问题描述
我正在将 ML Kit for Firebase 用于我的 Android 应用程序(ReCalc:收据计算器),除了斜线零的情况外,它的性能非常好.在大约一半或更多的情况下,它会将斜杠零识别为八.
I'm using ML Kit for Firebase for my Android app (ReCalc: Receipt Calculator) and it performs very well except in the case of slashed zero.In around half or more of the cases it recognizes slashed zero as eight.
我的一个主意是将包含零区域的矩形切成薄片,并检测正好位于中间上方和下方的区域是否较暗.但是实际上...
One idea I have is to slice the rectangle containing the zero in regions and detect whether the regions just above and below the middle are dark or not.But actually...
我正计划训练模型以对零和八进行分类.
这是很多工作,因此我决定首先在这里要求其他解决方案/想法.
This is a lot of work thus I decided first to ask here for another solution/idea.
这里是一个例子:
类似的问题: Tesseract OCR混淆了将0减为8
推荐答案
最后,我自己训练了一个模型.
Finally I've trained a model myself.
其准确性非常好(超过98%).但是,我担心它的概括性如何.
Its accuracy is pretty good (more than 98%). However I have concerns how well it generalize.
这是项目: ZEC-斜零分类器
我还创建了一个显示如何在Android上使用该模型的应用程序: ZECA-斜零分类器对于Android
I've created also an application showing how to use the model on Android: ZECA - Slashed Zero-Eight Classifier for Android
这篇关于如何在 OCR 中区分斜线零和八 (0-> 8)的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!