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)

The Clash of Clans: Kotlin Vs. Flutter

First things first – Kotlin is a programing language whereas Flutter is a framework. As frameworks provide solutions to particular problems, you’ll find several inbuilt functions in Flutter to complete an application. And, of course, programming languages know no limit for app development. 

Since May 2019, Google officially supports Kotlin for mobile app development on Android. But, Flutter is an open-source mobile application development framework created by Google itself!

Both Kotlin and Flutter have a ‘Google tag’ attached with them. Therefore, ‘which is better’ is a big question before developers. Reading further, you’ll get to know ‘when’ to use Kotlin or Flutter.

When to use Kotlin?

Kotlin is a cross-platform general-purpose programming language. Although it relies on Java Class Library, its syntax is more concise. Want to know the difference between Kotlin and Java? Here’s your answer.

The scope of app development in Kotlin is unlimited. For instance, Uber’s internal tooling processes (e.g. Annotation processors, Gradle plugins, etc.) are coded in Kotlin. Pinterest app moved from Java to Kotlin to provide users a better interface. 

Source: Pinterest@GooglePlay

Following are the situations where Kotlin supersedes any other programming language for mobile app development.

#1 Adding Features to an Existing App

Kotlin works well and is interoperable with Java and Java components. If you want to add features to an existing app, then instead of revamping the entire architecture or changing the platform, you can simply use Kotlin to solve the purpose.

#2 Simple Syntax for Sophisticated Codes

With intuitive syntax, it is easy to write and deploy new codes in Kotlin. For apps that require heavy coding, Kotlin is simple to maintain. 

#3 Inbuilt Debugging

Kotlin’s fail-fast compiler can search bugs automatically and prevents them from coming again. Thus, Kotlin is safer than Java and reports and resolves crashes instantly.

StackOverflow survey 2019 reveals-  Kotlin is the fourth most loved programing language!

When to use Flutter?

Flutter is a framework developed by google on Dart programming language. Its architecture includes the Dart platform, Flutter engine, Foundation library, and design-specific widgets. Flutter got the spotlight because apps developed in Flutter are compatible with both iOS and Android.

The Flutter framework is capable of building full-fledged applications in different domains like e-commerce, utility, social, and entertainment. For example, Alibaba’s mobile app is built in Flutter.

Image source: Alibaba@GooglePlay

#1 For Building Minimum Viable Product (MVP)

If you want to build an application in minimum possible time, you should go for Flutter. Be it to impress investors, or present prototypes, Flutter is just sufficient (and fast too) to give a clearer idea of the product.

#2 Quick Fixes

Flutter’s hot reload feature allows developers to execute code changes in real-time. If you know, the project will require frequent changes, Flutter can give you quick fixes. 

#3 Easy Set-up

Flutter is easy to set-up, even in low-end PCs. It enables developers to access native features like Geo-location and camera along with additional widget support.

It would be unjust if we don’t discuss the situations where Flutter doesn’t meet developers’ expectations.

At present Flutter is still in its early stages. There aren’t too many CI (Continuous Integration) Platforms (e.g. Jenkins and Travis) that support it. Flutter, although makes it easy to build apps for android and iOS, does not cover web-apps. Therefore, Flutter is a misfit for businesses that require both mobile and web applications.

Now that Kotlin vs. Flutter is a hot-topic, should ‘React JS’ feel left out?

React JS, which is backed by Facebook was once popular for developing mobile user interfaces. Many developers still prefer React Native, which enables native Android, iOS, and UWP development with React. However, the new-age developers are more inclined towards Kotlin and Flutter.

What Developers say on Kotlin Vs. Flutter

“Dart is just a wannabe amateur hobby me-too project compared to Kotlin.”

Mike Milpot, Software Architect, Inventor

“Apart from the fact that you can still call Android/iOS APIs, building Flutter UIs is a bit more exhaustive than it is on Android.”

Wilberforce Uwadiegwu, Mobile Software Engineer, NCK Tech

“You can of course, use the Flutter knowledge to develop iOS apps later, so it can be a more useful knowledge if you want to focus on mobile development, but learning java will give you a step if you want to work on Back-end web development.”

Maycon Miranda, Web Developer, Bio Extratus

“Currently flutter lacks library/guide when comparing to Kotlin/Java. Therefore sometimes you’ll need to transfer or wrap Android library to flutter by yourself. It’ll make the time of developing your application increased.”

Phạm Anh Minh, Samsung Vietnam Mobile R&D Center

Final Thoughts

Kotlin and Flutter are competitive and are going to be better with every release. Experts say, if you want to strengthen back-end app development skills, you should learn Java followed by Kotlin. Thereafter, with little effort, you’ll automatically get hold of flutter.

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