时间:2021-05-22
本文为大家分享了python实现文字识别功能大全,供大家参考,具体内容如下
1.通用文字识别
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "test3.png" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() # 定义参数变量options = { 'detect_direction': 'true', 'language_type': 'CHN_ENG',} # 调用通用文字识别接口result = aipOcr.basicGeneral(get_file_content(filePath), options)print(result)words_result=result['words_result']for i in range(len(words_result)): print(words_result[i]['words'])2.网络图片文字识别
识别一些网络上背景复杂,特殊字体的文字。
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "2-5.jpg" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={}options["detect_direction"] = "true" #检测朝向options["detect_language"] = "true" #检测语言 result= aipOcr.webImage(get_file_content(filePath),options)print(result)for i in range(len(result['words_result'])): print(result['words_result'][i]['words'])3.身份证识别
身份证识别包括正面和背面。
# -*- coding: UTF-8 -*-from aip import AipOcr# 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath1 = "2-6-2.jpg" #正面filePath2 = "2-6-1.jpg" #背面def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={}options["detect_direction"] = "true" #检测朝向options["detect_risk"] = "true"#是否开启身份证风险类型(身份证复印件、临时身份证、身份证翻拍、修改过的身份证)功能,默认不开启 result1= aipOcr.idcard(get_file_content(filePath1),'front',options)result2= aipOcr.idcard(get_file_content(filePath2),'back',options)print(result1)print(result2)for key in result1['words_result'].keys(): print(key+':'+result1['words_result'][key]['words']) for key in result2['words_result'].keys(): print(key+':'+result2['words_result'][key]['words'])4.银行卡识别
识别银行卡并返回卡号和发卡行。
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "2-7.jpeg" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={} result=aipOcr.bankcard(get_file_content(filePath),options)print(result)#bank_card_type 银行卡类型,0:不能识别; 1: 借记卡; 2: 信用卡for key in result['result']: print(key+':'+str(result['result'][key]))5.驾驶证识别
对机动车驾驶证所有关键字段进行识别。
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "2-8.jpg" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={} result=aipOcr.drivingLicense(get_file_content(filePath),options)print(result) for key in result['words_result']: print(key+':'+str(result['words_result'][key]['words']))6.行驶证识别
对机动车行驶证正本所有关键字段进行识别。
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "2-9.jpg" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={} result=aipOcr.vehicleLicense(get_file_content(filePath),options)print(result) for key in result['words_result']: print(key+':'+str(result['words_result'][key]['words']))7.车牌识别
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "2-3.png" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={}options["multi_detect"] = "true"#是否检测多张车牌,默认为false,当置为true的时候可以对一张图片内的多张车牌进行识别 result= aipOcr.licensePlate(get_file_content(filePath),options) for i in range(len(result['words_result'])): print(result['words_result'][i]['color']+' '+result['words_result'][i]['number'])8.营业执照识别
识别营业执照,并返回关键字段的值,包括单位名称、法人、地址、有效期、证件编号、社会信用代码等。
# -*- coding: UTF-8 -*-from aip import AipOcr # 定义常量APP_ID = '11352343'API_KEY = 'Nd5Z1NkGoLDvHwBnD2bFLpCE'SECRET_KEY = 'A9FsnnPj1Ys2Gof70SNgYo23hKOIK8Os' # 初始化AipFace对象aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) # 读取图片filePath = "2-10.jpg" def get_file_content(filePath): with open(filePath, 'rb') as fp: return fp.read() options={} result=aipOcr.businessLicense(get_file_content(filePath),options)print(result) for key in result['words_result']: print(key+':'+str(result['words_result'][key]['words']))以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。
声明:本页内容来源网络,仅供用户参考;我单位不保证亦不表示资料全面及准确无误,也不保证亦不表示这些资料为最新信息,如因任何原因,本网内容或者用户因倚赖本网内容造成任何损失或损害,我单位将不会负任何法律责任。如涉及版权问题,请提交至online#300.cn邮箱联系删除。
python实现连连看辅助–图像识别延伸(百度AI),供大家参考,具体内容如下百度AI平台提供图片相似检索API接口,并有详细的API文档说明,可以更好的实现图
现在百度ai特别强大,很多大公司都是调用百度的数据,那么对于习惯易语言的我们改怎么操作呢?今天以百度ai文字识别为例。首先打开百度ai平台注册或登录百度账号,进
本文实例为大家分享了python实现简单的文字识别的具体代码,供大家参考,具体内容如下Python版本:3.6.5百度云提供的文字识别技术,准确率还是非常高的,
百度AI功能还是很强大的,百度AI开放平台真的是测试接口的天堂,免费接口很多,当然有量的限制,但个人使用是完全够用的,什么人脸识别、MQTT服务器、语音识别等等
本文实例为大家分享了Python实现最简单的文字识别的具体代码,供大家参考,具体内容如下Python版本:3.6.5百度云提供的文字识别技术,准确率还是非常高的