文档中心

上云无忧 > 文档中心 > 百度智能云iOCR自定义模板文字识别财会版API文档
百度智能云
iOCR自定义模板文字识别
简介/价格/文档
百度智能云iOCR自定义模板文字识别财会版API文档

文档简介：
请求说明 请求示例 HTTP 方法：POST 请求URL： https://aip.baidubce.com/rest/2.0/solution/v1/iocr/recognise/finance URL参数： 参数 值 access_token 通过API Key和Secret Key获取的access_token,参考“Access Token获取” Header如下： 参数 值 Content-Type application/x-www-form-urlencoded Body中放置请求参数，参数详情如下：
*此产品及展示信息均由百度智能云官方提供。免费试用 咨询热线：400-826-7010，为您提供专业的售前咨询，让您快速了解云产品，助您轻松上云！ 微信咨询
  免费试用、价格特惠

请求说明

请求示例

HTTP 方法：POST

请求URL： https://aip.baidubce.com/rest/2.0/solution/v1/iocr/recognise/finance

URL参数：

参数 值
access_token 通过API Key和Secret Key获取的access_token,参考“Access Token获取”

Header如下：

参数 值
Content-Type application/x-www-form-urlencoded

Body中放置请求参数，参数详情如下：

请求参数

参数 是否必选 类型 可选值范围 说明
image 和 url/pdf_file 三选一 string - 图像数据，base64编码后进行urlencode，需去掉编码头（data:image/jpeg;base64, ）
要求base64编码和urlencode后大小不超过4M，最短边至少15px，最长边最大4096px，支持jpg/jpeg/png/bmp格式
url 和 image/pdf_file 三选一 string - 图片完整URL，URL长度不超过1024字节，URL对应的图片base64编码后大小不超过4M，最短边至少15px，最长边最大4096px，支持jpg/jpeg/png/bmp格式，当image字段存在时url字段失效
请注意关闭URL防盗链
pdf_file 和 image/url 三选一 string - PDF文件，base64编码后进行urlencode，需去掉编码头（data:application/pdf;base64, ）
要求base64编码和urlencode后大小不超过4M
注：目前仅支持单页PDF识别，如上传的为多页PDF，仅识别第一页
templateSign 否 string - 模板 ID，自定义模板或预置模板的唯一标示，可用于调用指定的识别模板进行结构化识别，可在「模板管理」页查看并复制使用
classifierId 否 string - 分类器Id，分类器的唯一标示，可用于调用指定的分类器对传入的图片进行自动分类及识别
与 templateSign 至少存在一个，如同时存在，则优先级 templateSign > classfierId

请求代码示例

提示一：使用示例代码前，请记得替换其中的示例Token、图片地址或Base64信息。

提示二：部分语言依赖的类或库，请在代码注释中查看下载地址。 



# 请求模板id curl -i -k 'https://aip.baidubce.com/rest/2.0/solution/v1/iocr/recognise
/finance?access_token=【调用鉴权接口获取的token】' --data 
'templateSign=xxx&image=【图片Base64编码，需UrlEncode】'
 -H 'Content-Type:application/x-www-form-urlencoded' #
 请求分类器id curl -i -k 'https://aip.baidubce.com/rest/2.0/solution/v1/iocr
/recognise/finance?access_token=【调用鉴权接口获取的token】' --data 'classifierId=xxx&image=
【图片Base64编码，需UrlEncode】' -H 'Content-Type:application/x-www-form-urlencoded'


