Accuracy And Bias Of Selfie Detection On  Open Data

Shpot, Natalia-Yana

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Бакалаврська програма "Комп'ютерні науки"
→
2020
→
Перегляд матеріалів

dc.contributor.author	Shpot, Natalia-Yana
dc.date.accessioned	2024-02-15T09:26:55Z
dc.date.available	2024-02-15T09:26:55Z
dc.date.issued	2020
dc.identifier.citation	Shpot, Natalia-Yana. Accuracy And Bias Of Selfie Detection On Open Data / Shpot, Natalia-Yana; Supervisor: Miriam Redi; Ukrainian Catholic University, Department of Computer Sciences. – Lviv: 2020. – 38 p.	uk
dc.identifier.uri	https://er.ucu.edu.ua/handle/1/4515
dc.language.iso	en	uk
dc.title	Accuracy And Bias Of Selfie Detection On Open Data	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	There are many challenges related to the openness of the Wikimedia Commons im- age upload platform, and one of them is about making sure to get high-quality con- tent in. Goes without saying, selfies are not precisely the ideal wanted content for a platform whose aim is to represent the world’s knowledge through pictorial rep- resentations. One way to automatically check the data quality in the domain of computer vision is to design a selfie detector that, given an image, can automatically predict whether it is a selfie or not. Thus in this thesis, we are using state-of-the-art models to create a classifier that, given an image, can say whether the image is a selfie, a person, or neither of that. With such a classifier, it would be easier to auto- matically detect and scale selfies for Wikimedia or other platforms that have humans in the loop to check the quality of user-generated content. In addition to this we ex- amine whether approaches of our choice show bias in demographics such as race, gender, and age. Furthermore, we will introduce two datasets for our project: one containing selfies, pictures with persons and random pictures, and another contain- ing a smaller set of pictures of persons along with the demographic metadata.	uk