10%

Try : Insurtech, Application Development

Edtech(5)

Events(31)

Interviews(10)

Life@mantra(10)

Logistics(1)

Strategy(14)

Testing(7)

Android(43)

Backend(28)

Dev Ops(2)

Enterprise Solution(20)

Frontend(28)

iOS(39)

Javascript(13)

AI in Insurance(26)

Insurtech(57)

Product Innovation(34)

Solutions(13)

Augmented Reality(7)

Customer Journey(7)

Design(6)

User Experience(21)

Artificial Intelligence(95)

Bitcoin(7)

Blockchain(14)

Cognitive Computing(7)

Computer Vision(6)

Data Science(14)

FinTech(41)

Intelligent Automation(25)

Machine Learning(43)

Natural Language Processing(10)

E-health(2)

HealthTech(5)

mHealth(3)

Telehealth Care(1)

MeetUp on Building Apps Using Meteor.JS at Mantra Labs

On July 24, 2016, Mantra Labs organized a MeetUp at their Head-office in Bangalore. Mr. Atul Yadav was the lead speaker at the conference. He kicked off the MeetUp with the keynote Meteor and addressed why Meteor is becoming a mainstream framework? And why developers are going Meteor way. The MeetUp was attended by Web and Mobile development experts, who were eager to know why Meteor?

In his power point presentation he highlighted some of the major points that support developers for choosing Meteor.

He said, “Every developer is looking for a common framework that can be used for the web and mobile – to save time and effort. Meteor is one such framework that solves this problem for the developer community”. “At the same time, this also speeds up the development process for the client”, he added.

Why Meteor?

Meteor is the simplest possible app framework, yet fully-powered “gateway drug” into modern JavaScript development. Even if you don’t end up sticking with Meteor, your mind will be opened to new possibilities after spending some time with it.

Meteor has been built on concepts from other frameworks and libraries in a way that makes it easy to prototype applications. Even Angular and React are not as accessible to a wide range of developers as Meteor is, because of a steeper learning curve, and a bit more abstraction that requires more programming skills to use. Meteor on the other hand is easy to learn and quick to build with, as it is flexible and requires less code, which means less bugs and typically a higher quality and more stable end result.

This framework from JavaScript can help you to get a MVP built quickly, and the framework has the ambition to allow developers to scale their apps well beyond MVP-stage. It is establishing itself as a mainstream development technology on the same level as Rails or even vanilla Node.js.

The reasons why Meteor is hottest frameworks for development in today’s time. The 11 major point on Meteor were:

1. Real Time Web Development:
Meteor is a development framework that has got the distinctive feature of real time development.

2. Develop with a Single Language:
With Meteor, the development process is highly simplified with frontend, backend and database all rolled into one language – Javascript. Another benefit of this feature is that it works equally well for the client side as well as the server side.

3. Avail Smart Packages:
Meteor helps you to create users through and accounts system that is highly simplified. The system makes the process highly simplified. You can also use the smart package to do other things like: Writing CoffeeScript apps etc.

4. Large and Helpful Community:
Meteor has a large and helpful community for you to get on with the basics really fast. There is lots of proper documentation of the framework that makes it really useful.

5. Simplified For Developers:
Javascript is devoid of CSS, HTML and Javascript which makes the development process really simple in Meteor.

6. Easy To Learn:
There is enough community support and by just knowing a single development language, one can learn Meteor with ease.

7. Meteor Is The Framework Of The Future:
With features like real time development and ease of use for developers and users, Meteor is certainly the development framework of the future.

8. Meteor Is Easy To Set Up:
One can easily start creating projects in Meteor as soon as it is installed. This makes the process much simpler and faster.

9. Faster Development and Testing of Lean Products:
Start-ups are mostly looking to develop lean products which are quick to develop and can be test marketed equally quickly. Meteor provides suited solution for lean start-ups. They can create smaller product and test market it, in a short span of time.

10. Meteor for Native Mobile Apps:
A developer can build faster native mobile apps with Cordova integration using meteor.

11. Project Scalability:
Scalability is the prime concern of large projects run by enterprises. Meteor is a highly scalable framework and that is what makes it so highly preferred for large scale projects. In addition to that, meter is soon coming up with a hosting service which shall definitely be an add-on for businesses.

Mr Atul wrapped-up the MeetUp with these highlighted points. Over all the MeetUp was successful.
If any queries on Meteor MeetUp, feel free to approach us on hello@mantralabsglobal.com.

Cancel

Knowledge thats worth delivered in your inbox

Tabular Data Extraction from Invoice Documents

5 minutes, 12 seconds read

The task of extracting information from tables is a long-running problem statement in the world of machine learning and image processing. Although the latest accomplishments in the field of deep learning have seen a lot of success, tabular data extraction still remains a challenge due to the vast amount of ways in which tables are represented both visually and structurally. Below are some of the examples: 

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Invoice Documents

Many companies process their bills in the form of invoices which contain tables that hold information about the items along with their prices and quantities. This information is generally required to be stored in databases while these invoices get processed.

