Success Stories

#1. Retail Traffic Counter

PROJECT DOMAIN: Artificial Intelligence / Machine Learning / Deep Learning

Customer: Japanese Company

Description: Counting people entering and exiting a store help boost in-store analytics & facilitate marketing segmentation. This is a problem of the detection and tracking people from surveillance videos. In order to solve the problem of detecting people in each video frame, Deep Learning approach is used. In details, a detection engine is built by making uses of TensorFlow’s Object detection API/ Faster R-CNN. After recognizing people and PeopleID is generated, SORT/ deep SORT, a tracking algorithm for 2D multiple object tracking in video sequences, is applied for real-time tracking people. The project is now going to evaluation phase.

Technical Used: TensorFlow, OpenCV, Python.

#2. AI-OCR – Printed text and Handwriting Recognition

PROJECT DOMAIN: Artificial Intelligence / Machine Learning / Deep Learning

Customer: Japanese Company

Description: Development of an off-line handwritten recognition engine that can automatically read English handwritten prescription from scanned/captured images. We form a perfect combination of OCR engine, deep learning, computer vision algorithms and Deep Neural Network to process document content much more precisely and comprehensively. Regardless of the quality of the original documents, whether printed text, hand-written text or poor-quality images, we are able to extract text with a high accuracy rate. 

Technical Used: LSTM, OpenCV, Python.

#3. Rubber Stamp Removal

PROJECT DOMAIN: Artificial Intelligence / Machine Learning / Deep Learning

Customer: Japanese Company

Description: The project aims to develop an engine that can automatically detect & remove rubber stamp from scanned/captured document images.. There are many challenging that we have to cope with in this project. For example, no any standards for rubbers so far (e.g. the variety of rubber shapes, colors) or especially dealing with both scanned and captured images are also a big challenging. After trying several methods and considering between two important metrics (accuracy and performance), we finally deployed YOLOv3 for object detection step and making use of K-means scikit-learn and OpenCV for output generation.

Technical Used: YOLOv3, OpenCV, Python, Scikit-Learn.

#4. Reading Insurance Card

PROJECT DOMAIN: Artificial Intelligence / Machine Learning / Deep Learning

Customer: Japanese Company

Description: Reading information from Insurance Cards is a problem of OCR (Optical Character Recognition) for Japanese Words. In order to read the 3 information from Insurance Card, Deep Learning approach is used. In details, we use Tesseract engine to read all information from the card and then employ some combination/ modification features to improve the recognition results. The improvement is basically based on “try and improve” process based on real data that we collected from Internet.

Technical Used: Tesseract, TensorFlow, OpenCV, Python.

#5. Dental Classification

PROJECT DOMAIN: Artificial Intelligence / Machine Learning / Deep Learning

Customer: Japanese Company

Description: The project aims to develop an engine that can automatically detect & remove rubber stamp from scanned/captured document images.. There are many challenging that we have to cope with in this project. For example, no any standards for rubbers so far (e.g. the variety of rubber shapes, colors) or especially dealing with both scanned and captured images are also a big challenging. After trying several methods and considering between two important metrics (accuracy and performance), we finally deployed YOLOv3 for object detection step and making use of K-means scikit-learn and OpenCV for output generation.

Technical Used: TensorFlow, OpenCV, Python, YOLOv3.

#6. Pneumonia Detection

PROJECT DOMAIN: Artificial Intelligence / Machine Learning / Deep Learning

Customer: Japanese Company

Description: The project aims to build an algorithm to detect a visual signal for pneumonia in medical images. Specifically, the algorithm needs to automatically locate lung opacities on chest radiographs. The dataset size is set around 23,124 images while the validation size is 2,560 images. To solve the problem, we built our own U-Net with the enhancement of resblock to improve the accuracy of the algorithm. The result based testing dataset (1000 images) is very positive (f2 score ~0.2)

Technical Used: U-Net, Keras, OpenCV.

#7. E-commerce & Management System

PROJECT DOMAIN: Business Management System

Customer: Viettel ICD – The biggest Vietnamese Tele-Communication Company

Description: This system is built for Viettel IDC, the biggest telecommunication company in Vietnam. This manages a large range of internet application to compete directly with the world’s leading companies such as Amazon, Azure, etc. Some important features are listed as below: automated service management system (Cloud server, VPS, email, hosting, web hosting, domain, backup etc.). End users can easily register services, do payment and manage registered services. The system help to easily manage costs, expand and scale resources as needed.

