[Face++]Face初探——人脸检测
经过了强烈的思想斗争才把自己拖到图书馆做毕设T^T
anyway, 因为毕设里面有人脸识别的部分，所以就想找个现成的api先玩玩，于是就找到最近很火的face++：http://www.faceplusplus.com.cn/
接口什么的还是很简单的，主要就是看它的api开发文档，最终实现把demo中的hello.py改造之后能够上传本地的三张图片进行训练，然后对新的一幅图片进行识别，看这幅图片中的人脸是三张图片中的哪一张，对于我的毕设而言，这个功能其实就足够了。修改后的hello.py如下：
1 #!/usr/bin/env python2 2 # -*- coding: utf-8 -*- 3 # $File: hello.py 4 5 # In this tutorial, you will learn how to call Face ++ APIs and implement a 6 # simple App which could recognize a face image in 3 candidates. 7 # 在本教程中，您将了解到Face ++ API的基本调用方法，并实现一个简单的App，用以在3 8 # 张备选人脸图片中识别一个新的人脸图片。 9 10 # You need to register your App first, and enter you API key/secret. 11 # 您需要先注册一个App，并将得到的API key和API secret写在这里。 12 API_KEY = '********' 13 API_SECRET = '*********' 14 15 # Import system libraries and define helper functions 16 # 导入系统库并定义辅助函数 17 import time 18 from pprint import pformat 19 def print_result(hint, result): 20 def encode(obj): 21 if type(obj) is unicode: 22 return obj.encode('utf-8') 23 if type(obj) is dict: 24 return {encode(k): encode(v) for (k, v) in obj.iteritems()} 25 if type(obj) is list: 26 return [encode(i) for i in obj] 27 return obj 28 print hint 29 result = encode(result) 30 print '\n'.join([' ' + i for i in pformat(result, width = 75).split('\n')]) 31 32 # First import the API class from the SDK 33 # 首先，导入SDK中的API类 34 from facepp import API 35 from facepp import File 36 37 api = API(API_KEY, API_SECRET) 38 39 # Here are the person names and their face images 40 # 人名及其脸部图片 41 PERSONS = [ 42 ('Yanzi Sun', './syz.jpeg'), 43 ('Qiaoen Chan', './cqe.jpeg'), 44 ('Jackie Chan', './jk.jpeg') 45 ] 46 TARGET_IMAGE = './cl.jpg' 47 48 # Step 1: Create a group to add these persons in 49 # 步骤1： 新建一个group用以添加person 50 api.group.create(group_name = 'forfun') 51 52 # Step 2: Detect faces from those three images and add them to the persons 53 # 步骤2：从三种图片中检测人脸并将其加入person中。 54 for (name, path) in PERSONS: 55 result = api.detection.detect(img = File(path)) 56 print_result('Detection result for {}:'.format(name), result) 57 58 face_id = result['face'][0]['face_id'] 59 60 # Create a person in the group, and add the face to the person 61 # 在该group中新建一个person，并将face加入期中 62 api.person.create(person_name = name, group_name = 'forfun', 63 face_id = face_id) 64 65 66 # Step 3: Train the group. 67 # Note: this step is required before performing recognition in this group, 68 # since our system needs to pre-compute models for these persons 69 # 步骤3：训练这个group 70 # 注：在group中进行识别之前必须执行该步骤，以便我们的系统能为这些person建模 71 result = api.recognition.train(group_name = 'forfun', type = 'all') 72 73 # Because the train process is time-consuming, the operation is done 74 # asynchronously, so only a session ID would be returned. 75 # 由于训练过程比较耗时，所以操作必须异步完成，因此只有session ID会被返回 76 print_result('Train result:', result) 77 78 session_id = result['session_id'] 79 80 # Now, wait before train completes 81 # 等待训练完成 82 while True: 83 result = api.info.get_session(session_id = session_id) 84 if result['status'] == u'SUCC': 85 print_result('Async train result:', result) 86 break 87 time.sleep(1) 88 89 #也可以通过调用api.wait_async(session_id)函数完成以上功能 90 91 92 # Step 4: recognize the unknown face image 93 # 步骤4：识别未知脸部图片 94 result = api.recognition.recognize(img = File(TARGET_IMAGE), group_name = 'forfun') 95 print_result('Recognize result:', result) 96 print '=' * 60 97 print 'The person with highest confidence:', \ 98 result['face'][0]['candidate'][0]['person_name'] 99 100 101 # Finally, delete the persons and group because they are no longer needed 102 # 最终，删除无用的person和group 103 api.group.delete(group_name = 'forfun') 104 api.person.delete(person_name = [i[0] for i in PERSONS]) 105 106 # Congratulations! You have finished this tutorial, and you can continue 107 # reading our API document and start writing your own App using Face++ API! 108 # Enjoy :) 109 # 恭喜！您已经完成了本教程，可以继续阅读我们的API文档并利用Face++ API开始写您自 110 # 己的App了！ 111 # 旅途愉快 :)
要注意的就是35行，因为原来demo里面的图像是通过url获取的，而这里需要从本地上传，所以就要用到facepp.py里面定义的File类。另外注意12，13行的API_KEY和API_SECRET是通过在网站注册得到的。
其它改动的地方就是图片的路径，剩下的都是原来demo中的代码了。最终的结果如下：
