# API-work
**Repository Path**: he_lai/api-work
## Basic Information
- **Project Name**: API-work
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: ISC
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-10-23
- **Last Updated**: 2020-12-19
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# API-work
# API 作业-1
* [一、人脸识别](#face)
* [二、计算机视觉](#vision)
* [三、学习心得](#learn)
---
一、人脸识别
### Azure
参考：[Azure 人脸识别文档](https://docs.microsoft.com/zh-cn/rest/api/cognitiveservices/face/facelist/create)
- Face Detect
```python
# A-1 面部检测
import requests
import json
# set to your own subscription key value
subscription_key = 'aa3f3860bc894397a5018c908cbb79ff'
assert subscription_key
# replace with the string from your endpoint URL
face_api_url = 'https://api-hr.cognitiveservices.azure.com/face/v1.0/detect'
# 请求正文body
image_url = 'https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603820202732&di=86272f613bbc0793a37c8afcabc088df&imgtype=0&src=http%3A%2F%2Fc-ssl.duitang.com%2Fuploads%2Fitem%2F202007%2F30%2F20200730175754_rhdsN.thumb.200_200_c.jpeg'
headers = {'Ocp-Apim-Subscription-Key': subscription_key}
# 请求参数parameters
params = {
'returnFaceId': 'true',
'returnFaceLandmarks': 'false',
# 可选参数,请仔细阅读API文档
'returnFaceAttributes': 'age,gender,headPose,smile,facialHair,glasses,emotion,hair,makeup,occlusion,accessories,blur,exposure,noise',
}
response = requests.post(face_api_url, params=params,
headers=headers, json={"url": image_url})
# json.dumps 将json--->bytes
response
# 返回状态码
```
```python
# bytes or string 编码不同 ***** encoding ="utf-8"
# response.text
# response.content
results = response.json()
results
[{'faceId': 'bf345c8a-376d-473a-8f57-75e0699ea576',
'faceRectangle': {'top': 40, 'left': 74, 'width': 58, 'height': 58},
'faceAttributes': {'smile': 0.604,
'headPose': {'pitch': 0.7, 'roll': 4.8, 'yaw': 14.9},
'gender': 'female',
'age': 23.0,
'facialHair': {'moustache': 0.0, 'beard': 0.0, 'sideburns': 0.0},
'glasses': 'NoGlasses',
'emotion': {'anger': 0.0,
'contempt': 0.003,
'disgust': 0.0,
'fear': 0.0,
'happiness': 0.604,
'neutral': 0.392,
'sadness': 0.001,
'surprise': 0.0},
'blur': {'blurLevel': 'low', 'value': 0.0},
'exposure': {'exposureLevel': 'goodExposure', 'value': 0.75},
'noise': {'noiseLevel': 'medium', 'value': 0.4},
'makeup': {'eyeMakeup': True, 'lipMakeup': True},
'accessories': [],
'occlusion': {'foreheadOccluded': False,
'eyeOccluded': False,
'mouthOccluded': False},
'hair': {'bald': 0.09,
'invisible': False,
'hairColor': [{'color': 'brown', 'confidence': 0.9},
{'color': 'red', 'confidence': 0.85},
{'color': 'other', 'confidence': 0.54},
{'color': 'black', 'confidence': 0.42},
{'color': 'blond', 'confidence': 0.31},
{'color': 'gray', 'confidence': 0.05},
{'color': 'white', 'confidence': 0.0}]}}}]
```
```python
# A-2 json转译
results = response.json()
results
[{'faceId': 'bf345c8a-376d-473a-8f57-75e0699ea576',
'faceRectangle': {'top': 40, 'left': 74, 'width': 58, 'height': 58},
'faceAttributes': {'smile': 0.604,
'headPose': {'pitch': 0.7, 'roll': 4.8, 'yaw': 14.9},
'gender': 'female',
'age': 23.0,
'facialHair': {'moustache': 0.0, 'beard': 0.0, 'sideburns': 0.0},
'glasses': 'NoGlasses',
'emotion': {'anger': 0.0,
'contempt': 0.003,
'disgust': 0.0,
'fear': 0.0,
'happiness': 0.604,
'neutral': 0.392,
'sadness': 0.001,
'surprise': 0.0},
'blur': {'blurLevel': 'low', 'value': 0.0},
'exposure': {'exposureLevel': 'goodExposure', 'value': 0.75},
'noise': {'noiseLevel': 'medium', 'value': 0.4},
'makeup': {'eyeMakeup': True, 'lipMakeup': True},
'accessories': [],
'occlusion': {'foreheadOccluded': False,
'eyeOccluded': False,
'mouthOccluded': False},
'hair': {'bald': 0.09,
'invisible': False,
'hairColor': [{'color': 'brown', 'confidence': 0.9},
{'color': 'red', 'confidence': 0.85},
{'color': 'other', 'confidence': 0.54},
{'color': 'black', 'confidence': 0.42},
{'color': 'blond', 'confidence': 0.31},
{'color': 'gray', 'confidence': 0.05},
{'color': 'white', 'confidence': 0.0}]}}}]
```
```python
# A-3 pandas数据表格化
import pandas as pd
df_face = pd.json_normalize(results)
df_face
```
|faceId|faceRectangle.top|faceRectangle.left|faceRectangle.width|faceRectangle.height|faceAttributes.smile|faceAttributes.headPose.pitch|faceAttributes.headPose.roll|faceAttributes.headPose.yaw|faceAttributes.gender|...|faceAttributes.noise.value|faceAttributes.makeup.eyeMakeup|faceAttributes.makeup.lipMakeup|faceAttributes.accessories|faceAttributes.occlusion.foreheadOccluded|faceAttributes.occlusion.eyeOccluded|faceAttributes.occlusion.mouthOccluded|faceAttributes.hair.bald|faceAttributes.hair.invisible|faceAttributes.hair.hairColor|
