CV-Powered Logo Generation Engine

Offering an automated logo generation solution for companies.

Yuliya Sychikova
COO @ DataRoot Labs
17 May 2020
4 min read
CV-Powered Logo Generation Engine
Client Services
Industries
Entertainment

Summary

  • While most presume that logotype drawing is more of an art than science, our client decided to challenge that notion by offering an automated logo generation solution for companies from any industry.
  • Our team was tasked with building a platform that would automatically generate company logos by identifying the most common logo features for each industry and use those features when generating new logotypes.
3
Months
6
Engineers
5+
Technologies

Tech Stack

Gensim
OpenCV
Scikit-learn
TensorFlow
Python

Timeline

1 Week
Data Gathering Pipeline Design
Data Engineer
1 Week
Data Gathering
Data Engineer
1 Week
Data Labelling and Processing
Data Engineer
1 Week
Data Augmentation
Data Engineer
1 Week
Solution Architecture Design
Solution Architect
2 Weeks
Architecture Modelling
Deep Learning Researcher
2 Weeks
Training & Tuning Cycle
Deep Learning Researcher
3 Weeks
Logo Rendering Engine Development
Deep Learning Engineer
4 Weeks
Web App Development
Backend Developer
Frontend Developer

Tech Challenge

  • By using a small dataset of 5K logos, the model had to learn how to generate relevant and appealing company logos.
  • Generation had to be based on the name of the company and the industry it represents while identifying and analyzing the dependencies of the color, font, and icons relevant for the industry.
  • Using OpenCV + Tensorflow based GAN to generate unseen logo suggestions.

Solution

  • By using a disentangled variational auto-encoder, we determined the features of each ring.
  • Then, we created a vector space based on the values of the bottleneck layer, which laid the foundation for the recommendations system.
  • Exposed 1GB model with TF Serving on top of CGP, achieving seamless inference with CPU only.

Impact

  • data root labs built a system that generates logos based only on the name of the company and the industry it represents.
  • The solution not only provided a magnitude of potential logo choices to the companies but also enabled them to save money and time on professional designers.

Have an idea? Let's discuss!

Book a meeting
Yuliya Sychikova
Yuliya Sychikova
COO @ DataRoot Labs
Do you have questions related to your AI-Powered project?

Talk to Yuliya. She will make sure that all is covered. Don't waste time on googling - get all answers from relevant expert in under one hour.
OR
Send us a note
Optional
File requirements pdf, docx, pptx

Author

Yuliya Sychikova
COO @ DataRoot Labs
Yuliya is a co-founder and COO of DataRoot Labs, where she oversees operations, sales, communication, and Startup Venture Services. She brings onboard business and venture capital experience that she gained at a leading tech investment company in CEE, where she oversaw numerous deals and managed a portfolio across various tech niches including AI and IT service companies.

Co-Authors

Ivan Didur
CTO @ DataRoot Labs
offices map
Kyiv (HQ)
Max Frolov
CEO @ DataRoot Labs
Tel Aviv
Ivan Didur
CTO @ DataRoot Labs
builds and implement AI-powered systems across different verticals to help our clients operate effectively.
GoodFirms Badge