
print("process失败:", ret)
-
######################## Age ################################
-
-
age_info = ASFAgeInfo()
-
ret = arcsoft_face_func.get_age(engine, byref(age_info))
-
-
if ret == 0:
-
print("get_age 成功")
-
age_ptr = cast(age_info.ageArray, POINTER(c_int))
-
for i in range(age_info.num):
-
print("face", i, "age:", age_ptr[i])
-
else:
-
print("get_age 失败:", ret)
-
-
####################### Gender #################################
-
-
gender_info = ASFGenderInfo()
-
ret = arcsoft_face_func.get_gender(engine, byref(gender_info))
-
-
if ret == 0:
-
print("get_gender 成功")
-
gender_ptr = cast(gender_info.genderArray, POINTER(c_int))
-
for i in range(gender_info.num):
-
print("face", i, "gender:",
-
"女性" if (gender_ptr[i] == 1) else (
-
"男性" if (gender_ptr[i] == 0) else "未知"
-
))
-
else:
-
print("get_gender 失败:", ret)
-
-
####################### 3D Angle #################################
-
-
angle_info = ASFFace3DAngle()
-
ret = arcsoft_face_func.get_3d_angle(engine, byref(angle_info))
-
-
if ret == 0:
-
print("get_3d_angle 成功")
-
roll_ptr = cast(angle_info.roll, POINTER(c_float))
-
yaw_ptr = cast(angle_info.yaw, POINTER(c_float))
-
pitch_ptr = cast(angle_info.pitch, POINTER(c_float))
-
status_ptr = cast(angle_info.status, POINTER(c_int32))
-
for i in range(angle_info.num):
-
print("face", i,
-
"roll:", roll_ptr[i],
-
"yaw:", yaw_ptr[i],
-
"pitch:", pitch_ptr[i],
-
"status:", "正常" if status_ptr[i] == 0 else "出错")
-
-
else:
-
print("get_3d_angle 失败:", ret)
g. RGB活体
在活体检测之前建议按照实际场景设置活体阈值,不设置即使用默认阈值,这里设置了RGB活体的阈值为0.75。并将检测的多人脸分别转为单张人脸的参数传到接口中。
-
######################### 活体阈值设置 ###############################
-
threshold_param = ASFLivenessThreshold()
-
threshold_param.thresholdmodel_BGR = 0.75
-
ret = arcsoft_face_func.set_liveness_param(engine,threshold_param)
-
-
if ret == 0:
-
print("set_liveness_param成功")
-
else:
-
print("set_liveness_param 失败:", ret)
-
-
temp_face_info = ASFMultiFaceInfo()
-
temp_face_info.faceNum = 1
-
LP_MRECT = POINTER(MRECT)
-
temp_face_info.faceRect = LP_MRECT(MRECT(malloc(sizeof(MRECT))))
-
LP_c_long = POINTER(c_long)
-
temp_face_info.faceOrient = LP_c_long(c_long(malloc(sizeof(c_long))))
-
-
for i in range(detect_faces.faceNum):
-
temp_face_info.faceRect[0] = detect_faces.faceRect[i]
-
temp_face_info.faceOrient[0] = detect_faces.faceOrient[i]
-
-
ret = arcsoft_face_func.process(
-
engine,
-
image1.width,
-
image1.height,
-
arcsoft_face_func.ASVL_PAF_RGB24_B8G8R8,
-
image_ubytes,
-
byref(temp_face_info),
-
c_int32(arcsoft_face_func.ASF_LIVENESS)
-
)
-
-
if ret == 0:
-
print("process成功")
-
else:
-
print("process失败:", ret)
-
## RGB活体检测
-
ret = arcsoft_face_func.process(
-
engine,
-
image1.width,
-
image1.height,
-
arcsoft_face_func.ASVL_PAF_RGB24_B8G8R8,
-
image_ubytes,
-
byref(temp_face_info),
-
c_int32(arcsoft_face_func.ASF_LIVENESS)
-
)
-
-
if ret == 0:
-
print("process成功")
-
else:
-
print("process失败:", ret)
-
-
liveness_info = ASFLivenessInfo()
-
ret = arcsoft_face_func.get_liveness_info(engine, byref(liveness_info))
-
-
if ret == 0:
-
print("get_liveness_info 成功")
-
liveness_ptr = cast(liveness_info.isLive, POINTER(c_int))
-
print("face", i, "liveness:",
-
"非真人" if (liveness_ptr[0] == 0) else (
-
"真人" if (liveness_ptr[0] == 1) else (
-
"不确定" if (liveness_ptr[0] == -1) else (
-
"传入人脸数>1" if (liveness_ptr[0] == -2) else
-
(liveness_ptr[0])
-
)
-
)
-
))
-
else:
-
print("get_liveness_info 失败:", ret)
最后,欢迎大家指教哦~
推荐你们了解虹软人脸识别SDK~
虹软人脸识别开放平台