返回说明

返回参数

字段 是否必选 类型 说明
logid 是 uint64 唯一的log id，用于问题定位
error_code 是 int 0代表成功，如果有错误码返回可以参考下方错误码列表排查问题
error_msg 是 string 如果error_code具体的失败信息，可以参考下方错误码列表排查问题
data 是 jsonObject 识别返回的结果
+ ret 是 jsonArray 识别出来的字段数组，每一个单元里包含以下几个元素
++ word_name 否 string isStructured 为 true 时存在，表示字段的名字；如果 isStructured 为 false 时，不存在
++ word 否 string 识别的字符串或单字
++ location 否 jsonObject 字段在原图上对应的矩形框位置，通过上边距、左边距、宽度、高度表示
++ probability 否 jsonObject 字段的置信度，包括平均、最小和方差
+ templateSign 否 string 图片分类结果对应的模板id或指定使用的模版id。templateSign的对应关系为：
- mixed_receipt：混贴发票，可对粘贴单中的多张不同票据进行检测分类，返回每张发票的类别及识别结果；
- vat_invoice：增值税发票；
- taxi：出租车票；
- roll_ticket：卷票；
- train_ticket：火车票；
- quota_invoice：定额发票；
- travel_itinerary：行程单；
- car_invoice：汽车票；
- toll_invoice：通行费发票；
- printed_invoice：机打发票。
+ scores 否 float 分类置信度，如果指定templateSign，则该值为1
+ isStructured 否 string 表示是否结构化成功，true为成功，false为失败；成功时，返回结构化的识别结果；失败时，如果能识别，按行返回结果，如果不能识别，返回空

返回示例

  • 使用自定义模板及自定义分类器功能时，返回结果可参考 iOCR通用版-返回示例；
  • templateSign = mixed_receipt 时，返回结果如下所示： 