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|bf345c8a-376d-473a-8f57-75e0699ea576|40|74|58|58|0.604|0.7|4.8|14.9|female|...|0.4|True|True|[]|0.0|False|False|False|0.09|False|[{'color': 'brown', 'confidence': 0.9}, {'colo...|
```
1 rows × 38 columns
```
- FaceList & Find Similar
```python
import requests
# 1.创建人脸列表
faceListId = "list_004" # 设置人脸列表ID
create_facelists_url ="https://api-hjq.cognitiveservices.azure.com/face/v1.0/facelists/{}" # URL（见API文档）
subscription_key ="aa3f3860bc894397a5018c908cbb79ff" # 密钥
# 请求头
headers = {
'Content-Type': 'application/json',
'Ocp-Apim-Subscription-Key': subscription_key,
}
# 相关信息及识别模型的选用
data = {
"name": "sample_list",
"userData": "相册",
"recognitionModel": "recognition_03"
}
# 发送请求
r_create = requests.put(create_facelists_url.format(faceListId), headers=headers, json=data)
r_create.content
# b''
# 创建成功
# 2.添加人脸
add_face_url ="https://api-hjq.cognitiveservices.azure.com/face/v1.0/facelists/{}/persistedfaces"
assert subscription_key
headers = {
'Content-Type': 'application/json',
'Ocp-Apim-Subscription-Key': subscription_key,
}
# 人脸相片地址
img_url ="https://ss2.bdstatic.com/70cFvnSh_Q1YnxGkpoWK1HF6hhy/it/u=781918665,2083273991&fm=26&gp=0.jpg"
# 人脸数据
params_add_face={
"userData":"joy"
}
# 发送请求
r_add_face = requests.post(add_face_url.format(faceListId),headers=headers,params=params_add_face,json={"url":img_url})
r_add_face.status_code
# 200
r_add_face.json() # 返回persistedFaceId
# {'persistedFaceId': '33bc32bc-2ffe-486f-9ee8-a86837911f50'}
# 封装成函数方便添加图片
def AddFace(img_url=str,userData=str):
add_face_url ="https://api-hjq.cognitiveservices.azure.com/face/v1.0/facelists/{}/persistedFaces"
assert subscription_key
headers = {
# Request headers
'Content-Type': 'application/json',
'Ocp-Apim-Subscription-Key': subscription_key,
}
img_url = img_url
params_add_face={
"userData":userData
}
r_add_face = requests.post(add_face_url.format(faceListId),headers=headers,params=params_add_face,json={"url":img_url})
return r_add_face.status_code #返回出状态码
AddFace("http://huangjieqi.gitee.io/picture_storage/Autumnhui.jpg","丘天惠")
AddFace("http://huangjieqi.gitee.io/picture_storage/L-Tony-info.jpg","林嘉茵")
AddFace("http://huangjieqi.gitee.io/picture_storage/TLINGP.jpg","汤玲萍")
AddFace("http://huangjieqi.gitee.io/picture_storage/WenYanZeng.jpg","曾雯燕")
AddFace("http://huangjieqi.gitee.io/picture_storage/XIEIC.jpg","谢依希")
AddFace("http://huangjieqi.gitee.io/picture_storage/YuecongYang.png","杨悦聪")
AddFace("http://huangjieqi.gitee.io/picture_storage/Zoezhouyu.jpg","周雨")
AddFace("http://huangjieqi.gitee.io/picture_storage/crayon-heimi.jpg","刘瑜鹏")
AddFace("http://huangjieqi.gitee.io/picture_storage/jiayichen.jpg","陈嘉仪")
AddFace("http://huangjieqi.gitee.io/picture_storage/kg2000.jpg","徐旖芊")
AddFace("http://huangjieqi.gitee.io/picture_storage/liuxinrujiayou.jpg","刘心如")
AddFace("http://huangjieqi.gitee.io/picture_storage/liuyu19.png","刘宇")
AddFace("http://huangjieqi.gitee.io/picture_storage/ltco.jpg","李婷")
AddFace("http://huangjieqi.gitee.io/picture_storage/lucaszy.jpg","黄智毅")
AddFace("http://huangjieqi.gitee.io/picture_storage/pingzi0211.jpg","黄慧文")
AddFace("http://huangjieqi.gitee.io/picture_storage/shmimy-cn.jpg","张铭睿")
AddFace("http://huangjieqi.gitee.io/picture_storage/yichenting.jpg","陈婷")
AddFace("http://huangjieqi.gitee.io/picture_storage/coco022.jpg","洪可凡")
AddFace("http://huangjieqi.gitee.io/picture_storage/lujizhi.png","卢继志")
AddFace("http://huangjieqi.gitee.io/picture_storage/zzlhyy.jpg","张梓乐")
# 3.检测人脸
face_api_url = 'https://api-hjq.cognitiveservices.azure.com/face/v1.0/detect'
image_url = 'https://ss2.bdstatic.com/70cFvnSh_Q1YnxGkpoWK1HF6hhy/it/u=781918665,2083273991&fm=26&gp=0.jpg'
headers = {'Ocp-Apim-Subscription-Key': subscription_key}
# 请求参数
params = {
'returnFaceId': 'true',
'returnFaceLandmarks': 'false',
# 选择模型
'recognitionModel':'recognition_03',#此参数需与facelist参数一致
'detectionModel':'detection_01',
# 可选参数,请仔细阅读API文档
'returnFaceAttributes': 'age,gender,headPose,smile,facialHair,glasses,emotion,hair,makeup,occlusion,accessories,blur,exposure,noise',
}
response = requests.post(face_api_url, params=params,headers=headers, json={"url": image_url})
