Digital Repository

UIDTECT - Automating User Interface Design Violation Detection for Mobile Applications

Show simple item record

dc.contributor.author Shanaz, Nabeel
dc.date.accessioned 2024-04-29T09:53:45Z
dc.date.available 2024-04-29T09:53:45Z
dc.date.issued 2023
dc.identifier.citation Shanaz, Nabeel (2023) UIDTECT - Automating User Interface Design Violation Detection for Mobile Applications. BSc. Dissertation, Informatics Institute of Technology en_US
dc.identifier.issn 2019240
dc.identifier.uri http://dlib.iit.ac.lk/xmlui/handle/123456789/2090
dc.description.abstract "The importance of user interface (UI) design in software applications cannot be overstated. It plays a pivotal role in shaping the user experience and overall usability of an application. Sadly, many developers, whether experienced or novice, often overlook fundamental UI design principles, leading to subpar user interfaces. These poor UI designs frequently result in users having a negative experience, which, in turn, discourages return visits and can ultimately hinder the success of an application. To tackle this issue, a novel research proposal presents a comprehensive system that combines the capabilities of object detection and rule-based methods to detect UI design violations. Specifically, an object detection model is employed to identify and locate UI elements within UI images. Once these elements are detected, a rule-based system comes into play, applying a set of established UI design guidelines to scrutinize the composition and layout of the user interface, seeking any violations. This combined approach aims to provide developers with actionable insights on how to enhance their UI design effectively. The system's performance, as evaluated, demonstrates its effectiveness, surpassing the capabilities of existing object detection models. It achieves a mean average precision at a 0.5 intersection over union (mAP@0.5) score of 97.2, signifying a higher level of accuracy and precision compared to its counterparts. This system is poised to bridge the existing gap in detecting UI design violations across both Android and iOS mobile application interfaces. By helping developers identify and rectify UI design flaws, it holds the promise of significantly improving the user experience and overall usability of software applications." en_US
dc.language.iso en en_US
dc.subject Graphical User Interface en_US
dc.subject Object Detection en_US
dc.subject Deep learning en_US
dc.title UIDTECT - Automating User Interface Design Violation Detection for Mobile Applications en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search


Advanced Search

Browse

My Account