{ "data": { "ret": [ { "ret": [ { "rect": { "top": 277, "left": 237, "width": 61, "height": 10 }, 
"probability": { "average": 0.98831981420517, "min": 0.96548694372177 }, "word_name": "AmountInWords", 
"word": "叁佰陆拾圆整" }, { "rect": { "top": 29, "left": 482, "width": 85, "height": 18 }, "probability":
 { "average": 0.99745708703995, "min": 0.99514311552048 }, "word_name": "InvoiceNumConfirm", "word": "07286261" }, 
{ "rect": { "top": 352, "left": 393, "width": 32, "height": 12 }, "probability": { "average": 0.99022936820984,
 "min": 0.98398983478546 }, "word_name": "NoteDrawer", "word": "余佳燕" }, { "rect": { "top": 326, "left": 158,
 "width": 214, "height": 10 }, "probability": { "average": 0.94039279222488, "min": 0.39105615019798 }, 
"word_name": "SellerAddress", "word": "杭州市转塘科技经济区块16号8幢0571-85022088" }, 
{ "rect": { "top": 311, "left": 171, "width": 146, "height": 12 }, "probability": { "average": 0.99681425094604,
 "min": 0.98468536138535 }, "word_name": "SellerRegisterNum", "word": "91330106673959654P" },
 { "rect": { "top": 0, "left": 0, "width": -1, "height": -1 }, "probability": { "average": 0, "min": 0 },
 "word_name": "MachineCode", "word": "" }, { "rect": { "top": 0, "left": 0, "width": -1, "height": -1 }, 
"probability": { "average": 0, "min": 0 }, "word_name": "Remarks", "word": "" }, { "rect": { "top": 339, "left": 158, 
"width": 181, "height": 11 }, "probability": { "average": 0.99247741699219, "min": 0.8911309838295 },
 "word_name": "SellerBank", "word": "招商银行杭州高新支行502905023610702" }, { "rect": { "top": 259,
 "left": 576, "width": 43, "height": 10 }, "probability": { "average": 0.97683322429657,
 "min": 0.89436012506485 }, "word_name": "TotalTax", "word": "20.38" }, { "rect": { "top": 32, "left": 124, "width": 101,
 "height": 16 }, "probability": { "average": 0.99661940336227, "min": 0.99573355913162 }, "word_name": 
"InvoiceCodeConfirm", "word": "3321192130" }, { "rect": { "top": 0, "left": 0, "width": -1, "height": -1 }, "probability": 
{ "average": 0, "min": 0 }, "word_name": "CheckCode", "word": "" }, { "rect": { "top": 32, "left": 124, 
"width": 101, "height": 16 }, "probability": { "average": 0.99661940336227, "min": 0.99573355913162 },
 "word_name": "InvoiceCode", "word": "3321192130" }, { "rect": { "top": 65, "left": 534, "width": 73, 
"height": 12 }, "probability": { "average": 0.99508810043335, "min": 0.97497177124023 }, "word_name": 
"InvoiceDate", "word": "2019年08月28日" }, { "rect": { "top": 104, "left": 168, "width": 147, "height": 12 },
 "probability": { "average": 0.9933996796608, "min": 0.96598559617996 }, "word_name": "PurchaserRegisterNum", 
"word": "91110911717743469K" }, { "rect": { "top": 18, "left": 257, "width": 164, "height": 19 },
 "probability": { "average": 0.99611341953278, "min": 0.98104286193848 }, "word_name": "InvoiceTypeOrg", "word":
 "浙江增值税专用发票" }, { "rect": { "top": 93, "left": 405, "width": 191, "height": 45 }, "probability": 
{ "average": 0.97755342721939, "min": 0.82740485668182 }, "word_name": "Password", 
"word": "508>3909>1*>01/-46709-6/3+*7+8>/1*19+7-0**>+58290-6>647-+324865*9*1
<*2191/7754/2<838+//5-69--748*<251408<" }, { "rect": { "top": 0, "left": 0, "width": -1, "height": -1 }, 
"probability": { "average": 0, "min": 0 },
 "word_name": "Agent", "word": "否" }, { "rect": { "top": 278, "left": 511, "width": 54, "height": 10 }, 
"probability": { "average": 0.95414996147156, "min": 0.68566131591797 }, "word_name": "AmountInFiguers", 
"word": "360.00" }, { "rect": { "top": 134, "left": 159, "width": 204, "height": 11 }, "probability": 
{ "average": 0.97773444652557, "min": 0.61343103647232 }, "word_name": "PurchaserBank", "word":
 "招商银行北京分行大电路支行866180100210002" }, { "rect": { "top": 352, "left": 259, "width": 
26, "height": 12 }, "probability": { "average": 0.98384791612625, "min": 0.97088402509689 },