response.json()
# 4.返回人脸相似置信度
findsimilars_url = "https://api-hjq.cognitiveservices.azure.com/face/v1.0/findsimilars"
# 请求正文 faceID需要先检测一张照片获取
data_findsimilars = {
"faceId":"e5a9b7a6-8d5e-4b81-829c-1ba94a853e52", #取上方的faceID
"faceListId": "list_003",
"maxNumOfCandidatesReturned": 10,
"mode": "matchFace" #matchPerson #一种为验证模式，一种为相似值模式
}
r_findsimilars = requests.post(findsimilars_url,headers=headers,json=data_findsimilars)
r_findsimilars.json()
# 查看列表
get_facelist_url = "https://api-hjq.cognitiveservices.azure.com/face/v1.0/facelists/{}"
r_get_facelist = requests.get(get_facelist_url.format(faceListId),headers=headers)
r_get_facelist.json()
# 用Pandas简化数据
import pandas as pd
# 返回facelist数据
adf = pd.json_normalize(r_get_facelist.json()["persistedFaces"])
adf
# 返回相似度数据
bdf = pd.json_normalize(r_findsimilars.json())# 升级pandas才能运行
bdf
#合并
pd.merge(adf, bdf,how='inner', on='persistedFaceId').sort_values(by="confidence",ascending = False)
# 5.删除人脸/人脸列表
faceListId = "list_004" # 需要删除的人脸列表
# 删除列表内人脸
delete_face_url = "https://api-hjq.cognitiveservices.azure.com/face/v1.0/facelists/{}/persistedfaces/{}"
assert subscription_key
# 获取上面的persistedFaceId
persistedFaceId = r_add_face.json()["persistedFaceId"]
headers = {
'Content-Type': 'application/json',
'Ocp-Apim-Subscription-Key': subscription_key,
}
# 注意requests请求为delete
r_delete_face = requests.delete(delete_face_url.format(faceListId,persistedFaceId),headers=headers)
# 删除人脸列表
delete_facelist_url = "https://api-hjq.cognitiveservices.azure.com/face/v1.0/facelists/{}"
assert subscription_key
headers = {
'Content-Type': 'application/json',
'Ocp-Apim-Subscription-Key': subscription_key,
}
r_delete_facelist = requests.delete(delete_facelist_url.format(faceListId),headers=headers)
```
### Face++
参考：[Face++ 人脸识别文档](https://console.faceplusplus.com.cn/documents/4888391)
- Face Detect
### 1.导入模块
```python
import requests
import json
```
### 2.输入face++官网给的api_secret和api_key
```python
api_secret = "vGEgDqiSEbiPlcEx0ggY8TP9Ch_7n0lh"
api_key = '_fV9pDujMV301iO8z0PP7tMpPulyCaMl'
```
### 3.detect face 添加一张人脸的图片，检测人脸
```python
api_url = "https://api-cn.faceplusplus.com/facepp/v3/detect"
img_url = "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603534564342&di=64a2b527aed7e83ff904f01950b22940&imgtype=0&src=http%3A%2F%2Fc-ssl.duitang.com%2Fuploads%2Fitem%2F201911%2F17%2F20191117195100_vtwef.thumb.400_0.jpg"
headers = {
'Content-Type': 'application/json',
}
payload = {
"image_url":img_url,
'api_key': api_key,
'api_secret': api_secret,
'return_attributes':'gender,age,smiling,emotion',
}
r = requests.post(api_url, params=payload, headers=headers)
r.status_code
200 # 返回状态码
```
```python
# 返回人脸信息
results = r.json()
results
{'request_id': '1603524562,9c3d0b36-e7f2-419f-a547-1599ff3a9bde',
'time_used': 278,
'faces': [{'face_token': '1d5d6cc2613425ddf461fc23971f5397',
'face_rectangle': {'top': 70, 'left': 137, 'width': 178, 'height': 178},
'attributes': {'gender': {'value': 'Female'},
'age': {'value': 23},
'smile': {'value': 0.0, 'threshold': 50.0},
'emotion': {'anger': 0.013,
'disgust': 0.016,
'fear': 0.013,
'happiness': 0.117,
'neutral': 81.228,
'sadness': 12.424,
'surprise': 6.188}}}],
'image_id': '5ECQAfB52+R8LP4JjiSNNw==',
'face_num': 1}
```
### 4.compare face 创建一个人脸的集合，存储人脸标识face_token一个FaceSet能够存储10000个face_token。
```python
api_secret = "vGEgDqiSEbiPlcEx0ggY8TP9Ch_7n0lh"
api_key = '_fV9pDujMV301iO8z0PP7tMpPulyCaMl'
display_name = "相册" # 人脸集合的名字
outer_id = "zhaolusi" # 账号下全局唯一的FaceSet自定义标识，可以用来管理 FaceSet 对象。
api_url = "https://api-cn.faceplusplus.com/facepp/v3/faceset/create"
payload = {
# 请求参数
'api_key': api_key,
'api_secret': api_secret,
'display_name':display_name,
'outer_id':outer_id,
}
r = requests.post(api_url, params=payload)
r.json()
# 返回人脸集合中的信息
{'faceset_token': 'e928099b1defddbf8f0f4bc7fb1bd3e8',
'time_used': 184,
'face_count': 0,
'face_added': 0,
'request_id': '1603524720,e6fdd753-9972-4ea0-a0ec-36fd8e457e24',
'outer_id': 'zhaolusi',
'failure_detail': []}
```
### 5.FaceSet GetDetail 获取一个FaceSet的所有信息，包括此FaceSet的faceset_token,outer_id,display_name的信息，以及此FaceSet中存放的face_token数量与列表。
```python
api_url = "https://api-cn.faceplusplus.com/facepp/v3/faceset/getdetail"
payload = {
'api_key': api_key,
'api_secret': api_secret,
'outer_id':outer_id,
}
r = requests.post(api_url,params=payload)
r.json()
