CV-Powered Logo Generation Engine
Offering an automated logo generation solution for companies.
AI R&D Center
17 May 2020
6 min read
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.
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
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.
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
Important copyright notice © DataRoot Labs and datarootlabs.com, 2024. Unauthorized use and/or duplication of this material without express and written permission from this site’s author and/or owner is strictly prohibited. Excerpts and links may be used, provided that full and clear credit is given to DataRoot Labs and datarootlabs.com with appropriate and specific direction to the original content.
Author
AI R&D Center
Our team shares experiences and insights on how AI and ML change and shape new markets, optimize various industries and our lives.
Co-Authors
CTO @ DataRoot Labs