 "word_name": "Checker", "word": "柳余" }, { "rect": { "top": 0, "left": 0, "width": -1, 
"height": -1 }, "probability": { "average": 0, "min": 0 }, "word_name": "City", "word": "" },
 { "rect": { "top": 258, "left": 460, "width": 49, "height": 11 }, "probability": 
{ "average": 0.98758614063263, "min": 0.9416212439537 }, "word_name": "TotalAmount", "word": "339.62" }, 
{ "rect": { "top": 90, "left": 159, "width": 150, "height": 12 }, "probability":
 { "average": 0.96976244449615, "min": 0.70321601629257 }, "word_name": "PurchaserName", "word":
 "百度在线网络技术(北京)有限公司" }, { "rect": { "top": 0, "left": 0, "width": -1, "height": -1 },
 "probability": { "average": 0, "min": 0 }, "word_name": "Province", "word": "浙江" }, { "rect": {
 "top": 18, "left": 257, "width": 164, "height": 19 }, "probability": { "average": 0.99611341953278,
 "min": 0.98104286193848 }, "word_name": "InvoiceType", "word": "专用发票" }, { "rect": { "top": 145,
 "left": 626, "width": 9, "height": 28 }, "probability": { "average": 0.99723851680756, "min": 0.99662339687347 }, 
"word_name": "SheetNum", "word": "第二联" }, { "rect": { "top": 119, "left": 159, "width": 158, "height": 12 },
 "probability": { "average": 0.89263164997101, "min": 0.21246993541718 }, "word_name": "PurchaserAddress",
 "word": "北京市海淀区上地十侧10号百厘大厦三座" }, { "rect": { "top": 353, "left": 113, "width": 22,
 "height": 10 }, "probability": { "average": 0.84802502393723, "min": 0.560218334198 },
 "word_name": "Payee", "word": "佳机" }, { "rect": { "top": 298, "left": 158, "width": 85,
 "height": 11 }, "probability": { "average": 0.96288979053497, "min": 0.8344641327858 },
 "word_name": "SellerName", "word": "阿里云计算有限公司" }, { "rect": { "top": 29, "left": 482,
 "width": 85, "height": 18 }, "probability": { "average": 0.99745708703995, "min": 0.99514311552048 },
 "word_name": "InvoiceNum", "word": "07286261" }, { "rect": { "top": 163, "left": 71, "width": 116,
 "height": 11 }, "probability": { "average": 0.9905007481575, "min": 0.98428183794022 }, "word_name":
 "DetailsOfTax#1#CommodityName", "word": "*信息技术服务*软件服务费" }, { "word_name": 
"DetailsOfTax#1#CommodityType", "word": "" }, { "rect": { "top": 164, "left": 292, 
"width": 10, "height": 10 }, "probability": { "average": 0.89159053564072, "min": 0.80279469490051 }, 
"word_name": "DetailsOfTax#1#CommodityUnit", "word": "套" }, { "rect": { "top": 166, "left": 360,
"width": 7, "height": 8 }, "probability": { "average": 0.95917397737503, "min": 0.95113134384155 },
 "word_name": "DetailsOfTax#1#CommodityNum", "word": "1" }, { "rect": { "top": 165, "left": 397,
 "width": 28, "height": 9 }, "probability": { "average": 0.97336208820343, "min": 0.89550644159317 },
 "word_name": "DetailsOfTax#1#CommodityPrice", "word": "339.62" }, { "rect": { "top": 165, "left": 480,
 "width": 28, "height": 9 }, "probability": { "average": 0.98559606075287, "min": 0.96932607889175 }, 
"word_name": "DetailsOfTax#1#CommodityAmount", "word": "339.62" }, { "rect": { "top": 165, "left": 522, 
"width": 11, "height": 9 }, "probability": { "average": 0.92075562477112, "min": 0.8382123708725 },
 "word_name": "DetailsOfTax#1#CommodityTaxRate", "word": "6%" }, { "rect": { "top": 165, "left": 595, 
"width": 24, "height": 9 }, "probability": { "average": 0.97626549005508, "min": 0.9149768948555 },
 "word_name": "DetailsOfTax#1#CommodityTax", "word": "20.38" } ], "receiptCoordinate": 
"{\"height\":642,\"left\":155,\"top\":178,\"width\":1106}", "error_msg": "success",
 "templateSign": "vat_invoice", "scores": 1, "templateName": "增值税发票", "isStructured": true, 
"error_code": 0 }, { "ret": [ { "probability": { "average": 0, "min": 0 }, "word_name": "PickupTime",
 "word": "16:50" }, { "probability": { "average": 0, "min": 0 }, "word_name": "DropoffTime", "word": "17:06" },
 { "rect": { "top": 212, "left": 48, "width": 66, "height": 9 }, "probability": { "average": 0.98931306600571,