Technical Used:

  • Business logic: Microsoft .NET 4.0/C#, C++
  • Web-based user interface: HTML5/CSS3, JQuery, JavaScript, Bootstrap3
  • Development toolchain: Visual Studio 2013, SSMS 2012

#8. BIG DATA PLATFORM & VIDEO RECOMMENDATION SYSTEM

PROJECT DOMAIN: Big Data/ Artificial Intelligence / Machine Learning / Deep Learning

Customer: Vietnamese Company

Description: 

Big Data Platform: Craw, collect, store, and analyse data from a variety of different data sources in real-time. Provide wide range of “bigdata reports” in real-time for the Company key stakeholders in order to help them make quick and accurate decisions to improve the business outcome.

Video Recommendation System: The Recommendation System for Video is developed upon Bigdata platform/technologies. This system gives personalised recommendation for customers on Web, OTT App, and Set-top-box platforms based on the customer history, the information of genre, content, and other similar user history also giving upcoming trending for customer.

Technical Used: Hadoop, Spark, Cassandra, Kafka, HBASE.

#9. HR MANAGEMENT SYSTEM

PROJECT DOMAIN: Business Management System

Customer: German recruitment firm, with around 1500 employees.

Description: The Project is to develop online HR portal product for all employees, administrators and managers for interaction, administration, and management. Key features include: Contract creation & management, face recognition, timesheet & payroll management, expense management, report & analysis, etc.

Technical Used:C#, .NET, jQuery, MySQL, Microsoft Cognitive Services, Microsoft Azure

#10. INTELLIGENT TRAFFIC SYSTEM

PROJECT DOMAIN: Big Data/ Artificial Intelligence / Machine Learning / Deep Learning /  IoT

Customer: Germany Company

Description: NetState is based on an interpretation of the network as a special recurrent neural network consisting of ∑-Π-neurons . It is realized through the cooperation of a nonlinear recurrent neural network and an enhanced version of a linear recurrent error-propagation network. Because of the neural network structure, the model can easily be implemented on a multi-processor computer. The visualization of the dynamic network states is done in 3D by means of colored fluids that flow through glass cuboids.

Technical Used: Microsoft WPF & WCF, C++, OpenGL.

#11. SITRAFFIC SX CONTROLLER

PROJECT DOMAIN:Big Data/ Artificial Intelligence / Machine Learning / Deep Learning /  IoT

Customer: German Company

Description: Sitraffic sX is part of the wider web-based Sitraffic offering from Siemens, which enables even small cities to implement traffic control. This system also includes the option of setting up a virtual traffic control center for those without their own control center.

Technical Used: GWT, LiNUX, PHP, C++

#12. BAGGAGE HANDLING SYSTEM

PROJECT DOMAIN: Big Data/ Artificial Intelligence / Machine Learning / Deep Learning /  IoT

Customer: Germany Company

Description: Baggage handling system is Siemens smart baggage handling system, deployed at international airports around the world. This system provides many advanced tools for baggage check in, sorting, tracking, loading and also various IT modules to control & manage. System handles hundred of cargo portfolios and fullfil IT and control solutions for manual or fully automatic systems.

Technical Used:ORACLE, Smartgwt, Java (J2EE), Javascript.

#13. ORDER MANAGEMENT SYSTEM

PROJECT DOMAIN: Business Management System

Customer: A biggest Vietnamese Logistic Company

Description: Development of an order management system (OMS) that receives customer’s orders for goods, then automates and streamlines order processing to suitable post office and post man. The whole process from order receiver and completing shipping to clients are also managed in this system.

Technical Used: Angular 6, C# Web API, Entity Framework, SQL Server.

#14. Smart City Management System

PROJECT DOMAIN: Business Management System

Customer: Japanese Company

Description: Development of a Town Management System to realize the evolution of a smart cities. Utilizing technology for creation of services such as Concierge service, SNS, Securities. Development of Management website and providing service APIs for further integration.

Technical Used: 

  • Android – Java / iOS – Swift
  • Backend: PHP, Node.JS
  • Database: Amazon Aurora MySQL
  • Cloud: Amazon Elastic Compute Cloud (EC2)
  • 安らかな API

Why choose us

Our Rich Experience
& High Quality
  • 20+ years experience in Software Industry
  • Current Partner with Siemens for many enterprise systems and adapt with their top-global requirements for quality
Save your IT Investment with us

Let’s success together with our reasonable prices but still maintain the top quality and high commitment

Our Professional Process Management

You can choose any world-class popular project management methodology such as Agile or Waterfall to work with us

REQUEST A CALL BACK