# 返回信息
{'faceset_token': 'e928099b1defddbf8f0f4bc7fb1bd3e8',
'tags': '',
'time_used': 95,
'user_data': '',
'display_name': '相册',
'face_tokens': [],
'face_count': 0,
'request_id': '1603524748,e936253a-b884-4c85-922e-39fbb517bd26',
'outer_id': 'zhaolusi'}
```
### 6.FaceSet AddFace 为已经创建好的FaceSet添加人脸标识face_token.
```python
api_url = " https://api-cn.faceplusplus.com/facepp/v3/faceset/addface"
payload = {
'api_key': api_key,
'api_secret': api_secret,
'faceset_token':'e928099b1defddbf8f0f4bc7fb1bd3e8',
'face_tokens':'1d5d6cc2613425ddf461fc23971f5397',
}
r = requests.post(api_url,params=payload)
r.json()
{'faceset_token': 'e928099b1defddbf8f0f4bc7fb1bd3e8',
'time_used': 674,
'face_count': 1,
'face_added': 1,
'request_id': '1603524919,dba413a0-6d56-43ed-9f31-3e37d9beac8c',
'outer_id': 'zhaolusi',
'failure_detail': []}
```
### 7.FaceSet RemoveFace 移除一个FaceSet中的某些或者全部face_token
```python
api_url = "https://api-cn.faceplusplus.com/facepp/v3/faceset/removeface"
payload = {
'api_key': api_key,
'api_secret': api_secret,
'faceset_token':'e928099b1defddbf8f0f4bc7fb1bd3e8',
'face_tokens':'1d5d6cc2613425ddf461fc23971f5397',
}
r = requests.post(api_url,params=payload)
r.json()
{'faceset_token': 'e928099b1defddbf8f0f4bc7fb1bd3e8',
'face_removed': 1,
'time_used': 201,
'face_count': 0,
'request_id': '1603525024,628ce3e6-c789-4ebe-bd3b-b40933d74df0',
'outer_id': 'zhaolusi',
'failure_detail': []}
```
### 8.FaceSet Update 更新人脸集合的属性
```python
api_url = "https://api-cn.faceplusplus.com/facepp/v3/faceset/update"
payload = {
'api_key': api_key,
'api_secret': api_secret,
'faceset_token':'e928099b1defddbf8f0f4bc7fb1bd3e8',
'display_name':"相册",
}
r = requests.post(api_url,params=payload)
r.json()
{'faceset_token': 'e928099b1defddbf8f0f4bc7fb1bd3e8',
'request_id': '1603525060,139c0bb5-e6b6-47d6-a380-1e7e5f50cdf2',
'time_used': 72,
'outer_id': 'zhaolusi'}
```
### 9.1检测两张需要对比的人脸，获得face_token
```python
api_secret = "vGEgDqiSEbiPlcEx0ggY8TP9Ch_7n0lh"
api_key = '_fV9pDujMV301iO8z0PP7tMpPulyCaMl'
api_url = "https://api-cn.faceplusplus.com/facepp/v3/detect"
zrn = "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603535266559&di=6f8b88ca1a5cedb6eced6ac4385d8a7a&imgtype=0&src=http%3A%2F%2Fc-ssl.duitang.com%2Fuploads%2Fblog%2F202009%2F18%2F20200918231607_8d90a.thumb.1000_0.jpg"
headers = {
'Content-Type': 'application/json',
}
payload = {
"image_url":zrn,
'api_key': api_key,
'api_secret': api_secret,
'return_attributes':'gender,age,smiling,emotion',
}
r = requests.post(api_url, params=payload, headers=headers)
r.status_code
200
results = r.json()
results
{'request_id': '1603525219,de0b42f9-6cb2-4410-b4fc-3ae96013919b',
'time_used': 391,
'faces': [{'face_token': 'c18006563b4aea01921f741820576f37',
'face_rectangle': {'top': 195, 'left': 329, 'width': 334, 'height': 334},
'attributes': {'gender': {'value': 'Female'},
'age': {'value': 32},
'smile': {'value': 0.092, 'threshold': 50.0},
'emotion': {'anger': 0.006,
'disgust': 0.022,
'fear': 0.006,
'happiness': 0.447,
'neutral': 96.478,
'sadness': 0.042,
'surprise': 2.999}}}],
'image_id': 'ylMBdvtY/tw4R/STQQXCUw==',
'face_num': 1}
```
### 9.2 第二张人脸图片
```python
api_secret = "vGEgDqiSEbiPlcEx0ggY8TP9Ch_7n0lh"
api_key = '_fV9pDujMV301iO8z0PP7tMpPulyCaMl'
api_url = "https://api-cn.faceplusplus.com/facepp/v3/detect"
zls = "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603535396449&di=57c3051fe091fe0e8dd82f191efbc9f7&imgtype=0&src=http%3A%2F%2Fimgsa.baidu.com%2Fbaike%2Fpic%2Fitem%2F267f9e2f07082838da47ac79b799a9014c08f111.jpg"
headers = {
'Content-Type': 'application/json',
}
payload = {
"image_url":zls,
'api_key': api_key,
'api_secret': api_secret,
'return_attributes':'gender,age,smiling,emotion',
}
r = requests.post(api_url, params=payload, headers=headers)
r.status_code
200
results = r.json()