 "min": 0.92181307077408 }, "word_name": "Time", "word": "16:50-17:06" }, 
{ "probability": { "average": 0, "min": 0 }, "word_name": "City", "word": "" },
 { "rect": { "top": 288, "left": 84, "width": 30, "height": 9 }, "probability": { "average": 0.99606895446777,
 "min": 0.99255055189133 }, "word_name": "FuelOilSurcharge", "word": "1.00" },
 { "rect": { "top": 198, "left": 53, "width": 61, "height": 9 }, "probability": { "average": 0.99483448266983, 
"min": 0.98498445749283 }, "word_name": "Date", "word": "2019-03-20" }, { "probability":
 { "average": 0, "min": 0 }, "word_name": "Province", "word": "陕西省" }, { "probability": 
{ "average": 0, "min": 0 }, "word_name": "CallServiceSurcharge", "word": "0.00" }, { "rect": 
{ "top": 275, "left": 76, "width": 38, "height": 9 }, "probability": { "average": 0.98517167568207,
 "min": 0.97685235738754 }, "word_name": "Fare", "word": "21.10" }, { "rect": { "top": 314, "left":
 76, "width": 39, "height": 9 }, "probability": { "average": 0.97668653726578, "min": 0.93554848432541 },
 "word_name": "TotalFare", "word": "2.00" }, { "rect": { "top": 173, "left": 72, "width": 42, "height": 8 },
 "probability": { "average": 0.98336416482925, "min": 0.88234621286392 }, "word_name": "TaxiNum", "word":
 "BQ6353" }, { "rect": { "top": 225, "left": 89, "width": 25, "height": 8 }, "probability":
 { "average": 0.99482887983322, "min": 0.99453765153885 }, "word_name": "PricePerkm", "word": "2.30" }, 
{ "rect": { "top": 124, "left": 14, "width": 90, "height": 11 }, "probability": { "average": 0.99889290332794,
 "min": 0.99876511096954 }, "word_name": "InvoiceCode", "word": "161001881016" }, { "rect": { "top": 238,
 "left": 96, "width": 18, "height": 8 }, "probability": { "average": 0.99126571416855, "min": 0.98285579681396 }, 
"word_name": "Distance", "word": "6.0" }, { "rect": { "top": 137, "left": 14, "width": 60, "height": 10 },
 "probability": { "average": 0.99211621284485, "min": 0.94001615047455 }, "word_name": "InvoiceNum",
 "word": "05070716" }, { "probability": { "average": 0, "min": 0 }, "word_name": "Location", "word"
 "陕西省" } ], "receiptCoordinate": "{\"height\":618,\"left\":1325,\"top\":200,\"width\":215}", 
"error_msg": "success", "templateSign": "taxi", "scores": 1, "templateName": "出租车发票", 
"isStructured": true, "error_code": 0 } ], "templateSign": "mixed_receipt", "templateName": "混贴票据", 
"scores": 1, "isStructured": true, "logId": "164196999300761", "version": 1 }, "error_code": 0,
 "error_msg": "", "log_id": "164196999300761" }
相似文档
  • 百度智能云iOCR自定义模板文字识别常见问题QA
    Q：什么是自定义模板文字识别？什么场景下我该使用这个产品？ A：自定义模板文字识别是一款您可以针对各种票据、卡证实现字段名和字段值对应提取的OCR产品；举例：当您需要识别某一种证件（比如房产证），但是百度官方还没有针对这种类型的证件推出具体的模板识别接口，而使用通用文字识别无法实现字段名和字段值对应化的提取，这种情况下您可以使用自定义模板文字识别产品，实现结构化的数据提取。
  • 百度智能云iOCR自定义模板文字识别错误码
    若请求错误，服务器将返回的JSON文本包含以下参数： error_code：错误码。 error_msg：错误描述信息，帮助理解和解决发生的错误。 例如Access Token失效返回： { "error_code": 110, "error_msg": "Access token invalid or no longer valid" } 需要重新获取新的Access Token再次请求即可。
  • 百度智能云EasyDL文字识别OCR简介
    功能介绍： EasyDL文字识别，可定制识别图片中的文字信息，结构化输出关键字段内容，极大提升OCR模型训练效率，满足个性化卡证票据识别需求 数据标注： 创建数据集并上传真实图片，定义数据识别字段作为标注标签，在图片中框选对应的 Key/Value 内容区域，自动识别框选区域内容完成转写，标注人员对识别结果进行查验纠正即可完成标注。 【百度智能云】iOCR自定义模板文字识别 【百度智能云】飞桨EasyDL零门槛AI开发平台
  • 百度智能云EasyDL文字识别OCR API文档
    请求说明 请求示例 HTTP 方法：POST 请求URL： https://aip.baidubce.com/rest/2.0/ai_custom/v1/ocr URL参数： 参数 值 access_token 通过API Key和Secret Key获取的access_token,参考“Access Token获取” Header如下： 参数 值 Content-Type application/x-www-form-urlencoded Body中放置请求参数，参数详情如下： 【百度智能云】iOCR自定义模板文字识别 【百度智能云】飞桨EasyDL零门槛AI开发平台
  • 百度智能云EasyDL文字识别OCR错误码
    若请求错误，服务器将返回的JSON文本包含以下参数： error_code：错误码。 error_msg：错误描述信息，帮助理解和解决发生的错误。 例如Access Token失效返回： { "error_code": 110, "error_msg": "Access token invalid or no longer valid" } 需要重新获取新的Access Token再次请求即可。 【百度智能云】iOCR自定义模板文字识别 【百度智能云】飞桨EasyDL零门槛AI开发平台
官方微信
联系客服
400-826-7010
7x24小时客服热线
分享
  • QQ好友
  • QQ空间
  • 微信
  • 微博
返回顶部