From Pixels to Results: Computer Vision and ML Safeguarding UI Quality
-
-
40 min
Traditional UI testing methods face significant limitations: test fragility, labor-intensive visual regression detection, and issues with dynamic content. The presentation introduces a novel approach based on the integration of Computer Vision (CV) and Machine Learning (ML).
This method allows:
1. Creating robust tests.
2. Detecting visual bugs.
3. Reducing test maintenance time.
4. Improving UI test coverage.
The talk will cover practical examples of CV and ML application in QA, using our product as a case study. The use of CV and ML opens up new opportunities to enhance the quality and efficiency of QA processes. This approach helps overcome the limitations of traditional methods, making tests more reliable and informative. Implementing CV and ML in UI testing is a step towards creating intelligent quality assurance systems that meet the challenges of modern software development.