Face - Identify 在一个人组中识别未知的面部 对于faceids数组中每一张人脸，人脸识别会计算这张查询的脸和在人组中（personGroupId提供的）所有的脸之间的相似度，然后按照相似度等级排序返回一个候选的person(s)。人组应该是可以被鉴别的。更多知识请查看Person Group - Train Person Group. Remarks: * 该算法允许在相同的请求下独立识别多个面部，但不超过10个面部。 * Person group中的每个person可以有不止一张脸，但不超过248张脸 * 识别适用于正面和近正面 * 返回的候选人数量受maxNumOfCandidatesReturned和confidenceThreshold限制。如果没有人被识别，返回一个空数组 * 当需要从face list而不是person group中识别相似的脸部时，请尝试 Face - Find Similar Http Method `POST` Request URL `https://api.cognitive.azure.cn/face/v1.0/identify` Request headers | 请求头部 | 类型 | 描述 | | --- | --- | --- | | Content-Type(可选) | string | Media type of the body sent to the API. | | Ocp-Apim-Subscription-Key | string | Subscription key which provides access to this API. Found in your Cognitive Services accounts. | Request body JSON fields in request body | Fields | Type | Description | | --- | --- | --- | | faceIds | Array | 查询面faceIds组成的数组，由Face - Detect创建。每个面都是独立标识的。faceIds的有效数量在[1，10]之间| | personGroupId | String | 指定的persong group 的personGroupId 由 Person Group - Create a Person Group.创建 | | maxNumOfCandidatesReturned （可选） |Number | maxNumOfCandidatesReturned的范围在1到5之间（默认为1） | | confidenceThreshold (可选) | Number | 可选参数。识别的置信度阈值，用于判断这张脸是否属于这个人。confidenceThreshold的范围是[0，1]（默认由算法指定） | ~~~ { "personGroupId":"sample_group", "faceIds":[ "c5c24a82-6845-4031-9d5d-978df9175426", "65d083d4-9447-47d1-af30-b626144bf0fb" ], "maxNumOfCandidatesReturned":1, "confidenceThreshold": 0.5 } ~~~ Response 200 成功后，返回每个查询返回标识的候选人员 JSON fields in response body | Fields | Type | Description | | --- | --- | --- | | faceId | String | 查询面的faceId | | Candidates | Array | 符合请求的面部数据识别的person，根据相似度排序 | | personId | String | 获选人的personId | |confidence | Number | 一个0.0-1.0之间的浮点数 | ~~~ { [ { "faceId":"c5c24a82-6845-4031-9d5d-978df9175426", "candidates":[ { "personId":"25985303-c537-4467-b41d-bdb45cd95ca1", "confidence":0.92 } ] }, { "faceId":"65d083d4-9447-47d1-af30-b626144bf0fb", "candidates":[ { "personId":"2ae4935b-9659-44c3-977f-61fac20d0538", "confidence":0.89 } ] } ] } ~~~ Response 400 Error code and message returned in JSON | Error Code | Error Message Description | | --- | --- | | BadArgument | 无效的请求正文 | | BadArgument | 参数maxNumOfCandidatesReturned无效。范围是[1,5] | | BadArgument | 参数confidenceThreshold无效。范围是[0，1] | | BadArgument |FaceID无效 | | BadArgument | Person group ID无效。有效格式应该是由数字组成的字符串，英文字母小写，' - '，'_'，不超过64个字符。 | | PersonGroupNotFound | Person group未找到 | | FaceNotFound | Face未找到| | PersonGroupNotTrained | Person group 样本点未trained| ~~~ { "error":{ "code":"BadArgument", "message":"Person group 'sample_group' is invalid." } } ~~~ 返回值401 Error code and message returned in JSON | Error Code| Error Message Description | | --- | --- | | Unspecified | 无效的subscription Key或用户/计划被冻结 | ~~~ { "error":{ "code": "Unspecified", "message": "Access denied due to invalid subscription key. Make sure you are subscribed to an API you are trying to call and provide the right key." } } ~~~ Response 403 ~~~ { "error":{ "statusCode": 403, "message": "Out of call volume quota. Quota will be replenished in 2.12 days." } } ~~~ Response 409 训练过程与识别相冲突。训练结束后再试一次 ~~~ { "error":{ "code":"PersonGroupTrainingNotFinished", "message":"Person group 'sample_group' is under training." } } ~~~ Response 415 不支持的媒体类型错误。只有“application / json”对这个API有效 ~~~ { "error":{ "code":"BadArgument", "message":"Invalid Media Type" } } ~~~ Response 429 ~~~ { "error":{ "statusCode": 429, "message": "Rate limit is exceeded. Try again in 26 seconds." } } ~~~