Article Details

Title · Authors · Abstract · Keywords · DOI · References

Image Intelligent Recognition and Its Application in Automated Testing

HUANG Fei

(School of Computer Science, Yangtze University, Jingzhou 434023, China)

Section：Computer Technology · Vol. 2025, Issue 6 · Pages：67-70 · 2096-4706（2025）06-0067-04 · CLC number：TP181；TP391 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2025.06.013

Abstract

The traditional interface automated testing tools have the problems of designing a large number of program scripts and poor compatibility. Therefore, an automated testing method based on Artificial Intelligence model is proposed. This method uses the SAM model for image intelligent recognition, and uses the BERT model for text retrieval matching, which can analyze the specific test interface and extract the image. The image file name is marked as a text dataset in a semi-manual manner, and then text classification training is performed to achieve text-to-image matching. Finally, the automated testing steps are simulated with the help of a graph matching algorithm. The experimental results show that the method has high matching accuracy and is more flexible and convenient than traditional automated testing tools.

Keywords

software testing; intelligent recognition; Machine Learning

References

  1. [1] CRISPIN L, GREGORY J. Agile Software Testing: A Practical Guide for Testers and Agile Teams [M]. Translated by Cui Kang Beijing: Tsinghua University Press, 2009
  2. [2] SPILLNER A，LINZ T，SCHAEFER H. Software Testing Foundations: A Study Guide for the Certified Tester Exam：2nd Edition [M].[S.I.]：Rocky Nook，2007.
  3. [3] CHANDRAPRABHA，KUMAR A，SAXENA S. Data Driven Testing Framework using Selenium WebDriver [J].International Journal of Computer Applications，2015，118（18）：0975-8887.
  4. [4] Lu Meng Design and Implementation of a Selenium based Web Automation Testing System [D]. Beijing: Beijing Jiaotong University, 2020
  5. [5] Zhang Zhongyang Research on Component Recognition Method of Mobile Application Graphic User Interface Based on Deep Learning [D]. Chengdu: Sichuan University, 2021
  6. [6] YEH T，CHANG T-H，MILLER R C. Sikuli: Using GUI Screenshots for Search and Automation [C]//Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology.New York：Association for Computing Machinery，2009：183-192.
  7. [7] KIRILLOV A，MINTUN E，RAVI N，et al. Segment Anything [C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV).Paris：IEEE，2023：4015-4026.
  8. [8] ADHIKARI A，RAM A，TANG R，et al. DocBERT: BERT for Document Classification [J/OL].arXiv:1904.08398 [cs.CL].[2024-08-20].https://doi.org/10.48550/arXiv.1904.08398.
  9. [9] Wu Chenxia Binary Image Features and Their Applications [D]. Hangzhou: Zhejiang University, 2013
  10. [10] Guo Yilun Efficiency analysis of edge detection algorithm based on OpenCV [J]. Science and Technology Innovation, 2019 (1): 87-88

About the authors

Huang Fei (1984-), male, Han ethnicity, from Jingzhou, Hubei, is currently pursuing a master's degree in artificial intelligence and machine learning.