Logo generation and discovery
Summary
Logo concepts from company names and industry context.
The client wanted to connect company and industry inputs with generated logo concepts.
A logo-generation system using company names and industry context to produce visual concepts.
Tech Stack
- Gensim
- OpenCV
- Scikit-learn
- TensorFlow
- Python
Project workstreams
- 01
1 Week
Data Gathering Pipeline Design
Data Engineer - 02
1 Week
Data Gathering
Data Engineer - 03
1 Week
Data Labelling and Processing
Data Engineer - 04
1 Week
Data Augmentation
Data Engineer - 05
1 Week
Solution Architecture Design
Solution Architect - 06
2 Weeks
Architecture Modelling
Deep Learning Researcher - 07
2 Weeks
Training & Tuning Cycle
Deep Learning Researcher - 08
3 Weeks
Logo Rendering Engine Development
Deep Learning Engineer - 09
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.
- The project worked with a dataset of approximately 5,000 logos to explore generation of new visual concepts.
Solution
The delivered system uses company names and industry context as inputs for generating logo concepts.
The project used a dataset of approximately 5,000 logos to explore visual patterns across industries.
Outcome
A system that produces logo concepts from a company name and its industry.
Published