Application of Optimized GUI Component Identification Method in User Interface Graphic Design.

Saved in:

Bibliographic Details
Title:	Application of Optimized GUI Component Identification Method in User Interface Graphic Design.
Authors:	Jie Song¹ songjie@ahszu.edu.cn, Na Li² li_na0541@hotmail.com
Source:	Engineering Letters. Nov2025, Vol. 33 Issue 11, p4362-4374. 13p.
Subjects:	Graphical user interfaces, Image recognition (Computer vision), Mobile app development, Algorithms, Machine learning, Deep learning
Abstract:	This study addresses the limitations of traditional manual recognition methods in mobile GUI design, which are often time-consuming and prone to errors. We propose an improved deep learning-based algorithm to optimize the detection, localization, and classification of GUI components. The method incorporates an attention mechanism and Complete Intersection over Union (C-IoU) for enhanced accuracy in component recognition. Additionally, we introduce an improved Bidirectional Feature Pyramid Network (BiFPN) and Adaptive Training Sample Selection (ATSS) strategy to improve classification performance. Experimental results show that the optimized detection method achieves a MAP peak at the 45th training round, with the SE76-PP-YOLO algorithm reaching a 93.1% recall, outperforming the comparison algorithm (71.2%). The improved SEBi76-PP-YOLO algorithm achieves a MAP@0.5 of 94.1%, significantly enhancing classification accuracy across GUI components. This work contributes novel techniques to improve GUI component recognition, offering practical applications in mobile app design. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	This study addresses the limitations of traditional manual recognition methods in mobile GUI design, which are often time-consuming and prone to errors. We propose an improved deep learning-based algorithm to optimize the detection, localization, and classification of GUI components. The method incorporates an attention mechanism and Complete Intersection over Union (C-IoU) for enhanced accuracy in component recognition. Additionally, we introduce an improved Bidirectional Feature Pyramid Network (BiFPN) and Adaptive Training Sample Selection (ATSS) strategy to improve classification performance. Experimental results show that the optimized detection method achieves a MAP peak at the 45th training round, with the SE76-PP-YOLO algorithm reaching a 93.1% recall, outperforming the comparison algorithm (71.2%). The improved SEBi76-PP-YOLO algorithm achieves a MAP@0.5 of 94.1%, significantly enhancing classification accuracy across GUI components. This work contributes novel techniques to improve GUI component recognition, offering practical applications in mobile app design. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X