USING COMPUTER VISION IN RETAIL ANALYTICS
Norrgård, Marcus (2020)
Norrgård, Marcus
Åbo Akademi
2020
Julkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2020043024685
https://urn.fi/URN:NBN:fi-fe2020043024685
Tiivistelmä
This thesis comprises the creation of a computer vision-based analytics platform for making age and gender-based inference for retail analytics. Computer vision in retail spaces is an emerging field with interesting opportunities for research. The thesis utilizes modern technologies to create a machine learning pipeline for training two convolutional neural networks for classifying age and gender. Furthermore, this thesis examines deployment and inference computing of the trained neural network models on a Raspberry Pi single board computer. The results presented in this thesis demonstrate the feasibility of the created solution.