evilgix / Evil
Licence: mit
Optical Character Recognition in Swift for iOS&macOS. 银行卡、身份证、门牌号光学识别
Stars: ✭ 648
Projects that are alternatives of or similar to Evil
Android Ocrsample
Android OCR example application which uses Google Text Recognition API
Stars: ✭ 100 (-84.57%)
Mutual labels: vision, ocr
Eyevis
Android based Vocal Vision for Visually Impaired. Object Detection, Voice Assistance, Optical Character Reader, Read Aloud, Face Recognition, Landmark Recognition, Image Labelling etc.
Stars: ✭ 48 (-92.59%)
Mutual labels: vision, ocr
craft-text-detector
Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector
Stars: ✭ 151 (-76.7%)
Mutual labels: ocr, vision
Card.io Android Source
The open-source code for the card.io-Android-SDK: provides fast, easy credit card scanning in mobile apps
Stars: ✭ 549 (-15.28%)
Mutual labels: ocr
Crow Translate
A simple and lightweight translator that allows to translate and speak text using Google, Yandex and Bing.
Stars: ✭ 503 (-22.38%)
Mutual labels: ocr
Facecropper
✂️ Crop faces, inside of your image, with iOS 11 Vision api.
Stars: ✭ 479 (-26.08%)
Mutual labels: vision
Deepdrive
Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
Stars: ✭ 628 (-3.09%)
Mutual labels: vision
Receipt Parser Legacy
A supermarket receipt parser written in Python using tesseract OCR
Stars: ✭ 614 (-5.25%)
Mutual labels: ocr
Cudasift
A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)
Stars: ✭ 555 (-14.35%)
Mutual labels: vision
Iowncode
A curated collection of iOS, ML, AR resources sprinkled with some UI additions
Stars: ✭ 499 (-22.99%)
Mutual labels: vision
Trwebocr
开源易用的中文离线OCR,识别率媲美大厂,并且提供了易用的web页面及web的接口,方便人类日常工作使用或者其他程序来调用~
Stars: ✭ 618 (-4.63%)
Mutual labels: ocr
Seglink
An Implementation of the seglink alogrithm in paper Detecting Oriented Text in Natural Images by Linking Segments
Stars: ✭ 479 (-26.08%)
Mutual labels: ocr
Tesseract.js
Pure Javascript OCR for more than 100 Languages 📖🎉🖥
Stars: ✭ 25,246 (+3795.99%)
Mutual labels: ocr
Paddlehub
Awesome pre-trained models toolkit based on PaddlePaddle.(300+ models including Image, Text, Audio and Video with Easy Inference & Serving deployment)
Stars: ✭ 7,284 (+1024.07%)
Mutual labels: vision
Millionheroassistant
百万 / 冲顶 / 芝士 / UC / 万能 答题助手(知识图谱更加专业,自动推荐答案, Android手机自动屏幕适配,模拟器支持,多开)
Stars: ✭ 524 (-19.14%)
Mutual labels: ocr
Evil
Optical Character Recognition in Swift for iOS&macOS.
图片来自于网络,侵删
Requirements
- iOS 11.0+ / macOS 10.13+
- Xcode9.2+
- Swift 4.0+
Installation
Basic Usage
Evil 使用 Vision 框架进行文字识别,因此你需要导入特定的MLModel到你的Xcode工程。例如识别身份证导入识别身份证的model,识别银行卡导入识别银行卡的model。
以下是目前已经训练好的模型
- ChineseIDCard ==> 🇨🇳中国二代身份证号码识别
如何导入
首先从上面的地址下载或者自己训练得到模型文件(*.mlmodel
),然后作为resource资源加入项目。但是模型文件size一般都比较大因此Evil还支持另外一种方式即:运行时从指定的服务器下载对应的模型。
- 获取对应的模型文件并重名命名为
[name].mlmodel
[name]
可通过以下方法获取print(Recognizer.chineseIDCard.name)
- 将模型文件上传至自己的服务器或者CDN并获取下载链接
- 在
info.plist
中配置下载链接如下
初始化
lazy var evil = try? Evil(recognizer: .chineseIDCard)
或者 手动指定下载路径
let downloadURL = URL(string: "https://****/ChineseIDCard.mlmodel")!
let chineseIDCard = Recognizer.custom(name: "ChineseIDCard", model: downloadURL, needComplie: true, processor: Recognizer.cropChineseIDCardNumberArea)
let evil = try? Evil(recognizer: chineseIDCard)
或者直接将模型文件拖入 xcode 项目
let url = Bundle.main.url(forResource: "ChineseIDCard", withExtension: "mlmodelc")!
let evil = try? Evil(contentsOf: url, name: "ChineseIDCard")
注意Extension 为mlmodelc
而不是mlmodel
因为xcode会自动编译mlmodel
文件,并且生成对应的class
. 所以请务必注意Model文件不要和现有的class
重名。
开始识别
let image: Recognizable = .....
let result = evil?.recognize(image)
print(result)
训练模型
参考Tools 目录下PrepareBot
项目
参考博文掘金
交流讨论
1.github issue (推荐)
2.qq 群:641256202
LICENSE
MIT
Copyright 2018 - 2019 Kevin.Gong aoxianglele#icloud.com
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].