Face analysis application

The client wanted to use initial research by the CHI Software team to develop a custom face detection solution, scalable according to their business needs.

Project background

Photographers usually take more than a thousand pictures at an event, party, or at festive celebrations. It’s very challenging to find the needed photos among so many files.  

Our client, a Japanese company, provides photo services at schools, kindergartens, camps, and various children’s events. The client wanted to use our initial research to develop a custom face detection solution, scalable according to their business needs.  

The system has to work with such complex cases as detection and recognition of small, rotated, collapsed faces, as well as faces detection in group photos.

The general app workflow: 

  1. Photographers conduct photo sessions and upload photos to the system.
  2. Parents log in to select 1-2 photos with their children.
  3. Upon a request from the parents, the system returns the results of all found and recognized faces.
  • May 2020 – Ongoing
  • Japan
  • Photography
  • Amazon
  • Kairos
  • Azure
  • Open CV
  • Docker
  1. Face detection
  2. Face recognition of not-frontal faces
  3. Face recognition of overlapped faces
  4. Small faces recognition
  5. Children with emotions recognition
  6. Face (and image) is turned in the roll direction
  7. Image in more than Full HD resolution
  8. Face captures big area on the image

Business needs

The company’s photographers usually take more than a thousand pictures at an event, and it’s challenging for parents to find their kid’s photos among so many files.  

  • Our client was looking for the best way to improve face recognition accuracy for picking the right child’s photos.  
  • Our client needed to improve both solution efficiency and face recognition accuracy.  

To begin with, the CHI Software team conducted a study to find a service for improving the accuracy of face recognition in photographs. We conducted a comparative review of Azure, Amazon, and Kairos APIs to figure out the best way to address the following issues: full face recognition, the number of people in the photo, and the size of the face on the photodetector. We evaluated a custom software solution to cover all the above-mentioned issues. After that, our team proceeded to the system development phase. To increase solution efficiency and face recognition accuracy, we did the following:

  • check
    We set up a cloud environment for development and product hosting. We recommended AWS EC2 as an infrastructure platform, AWS S3 storage, and RDS database as a server configuration model.
  • check
    We also performed system development and customization. We improved the accuracy of rolled and rotated face recognition (by 45-90 degrees), background recognition, and extremely small or big face detection.
  • check
    We provided opportunities to automate monitoring, analytical and comparative manual processes.
  • check
    After system integration, we are now providing support services.
Client values
  1. CHI Software researched, designed, and developed a face recognition system allowing photographers to upload numerous photos to the cloud.
  2. Thanks to face recognition technology, parents can find their children's pictures and get all the photos much faster.
  3. The solution saves photographers and parents time and improves the client's existing workflow.

Employee testimonial


CHI Software successfully completed the product sourcing phase and offered a custom software solution covering all of the customer's issues. The client selected our facial recognition service as their preferred option for improving current business processes. As a result of our work, we created and launched a face detection and recognition service for Lecre Inc. This Japanese company provides photography services in schools and kindergartens. Therefore, at the center of our product was work with children's faces, their emotions, from very different angles. I’m proud that our system works with such complex cases: detection and recognition of rotated and collapsed faces, faces rotated by 90 degrees (or shots taken from the side), small faces, faces in group photographs. In the future, this solution will be scalable to meet changing business needs of our client.

Hanna Vinokurova Project Manager

Let’s bring your idea to
life together!

    Successfully applied!