results
{'request_id': '1603525363,a67648bb-fdc9-4dcc-8b7e-8abba4c5c5ba',
'time_used': 673,
'faces': [{'face_token': '5118fbc4f0cf6cd435fa30da8a7a9f1c',
'face_rectangle': {'top': 178, 'left': 503, 'width': 464, 'height': 464},
'attributes': {'gender': {'value': 'Female'},
'age': {'value': 22},
'smile': {'value': 96.212, 'threshold': 50.0},
'emotion': {'anger': 0.008,
'disgust': 0.008,
'fear': 0.018,
'happiness': 95.569,
'neutral': 4.263,
'sadness': 0.123,
'surprise': 0.011}}}],
'image_id': 'v0yGX9B9xjPnyVRNLDe/QQ==',
'face_num': 1}
```
### 10.Compare Face 将两个人脸进行比对，来判断是否为同一个人，返回比对结果置信度和不同误识率下的阈值.
```python
api_secret = "vGEgDqiSEbiPlcEx0ggY8TP9Ch_7n0lh"
api_key = '_fV9pDujMV301iO8z0PP7tMpPulyCaMl'
api_url = "https://api-cn.faceplusplus.com/facepp/v3/compare"
zls = '5118fbc4f0cf6cd435fa30da8a7a9f1c'
zrn = 'c18006563b4aea01921f741820576f37'
# 第二张人脸图片的url
payload ={
'api_key': api_key,
'api_secret': api_secret,
'face_token1': zls,
'face_token2': zrn
}
r = requests.post(api_url,params=payload)
r.json()
{'confidence': 38.645, #相似度值
'request_id': '1603525513,07aa8924-0bd5-4880-a9a7-3ad3c6ab142f',
'time_used': 435,
'thresholds': {'1e-3': 62.327, '1e-5': 73.975, '1e-4': 69.101}}
```
### 百度智能云
参考：[百度智能云人脸识别文档](https://ai.baidu.com/ai-doc/FACE/yk37c1u4t)
#### 1. 导入模块，输入百度官网给出的API Key和Secret Key
```python
import requests
# client_id 为官网获取的APIKey，client_secret为官网获取的Secret Key
host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={}&client_secret={}'
client_id = "8YIS4b9PawXz9wjniTDeh5HZ"
client_secret = "1cnF87p0NyYVLMmWxgfhrxHMkifu0p9k"
response = requests.get(host.format(client_id, client_secret))
if response:
print(response.json())
# 返回结果
{'refresh_token': '25.02463672e95e9a83036c81a4e593b3da.315360000.1918886256.282335-22869548', 'expires_in': 2592000, 'session_key': '9mzdD0L28bUFiyArrlppYZMTJFthzMUcxkTBEXWa0Xx5rNYE0+XNK6y6BhP+rWrJy9Q1ozE5+OT+MCeV8zwfFWt2JgXPMQ==', 'access_token': '24.4fccd940570684564d194d9fd1bd92e4.2592000.1606118256.282335-22869548', 'scope': 'public brain_all_scope vis-faceverify_faceverify_h5-face-liveness vis-faceverify_FACE_V3 vis-faceverify_idl_face_merge vis-faceverify_FACE_EFFECT vis-faceverify_face_feature_sdk wise_adapt lebo_resource_base lightservice_public hetu_basic lightcms_map_poi kaidian_kaidian ApsMisTest_Test权限 vis-classify_flower lpq_开放 cop_helloScope ApsMis_fangdi_permission smartapp_snsapi_base smartapp_mapp_dev_manage iop_autocar oauth_tp_app smartapp_smart_game_openapi oauth_sessionkey smartapp_swanid_verify smartapp_opensource_openapi smartapp_opensource_recapi fake_face_detect_开放Scope vis-ocr_虚拟人物助理 idl-video_虚拟人物助理 smartapp_component', 'session_secret': '01fed1bf12ccb01d24a4a57b1afac680'}
```
```python
# (让它排列得整齐一点)
results = response.json()
results
{'refresh_token': '25.02463672e95e9a83036c81a4e593b3da.315360000.1918886256.282335-22869548',
'expires_in': 2592000,
'session_key': '9mzdD0L28bUFiyArrlppYZMTJFthzMUcxkTBEXWa0Xx5rNYE0+XNK6y6BhP+rWrJy9Q1ozE5+OT+MCeV8zwfFWt2JgXPMQ==',
'access_token': '24.4fccd940570684564d194d9fd1bd92e4.2592000.1606118256.282335-22869548',
'scope': 'public brain_all_scope vis-faceverify_faceverify_h5-face-liveness vis-faceverify_FACE_V3 vis-faceverify_idl_face_merge vis-faceverify_FACE_EFFECT vis-faceverify_face_feature_sdk wise_adapt lebo_resource_base lightservice_public hetu_basic lightcms_map_poi kaidian_kaidian ApsMisTest_Test权限 vis-classify_flower lpq_开放 cop_helloScope ApsMis_fangdi_permission smartapp_snsapi_base smartapp_mapp_dev_manage iop_autocar oauth_tp_app smartapp_smart_game_openapi oauth_sessionkey smartapp_swanid_verify smartapp_opensource_openapi smartapp_opensource_recapi fake_face_detect_开放Scope vis-ocr_虚拟人物助理 idl-video_虚拟人物助理 smartapp_component',
'session_secret': '01fed1bf12ccb01d24a4a57b1afac680'}
```
#### 2.1 人脸检测与属性分析
```python
request_url = "https://aip.baidubce.com/rest/2.0/face/v3/detect"
#添加人脸图片的url
params = "{\"image\":\"https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603536477084&di=5703c5fb651da5201f10ad840ea7375b&imgtype=0&src=http%3A%2F%2Fdingyue.ws.126.net%2F2020%2F0310%2Fc63836a2j00q6z2bw00acc000z901bjm.jpg\",\"image_type\":\"URL\",\"face_field\":\"faceshape,facetype\"}"
access_token = '24.4fccd940570684564d194d9fd1bd92e4.2592000.1606118256.282335-22869548'
request_url = request_url + "?access_token=" + access_token
headers = {'content-type': 'application/json'}
response = requests.post(request_url, data=params, headers=headers)
response.json()
# 返回结果
{'error_code': 0,
'error_msg': 'SUCCESS',
'log_id': 2015545754555,
'timestamp': 1603526426,
'cached': 0,
'result': {'face_num': 1,
'face_list': [{'face_token': 'ae407fb0ae5f4efe58f3d0fac00a139b',
'location': {'left': 271.97,
'top': 517.34,
'width': 758,
'height': 715,
'rotation': 2},
'face_probability': 1,
'angle': {'yaw': -27.84, 'pitch': 15.83, 'roll': 7.57},
'face_shape': {'type': 'heart', 'probability': 0.51},
'face_type': {'type': 'human', 'probability': 0.97}}]}}
```
#### 2.2 获取第二张人脸的face_token
```python
request_url = "https://aip.baidubce.com/rest/2.0/face/v3/detect"
#添加人脸图片的url
