Dual Model Medical Invoices Recognition

Abstract

Hospitals need to invest a lot of manpower to manually input the contents of medical invoices (nearly 300,000,000 medical invoices a year) into the medical system. In order to help the hospital save money and stabilize work efficiency, this paper designed a system to complete the complicated work using a Gaussian blur and smoothing–convolutional neural network combined with a recurrent neural network (GBS-CR) method. Gaussian blur and smoothing (GBS) is a novel preprocessing method that can fix the breakpoint font in medical invoices. The combination of convolutional neural network (CNN) and recurrent neural network (RNN) was used to raise the recognition rate of the breakpoint font in medical invoices. RNN was designed to be the semantic revision module. In the aspect of image preprocessing, Gaussian blur and smoothing were used to fix the breakpoint font. In the period of making the self-built dataset, a certain proportion of the breakpoint font (the font of breakpoint is 3, the original font is 7) was added, in this paper, so as to optimize the Alexnet–Adam–CNN (AA-CNN) model, which is more suitable for the recognition of the breakpoint font than the traditional CNN model. In terms of the identification methods, we not only adopted the optimized AA-CNN for identification, but also combined RNN to carry out the semantic revisions of the identified results of CNN, meanwhile further improving the recognition rate of the medical invoices. The experimental results show that compared with the state-of-art invoice recognition method, the method presented in this paper has an average increase of 10 to 15 percentage points in recognition rate.

Efficient Automated Processing of the Unstructured Documents Using Artificial Intelligence: A Systematic Literature Review and Future Directions

“…It means certain data is already labeled with the correct solution. Few supervised learning-based methods reported in the literature are Hidden Markov Model (HMM) [100], [12], SVM [2], [100], Decision Trees [61], and Naive Bayesian methods [10], [81], Conditional Random Fields (CRF) [84], [11]. Semisupervised learning algorithms iteratively apply a supervised learning algorithm with both labeled data and unlabeled data.…”

Multi-Layout Unstructured Invoice Documents Dataset: A Dataset for Template-Free Invoice Processing and Its Evaluation Using AI Approaches

“…Another study [41] Bidirectional LSTM (Bi-LSTM) is another variant of RNN comprising of the forward and backward layers. The forward layer holds the text input sequence, and the backward layer process the input in inverse order.…”

Research on Fast Text Recognition Method for Financial Ticket Image

“…However, due to the large number of tickets closely related to funds, the requirements for the recognition accuracy and speed are high. [22,31,3,14,1,29,8,7] used an RNN, LSTM, an AA-RNN to recognize medical tickets and VAT invoices. However, as mentioned above, due to the diversity of types and complexity of content, these models cannot include all types of tickets.…”