Detection result for Yanzi Sun: {'face': [{'attribute': {'age': {'range': 5, 'value': 30}, 'gender': {'confidence': 99.9991, 'value': 'Female'}, 'race': {'confidence': 80.13329999999999, 'value': 'Asian'}, 'smiling': {'value': 99.3116}}, 'face_id': 'f2790efd530b569cdc505cc2465da34f', 'position': {'center': {'x': 52.57732, 'y': 41.923077}, 'eye_left': {'x': 42.224794, 'y': 36.929538}, 'eye_right': {'x': 62.156701, 'y': 35.701385}, 'height': 27.692308, 'mouth_left': {'x': 42.051031, 'y': 49.590385}, 'mouth_right': {'x': 63.552577, 'y': 49.841154}, 'nose': {'x': 53.861856, 'y': 46.203462}, 'width': 37.113402}, 'tag': ''}], 'img_height': 260, 'img_id': '09c7c2d49eb98dc2e90340ef2a6c9531', 'img_width': 194, 'session_id': '3a47b91a118d4c7cae9dcaf5ba61eec5', 'url': None} Detection result for Qiaoen Chan: {'face': [{'attribute': {'age': {'range': 6, 'value': 15}, 'gender': {'confidence': 99.9974, 'value': 'Female'}, 'race': {'confidence': 98.2572, 'value': 'Asian'}, 'smiling': {'value': 2.82502}}, 'face_id': '805b397a72899eda36be3f1dfed73451', 'position': {'center': {'x': 32.0, 'y': 47.02381}, 'eye_left': {'x': 26.078067, 'y': 39.870476}, 'eye_right': {'x': 36.355667, 'y': 39.246726}, 'height': 38.095238, 'mouth_left': {'x': 28.270367, 'y': 59.064881}, 'mouth_right': {'x': 34.999667, 'y': 59.091369}, 'nose': {'x': 30.3052, 'y': 49.743036}, 'width': 21.333333}, 'tag': ''}], 'img_height': 168, 'img_id': 'ebee384c2b96399c3f52565682e4c249', 'img_width': 300, 'session_id': '5c1623ef71944c11a0efc6b4a698b3b0', 'url': None} Detection result for Jackie Chan: {'face': [{'attribute': {'age': {'range': 10, 'value': 50}, 'gender': {'confidence': 99.9967, 'value': 'Male'}, 'race': {'confidence': 76.5193, 'value': 'Asian'}, 'smiling': {'value': 96.2044}}, 'face_id': 'f164cc74a49e3d6766c8733ebdfe616d', 'position': {'center': {'x': 50.166667, 'y': 37.202381}, 'eye_left': {'x': 45.798, 'y': 32.12381}, 'eye_right': {'x': 53.721333, 'y': 30.344464}, 'height': 31.547619, 'mouth_left': {'x': 46.665333, 'y': 46.910298}, 'mouth_right': {'x': 54.770667, 'y': 45.298393}, 'nose': {'x': 49.889667, 'y': 39.642143}, 'width': 17.666667}, 'tag': ''}], 'img_height': 168, 'img_id': 'd2ef3d2bd1d907fa15130f505300226e', 'img_width': 300, 'session_id': 'c7d498450b28453f8f90135ca92a327c', 'url': None} Train result: {'session_id': '041678d25ac94c2689396d0e6a660302'} Async train result: {'create_time': 1438667400, 'finish_time': 1438667400, 'result': {'success': True}, 'session_id': '041678d25ac94c2689396d0e6a660302', 'status': 'SUCC'} Recognize result: {'face': [{'candidate': [{'confidence': 10.85891, 'person_id': '476ec2d1e98b8da80bf661a5241b85fd', 'person_name': 'Jackie Chan', 'tag': ''}, {'confidence': 0.24913, 'person_id': '0ef10cf989df7888f376fc54e339b93a', 'person_name': 'Yanzi Sun', 'tag': ''}, {'confidence': 0.0, 'person_id': 'a8070f1d28f28fffbb45491da06f3620', 'person_name': 'Qiaoen Chan', 'tag': ''}], 'face_id': 'e9b0968077ae7a40ff9eebffadec1520', 'position': {'center': {'x': 44.5, 'y': 29.75}, 'eye_left': {'x': 40.519167, 'y': 24.590125}, 'eye_right': {'x': 47.810167, 'y': 23.993575}, 'height': 23.0, 'mouth_left': {'x': 40.731833, 'y': 35.77625}, 'mouth_right': {'x': 47.273167, 'y': 35.041}, 'nose': {'x': 45.096167, 'y': 31.58725}, 'width': 15.333333}}], 'session_id': 'dbbabdf0e75d49ff8674f136f0c06bdd'} ============================================================ The person with highest confidence: Jackie Chan
我给了三张训练图片：syz.jpeg, cqe.jpeg, jk.jpeg分别代表三个明星，最后一个是Jackie Chan，测试图片也给的Jackie Chan，最终还是准确的检测和识别出来了。
最后要注意python是脚本语言，所以没有编译的过程，上述代码也没有错误处理的过程，所以如果程序出现了bug会直接停止执行，那么就没办法执行103，104行删除group和person的代码了。这个造成的影响就是再次运行上述代码的时候，云端数据库里面仍然有上一次的group和person，而同一个app里面是不允许的，就会报“NAME_EXIST”的错误，这时候一种办法是运行demo下面的cmdtool.py，在出现的交互式命令行里面用下面的代码手动删除创建的group和person：
api.group.delete(group_name = 'forfun') api.person.delete(person_name='Jackie Chan') api.person.delete(person_name='Qiaoen Chan') api.person.delete(person_name='Yanzi Sun')
参考：
［1］Face++主页：http://www.faceplusplus.com.cn/
［2］Face++开发者文档：http://www.faceplusplus.com.cn/api-overview/
［3］Face++ python sdk: https://github.com/FacePlusPlus/facepp-python-sdk