params = "{\"image\":\"https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603536654523&di=fb80a33087a34326b30abf704734f4af&imgtype=0&src=http%3A%2F%2Fugc.hitv.com%2Fzhuanlan%2F20200228143906_6e6734bc-914e-4206-af77-5ab8ac77a5c1.jpg\",\"image_type\":\"URL\",\"face_field\":\"faceshape,facetype\"}"
access_token = '24.4fccd940570684564d194d9fd1bd92e4.2592000.1606118256.282335-22869548'
request_url = request_url + "?access_token=" + access_token
headers = {'content-type': 'application/json'}
response = requests.post(request_url, data=params, headers=headers)
response.json()
# 返回结果
{'error_code': 0,
'error_msg': 'SUCCESS',
'log_id': 9415001455500,
'timestamp': 1603526586,
'cached': 0,
'result': {'face_num': 1,
'face_list': [{'face_token': 'ea1f2d40cd38038fcbbcfaebac4698e1',
'location': {'left': 167.59,
'top': 147.95,
'width': 144,
'height': 137,
'rotation': -2},
'face_probability': 1,
'angle': {'yaw': 6.1, 'pitch': 10.96, 'roll': -5.92},
'face_shape': {'type': 'round', 'probability': 0.46},
'face_type': {'type': 'human', 'probability': 1}}]}}
```
#### 3. 人脸对比
```python
# 3.人脸对比
request_url = "https://aip.baidubce.com/rest/2.0/face/v3/match"
params = "[{\"image\": \"ae407fb0ae5f4efe58f3d0fac00a139b\", \"image_type\": \"FACE_TOKEN\"}, {\"image\": \"ea1f2d40cd38038fcbbcfaebac4698e1\", \"image_type\": \"FACE_TOKEN\"}]"
access_token = '24.4fccd940570684564d194d9fd1bd92e4.2592000.1606118256.282335-22869548'
request_url = request_url + "?access_token=" + access_token
headers = {'content-type': 'application/json'}
response = requests.post(request_url, data=params, headers=headers)
if response:
print (response.json())
# 返回结果 score即为两张人脸的相似度
{'error_code': 0, 'error_msg': 'SUCCESS', 'log_id': 1018410145252, 'timestamp': 1603526714, 'cached': 0, 'result': {'score': 94.4076004, 'face_list': [{'face_token': 'ae407fb0ae5f4efe58f3d0fac00a139b'}, {'face_token': 'ea1f2d40cd38038fcbbcfaebac4698e1'}]}}
```
---
二、计算机视觉
参考：[Azure 计算机视觉文档](https://docs.microsoft.com/zh-cn/azure/cognitive-services/computer-vision/)
### 1. 分析远程图像
#### 1.分析远程图片
```python
import requests
%matplotlib inline
import matplotlib.pyplot as plt
import json
from PIL import Image
from io import BytesIO
# 从官网获取
endpoint = "https://api-hr01.cognitiveservices.azure.com/"
subscription_key = "7f058435c70043758c63fca8b017c360"
# base url
analyze_url = endpoint+ "vision/v3.1/analyze"
# 一张图片的链接
image_url = "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603540193573&di=c0dbf74e9ecf88285a2e4fdd6a1d1017&imgtype=0&src=http%3A%2F%2Fs3.lvjs.com.cn%2Fuploads%2Fpc%2Fplace2%2F2017-08-10%2Fabdf7dcc-ca9a-4000-b94f-38ef745ceaba.jpg"
headers = {'Ocp-Apim-Subscription-Key': subscription_key}
# 参数
params = {'visualFeatures': 'Categories,Description,Color'}
# 请求主体body
data = {'url': image_url}
response = requests.post(analyze_url, headers=headers,params=params, json=data)
response.raise_for_status()
# The 'analysis' object contains various fields that describe the image. The most
# relevant caption for the image is obtained from the 'description' property.
analysis = response.json()
print(json.dumps(response.json()))
image_caption = analysis["description"]["captions"][0]["text"].capitalize()
# Display the image and overlay it with the caption.
image = Image.open(BytesIO(requests.get(image_url).content))
plt.imshow(image)
plt.axis("off")
_ = plt.title(image_caption, size="x-large", y=-0.1)
plt.show()
```
#### 2.分析本地图片
```python
import os
import sys
import requests
%matplotlib inline
import matplotlib.pyplot as plt
from PIL import Image
from io import BytesIO
# 本地图片地址
image_path = "C:/Users/13513/Pictures/Saved Pictures/liuhaoran.jpg"
# Read the image into a byte array
image_data = open(image_path, "rb").read()
headers = {'Ocp-Apim-Subscription-Key': "7f058435c70043758c63fca8b017c360",
'Content-Type': 'application/octet-stream'}
params = {'visualFeatures': 'Categories,Description,Color'}
response = requests.post(
analyze_url, headers=headers, params=params, data=image_data)
response.raise_for_status()
# The 'analysis' object contains various fields that describe the image. The most
# relevant caption for the image is obtained from the 'description' property.
analysis = response.json()
print(analysis)
image_caption = analysis["description"]["captions"][0]["text"].capitalize()
# Display the image and overlay it with the caption.
image = Image.open(BytesIO(image_data))
plt.imshow(image)
plt.axis("off")
_ = plt.title(image_caption, size="x-large", y=-0.1)
```
#### 3.生成缩略图
```python
import os
import sys
import requests
%matplotlib inline
import matplotlib.pyplot as plt
from PIL import Image
from io import BytesIO
thumbnail_url = "https://api-hr01.cognitiveservices.azure.com/" + "vision/v3.1/generateThumbnail"
# 图片链接
image_url = "https://ss1.bdstatic.com/70cFuXSh_Q1YnxGkpoWK1HF6hhy/it/u=2406213756,3342094803&fm=26&gp=0.jpg"
headers = {'Ocp-Apim-Subscription-Key': "7f058435c70043758c63fca8b017c360"}
params = {'width': '100', 'height': '100', 'smartCropping': 'true'}
data = {'url': image_url}
response = requests.post(thumbnail_url, headers=headers,params=params, json=data)
response.raise_for_status()
thumbnail = Image.open(BytesIO(response.content))
# Display the thumbnail.
plt.imshow(thumbnail)
plt.axis("off")
