A Siamese Network-Based Visual Structure Comparison Approach for Addressing the Dynamic Content Challenge in Web Visual Testing.

Saved in:

Bibliographic Details
Title:	A Siamese Network-Based Visual Structure Comparison Approach for Addressing the Dynamic Content Challenge in Web Visual Testing.
Authors:	LIU, JHONG-YUN¹ john40066@gmail.com, LIN, TI-MO¹ lintimo1999@gmail.com, LEE, SHIN-JIE¹ jielee@mail.ncku.edu.tw, ZHANG, CI-YIN¹ solemn0219@gmail.com, CHU, WEI-TA¹ wtchu@gs.ncku.edu.tw
Source:	Journal of Information Science & Engineering. May2026, Vol. 42 Issue 3, p615-628. 14p.
Subjects:	False positive error, Computer software testing, Internet content, Artificial neural networks
Abstract:	Visual testing for cross-browser testing is an essential part of web automated regression testing. However, there is an inevitable challenge in visual testing, which is "dynamic content." Dynamic content, such as advertisements and news, constantly changes its appearance over and over time. Existing visual testing tools fail to handle dynamic content, and some even treat it as cross-browser incompatibilities (XBIs), then generate false positives warning to developer. Currently there are two types of approaches to identifying dynamic content First, manually marking the positions of dynamic content does not significantly alleviate the developers' workload. Second, repeatedly executing the website on the same browser and regarding different pixels as dynamic content However, this method can lead to false judgments. In this paper, we propose a Siamese network-based comparison approach to detect visual disparities by comparing the visual structures of a webpage rendered by two browsers. This approach can identify cross-browser inconsistencies and accommodate minor element shifts, achieving a high F1-score of 0.9749. A comparison with the usage of structural similarity (SSIM) and multi-scale structural similarity (MSSSIM) is also carried out and discussed. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Information Science & Engineering is the property of Institute of Information Science, Academia Sinica 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:	Visual testing for cross-browser testing is an essential part of web automated regression testing. However, there is an inevitable challenge in visual testing, which is "dynamic content." Dynamic content, such as advertisements and news, constantly changes its appearance over and over time. Existing visual testing tools fail to handle dynamic content, and some even treat it as cross-browser incompatibilities (XBIs), then generate false positives warning to developer. Currently there are two types of approaches to identifying dynamic content First, manually marking the positions of dynamic content does not significantly alleviate the developers' workload. Second, repeatedly executing the website on the same browser and regarding different pixels as dynamic content However, this method can lead to false judgments. In this paper, we propose a Siamese network-based comparison approach to detect visual disparities by comparing the visual structures of a webpage rendered by two browsers. This approach can identify cross-browser inconsistencies and accommodate minor element shifts, achieving a high F1-score of 0.9749. A comparison with the usage of structural similarity (SSIM) and multi-scale structural similarity (MSSSIM) is also carried out and discussed. [ABSTRACT FROM AUTHOR]
ISSN:	10162364
DOI:	10.6688/JISE.202605_42(3).0008