Traditionally, this information is required to be hand filled into a database software however, this approach has some drawbacks:

1. The whole process is time consuming.

2. Certain errors might get induced during the data entry process.

3. Extra cost of manual data entry.

 An invoice automation system can be deployed to address these shortcomings. The idea is to upload the invoice document and the system will read and generate the tabular information in the digital format making the whole process faster and more cost-effective for companies.

Fig. 6

Fig. 6 shows a sample invoice that contains some regular invoice details such as Invoice No, Invoice Date, Company details, and two tables holding transaction information. Now, our goal is to extract the information present in the two tables.

Tabular Information

The problem of extracting tables from invoices can be condensed into 2 main subtasks.

1. Table Detection

2. Tabular Structure Extraction.

 What is Table Detection?

 Table Detection is the process of identifying and locating tables that are present in a document, usually an image. There are multiple ways to detect tables in an image. Some of the approaches make use of image processing toolkits like OpenCV while some of the other approaches use statistical models on features extracted from the documents such as Text Position and Text Characteristics. Recently more deep learning approaches have been used to detect tables using trained neural networks similar to the ones used in Object Detection.

What is Table Structure Extraction?

Table Structure Extraction is the process of extracting the tabular information once the boundaries of the table are detected through Table Detection. The information within the rows and columns is then extracted and transferred to the desired format, usually CSV or Excel file.

Table Detection using Faster RCNN

Faster RCNN is a neural network model that comes from the RCNN family. It is the successor of Fast RCNN created by Ross Girshick in 2015. The name Faster RCNN is to signify an improvement over the previous model both in terms of training speed and detection speed. 

To read more about the model framework, one can access the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

 There are many other object detection model architectures that are available for use today. Each model comes with certain advantages and disadvantages in terms of prediction accuracy, model parameter size, inference speed, etc.

For the task of detecting tables in invoice documents, we will select the Faster RCNN model with FPN(Feature Pyramid Network) as a feature extraction network. The model is pre-trained on the ImageNet corpus using ResNET 101 architecture. The ImageNet corpus is a public dataset that consists of more than 20,000 image categories of everyday objects.  We will therefore make use of a Pytorch framework to train and test the model.

The above mentioned model gives us a fast inference time and a high Mean Average Precision. It is preferred for cases where a quick real time detection is desired.

First, the model is to be trained using public datasets for Table Detection such as Marmot and UNLV datasets. Next, we further fine-tune the model with our custom labeled dataset. For the purpose of labeling, we will follow the COCO annotation format.

Once trained, the model displayed an accuracy close to 86% on our custom dataset. There are certain scenarios where the model fails to locate the tables such as cases containing watermarks and/or overlapping texts. Tables without borders are also missed in a few instances. However, the model has shown its ability to learn from examples and detect tables in multiple different invoice documents. 

Fig. 7

After running inference on the sample invoice from Fig 6, we can see two table boundaries being detected by the model in Fig 7. The first table gets detected with 100% accuracy and the second table is detected with 99% accuracy.

Table Structure Extraction

Once the boundaries of the table are detected by the model, an OCR (Optical Character Reader) mechanism is used to extract the text within the boundaries. The text is then processed using the information that is part of a unique table.

We were able to extract the correct structure of the table, including its headers and line items using logics derived from the invoices. The difficulty of this process depends on the type of invoice format at hand.

There are multiple challenges that one may encounter while building an algorithm to extract structure. Some of them are:

  1. The span of some table columns may overlap making it difficult to determine the boundaries between columns.
  2. The fonts and sizes present within tables may vary from one table to another. The algorithm should be able to accomodate for this variation.
  3. The tables might get split into two pages and detecting the continuation of a table might be challenging.

Certain deep learning approaches have also been published recently to determine the structure of a table. However, training them on custom datasets still remains a challenge. 

Fig 8

The final result is then stored in a CSV file and can be edited or stored according to one’s convenience as shown in Fig 8 which displays the first table information.

Conclusion

The deep learning approach to extracting information from structured documents is a step in the right direction. With high accuracy and low running time, the systems can only learn to perform better with more data. The recent and upcoming advancements in computer vision approaches have made processes such as invoice automation significantly accessible and robust.

About the author:

Prateek Sethi is a Data Scientist working at Mantra Labs. His work involves leveraging Artificial Intelligence to create data-driven solutions. Apart from his work he takes a keen interest in football and exploring the outdoors.

Further Reading:

Cancel

Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top
bot

May i help you?

bot shadow

Our Website is
Best Experienced on
Chrome & Safari

safari icon