# Verify the thumbnail size.
print("Thumbnail is {0}-by-{1}".format(*thumbnail.size))
```
#### 4.提取文本（读取API）
```python
import json
import os
import sys
import requests
import time
%matplotlib inline
import matplotlib.pyplot as plt
from matplotlib.patches import Polygon
from PIL import Image
from io import BytesIO
text_recognition_url = "https://api-hr01.cognitiveservices.azure.com/vision/v3.0/read/analyze"
# Set image_url to the URL of an image that you want to recognize.
image_url = "https://ss1.bdstatic.com/70cFvXSh_Q1YnxGkpoWK1HF6hhy/it/u=3025575980,164542079&fm=26&gp=0.jpg"
headers = {'Ocp-Apim-Subscription-Key': "e33e05cf8a914c73b9a740cab41e61cc"}
data = {'url': image_url}
response = requests.post(text_recognition_url, headers=headers, json=data)
response.raise_for_status()
# Extracting text requires two API calls: One call to submit the
# image for processing, the other to retrieve the text found in the image.
# Holds the URI used to retrieve the recognized text.
operation_url = response.headers["Operation-Location"]
# The recognized text isn't immediately available, so poll to wait for completion.
analysis = {}
poll = True
while (poll):
response_final = requests.get(
response.headers["Operation-Location"], headers=headers)
analysis = response_final.json()
print(json.dumps(analysis, indent=4))
time.sleep(1)
if ("analyzeResult" in analysis):
poll = False
if ("status" in analysis and analysis['status'] == 'failed'):
poll = False
polygons = []
if ("analyzeResult" in analysis):
# Extract the recognized text, with bounding boxes.
polygons = [(line["boundingBox"], line["text"])
for line in analysis["analyzeResult"]["readResults"][0]["lines"]]
# Display the image and overlay it with the extracted text.
image = Image.open(BytesIO(requests.get(image_url).content))
ax = plt.imshow(image)
for polygon in polygons:
vertices = [(polygon[0][i], polygon[0][i+1])
for i in range(0, len(polygon[0]), 2)]
text = polygon[1]
patch = Polygon(vertices, closed=True, fill=False, linewidth=2, color='y')
ax.axes.add_patch(patch)
plt.text(vertices[0][0], vertices[0][1], text, fontsize=20, va="top")
plt.show()
```
#### 返回结果
```
{
"status": "running",
"createdDateTime": "2020-10-24T09:18:11Z",
"lastUpdatedDateTime": "2020-10-24T09:18:11Z"
}
{
"status": "succeeded",
"createdDateTime": "2020-10-24T09:18:11Z",
"lastUpdatedDateTime": "2020-10-24T09:18:11Z",
"analyzeResult": {
"version": "3.0.0",
"readResults": [
{
"page": 1,
"angle": -0.1174,
"width": 311,
"height": 209,
"unit": "pixel",
"lines": [
{
"boundingBox": [
5,
7,
253,
6,
253,
41,
5,
44
],
"text": "Life is the flower for",
"words": [
{
"boundingBox": [
24,
7,
67,
9,
60,
44,
15,
44
],
"text": "Life",
"confidence": 0.981
},
{
"boundingBox": [
74,
10,
90,
10,
84,
44,
68,
44
],
"text": "is",
"confidence": 0.981
},
{
"boundingBox": [
97,
10,
135,
11,
132,
43,
92,
44
],
"text": "the",
"confidence": 0.985
},
{
"boundingBox": [
143,
11,
203,
11,
203,
41,
140,
43
],
"text": "flower",
"confidence": 0.652
},
{
"boundingBox": [
211,
11,
251,
10,
253,
38,
211,
40
],
"text": "for",
"confidence": 0.981
}
]
},
{
"boundingBox": [
16,
60,
262,
58,
263,
90,
16,
93
],
"text": "which love is the honey",
"words": [
{
"boundingBox": [
23,
62,
83,
60,
82,
92,
22,
94
],
"text": "which",
"confidence": 0.944
},
{
"boundingBox": [
89,
60,
128,
59,
128,
91,
89,
92
],
"text": "love",
"confidence": 0.981
},
{
"boundingBox": [
134,
59,
153,
59,
153,
91,
134,
91
],
"text": "is",
"confidence": 0.981
},
{
"boundingBox": [
159,
59,
201,
59,
200,
90,
159,
91
],
"text": "the",
"confidence": 0.985
},
{
"boundingBox": [
207,
59,
263,
61,
262,
90,
206,
90
],
"text": "honey",
"confidence": 0.736
}
]
},
{
"boundingBox": [
12,
106,
310,
112,
309,
143,
12,
140
],
"text": "Fine words butter no parsnips",
"words": [
{
"boundingBox": [
22,
107,
71,
107,
70,
141,
21,
141
],
"text": "Fine",
"confidence": 0.913
},
{
"boundingBox": [
78,
107,
127,
109,
127,
141,
77,
141
],
"text": "words",
"confidence": 0.983
},
{
"boundingBox": [
134,
109,
192,
111,
192,
141,
133,
141
],
"text": "butter",
"confidence": 0.892
},
{
"boundingBox": [
198,
111,
223,
112,
223,
142,
198,
141
],
"text": "no",
"confidence": 0.986
},
{
"boundingBox": [
230,
113,
308,
117,
308,
143,
230,
142
],
"text": "parsnips",
"confidence": 0.911
}
]
},
{
"boundingBox": [
7,
159,
251,
159,
251,
192,
7,
193
],
"text": "Bad neus travels fast",
"words": [
{
"boundingBox": [
21,
159,
67,
160,
68,
194,
21,
194
],
"text": "Bad",
"confidence": 0.979
},
{
"boundingBox": [
74,
160,
121,
160,
121,
193,
74,
194
],
"text": "neus",
"confidence": 0.559
},
{
"boundingBox": [
127,
160,
194,
161,
195,
191,
128,
193
],
"text": "travels",
"confidence": 0.69
},
{
"boundingBox": [
201,
161,
249,
163,
251,
189,
201,
191
],
"text": "fast",
"confidence": 0.978
}
]
}
]
}
]
}
}
```
#### 5. 提取文本（OCR API）
```python
import os
import sys
import requests
%matplotlib inline
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
from PIL import Image
from io import BytesIO
ocr_url = "https://api-hr01.cognitiveservices.azure.com/vision/v3.1/ocr"
