Large Scale Font Independent Urdu Text Recognition System

OCR algorithms have received a significant improvement in performance recently, mainly due to the increase in the capabilities of artificial intelligence algorithms. However, this advancement is not evenly distributed over all languages. Urdu is among the languages which did not receive much attention, especially in the font independent perspective. There exists no automated system that can reliably recognize printed Urdu text in images and videos across different fonts. To help bridge this gap, we have developed Qaida, a large scale data set with 256 fonts, and a complete Urdu lexicon. We have also developed a Convolutional Neural Network (CNN) based classification model which can recognize Urdu ligatures with 84.2% accuracy. Moreover, we demonstrate that our recognition network can not only recognize the text in the fonts it is trained on but can also reliably recognize text in unseen (new) fonts. To this end, this paper makes following contributions: (i) we introduce a large scale, multiple fonts based data set for printed Urdu text recognition;(ii) we have designed, trained and evaluated a CNN based model for Urdu text recognition; (iii) we experiment with incremental learning methods to produce state-of-the-art results for Urdu text recognition. All the experiment choices were thoroughly validated via detailed empirical analysis. We believe that this study can serve as the basis for further improvement in the performance of font independent Urdu OCR systems.

Intelligent EHRs: Predicting Procedure Codes From Diagnosis Codes

In order to submit a claim to insurance companies, a doctor needs to code a patient encounter with both the diagnosis (ICDs) and procedures performed (CPTs) in an Electronic Health Record (EHR). Identifying and applying relevant procedures code is a cumbersome and time-consuming task as a doctor has to choose from around 13,000 procedure codes with no predefined one-to-one mapping. In this paper, we propose a state-of-the-art deep learning method for automatic and intelligent coding of procedures (CPTs) from the diagnosis codes (ICDs) entered by the doctor. Precisely, we cast the learning problem as a multi-label classification problem and use distributed representation to learn the input mapping of high-dimensional sparse ICDs codes. Our final model trained on 2.3 million claims is able to outperform existing rule-based probabilistic and association-rule mining based methods and has a recall of 90@3.