# Set image_url to the URL of an image that you want to analyze.
image_url = "https://ss1.bdstatic.com/70cFvXSh_Q1YnxGkpoWK1HF6hhy/it/u=3025575980,164542079&fm=26&gp=0.jpg"
headers = {'Ocp-Apim-Subscription-Key': "7f058435c70043758c63fca8b017c360"}
params = {'language': 'unk', 'detectOrientation': 'true'}
data = {'url': image_url}
response = requests.post(ocr_url, headers=headers, params=params, json=data)
response.raise_for_status()
analysis = response.json()
# Extract the word bounding boxes and text.
line_infos = [region["lines"] for region in analysis["regions"]]
word_infos = []
for line in line_infos:
for word_metadata in line:
for word_info in word_metadata["words"]:
word_infos.append(word_info)
word_infos
# Display the image and overlay it with the extracted text.
plt.figure(figsize=(5, 5))
image = Image.open(BytesIO(requests.get(image_url).content))
ax = plt.imshow(image, alpha=0.5)
for word in word_infos:
bbox = [int(num) for num in word["boundingBox"].split(",")]
text = word["text"]
origin = (bbox[0], bbox[1])
patch = Rectangle(origin, bbox[2], bbox[3],
fill=False, linewidth=2, color='y')
ax.axes.add_patch(patch)
plt.text(origin[0], origin[1], text, fontsize=20, weight="bold", va="top")
plt.show()
plt.axis("off")
```
#### 6.使用域模型--识别地标
```python
import os
import sys
import requests
%matplotlib inline
import matplotlib.pyplot as plt
from PIL import Image
from io import BytesIO
landmark_analyze_url = endpoint + "vision/v3.1/models/landmarks/analyze"
# Set image_url to the URL of an image that you want to analyze.
image_url = "https://images.unsplash.com/photo-1587825338028-f1d568e0dbb3?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9&auto=format&fit=crop&w=2689&q=80"
headers = {'Ocp-Apim-Subscription-Key': "7f058435c70043758c63fca8b017c360"}
params = {'model': 'landmarks'}
data = {'url': image_url}
response = requests.post(
landmark_analyze_url, headers=headers, params=params, json=data)
response.raise_for_status()
# The 'analysis' object contains various fields that describe the image. The
# most relevant landmark for the image is obtained from the 'result' property.
analysis = response.json()
assert analysis["result"]["landmarks"] is not []
print(analysis)
landmark_name = analysis["result"]["landmarks"][0]["name"].capitalize()
# Display the image and overlay it with the landmark name.
image = Image.open(BytesIO(requests.get(image_url).content))
plt.imshow(image)
plt.axis("off")
_ = plt.title(landmark_name, size="x-large", y=-0.1)
plt.show()
```
#### 7.使用域模型--名人
```python
import requests
%matplotlib inline
import matplotlib.pyplot as plt
from PIL import Image
from io import BytesIO
# Replace with your valid subscription key.
subscription_key = "7f058435c70043758c63fca8b017c360"
assert subscription_key
vision_base_url = "https://api-hr01.cognitiveservices.azure.com/vision/v2.1/"
celebrity_analyze_url = vision_base_url + "models/celebrities/analyze"
# Set image_url to the URL of an image that you want to analyze.
image_url = "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1603541905213&di=863e904e625f5302e6c8094d3f441fff&imgtype=0&src=http%3A%2F%2Fpic.baike.soso.com%2Fp%2F20140504%2F20140504131147-671941598.jpg"
headers = {'Ocp-Apim-Subscription-Key': subscription_key}
params = {'model': 'celebrities'}
data = {'url': image_url}
response = requests.post(
celebrity_analyze_url, headers=headers, params=params, json=data)
response.raise_for_status()
# The 'analysis' object contains various fields that describe the image. The
# most relevant celebrity for the image is obtained from the 'result' property.
analysis = response.json()
assert analysis["result"]["celebrities"] is not []
print(analysis)
celebrity_name = analysis["result"]["celebrities"][0]["name"].capitalize()
# Display the image and overlay it with the celebrity name.
image = Image.open(BytesIO(requests.get(image_url).content))
plt.imshow(image)
plt.axis("off")
_ = plt.title(celebrity_name, size="x-large", y=-0.1)
plt.show()
```
---
三、学习心得
1. 在返回错误的结果时千万不要慌张、厌烦，运行报错一般会提示你哪里出错，一定要把那行代码出现到的值，从头找出逐次排查，一般就能检查出来，若是单纯显示某行信息运行错误，没有提示运行原因，查看是否是因为缩进或多打了空格或字符不对等基础性错误，不断尝试，不断修改问题总会解决的！
2. 对我来说API这门课程在前几周上课的过程中感到十分吃力，知识比较难懂，但是在渐渐的学习于练习探索中，发现api的学习还是蛮有趣的。API这门课程与Python相结合，学习各种网站的文档，多尝试，多练习。
3. 多看API文档，结合API文档写代码，api文档真的很有用！一开始看到老师给出的文档的时候根本看不懂是什么意思，一片密密麻麻的代码看得就头疼，盲目的操作，也不知道到底在改什么，所以也导致就算错了，给出错误信息了，也不知应如何修改。这时，好好阅读、对比官方网站给出的api文档就很重要，对比过在这次作业中使用到的azure、face++和百度官网除了能给我们提供免费的使用权限（key等）外，给出的api文档里都会包含功能描述、调用url、调用方法、请求方式、返回值的解释等信息，有些甚至会直接给出代码，根据这些信息我们就可以更好的理解每一行代码的意思，返回错误时，一查也能知道自己是哪里错了。
4. 积极与其他小伙伴交流经验，互相学习，减少不必要的错误。