SCIENCEBRING   /   HAMBURG, GERMANY
Login Register
International Journal of Advance Scientific Research SCIENTIFIC IDEAS. INTERNATIONAL PERSPECTIVES.
ISSN 2750-1396 12 issues per year · Monthly
Crossref DOI: 10.37547/ijasr
Submit Manuscript ↗

Search the Journal
Articles Published:

AI-Powered Software Testing Frameworks for Enhancing Quality, Reliability, and Development Efficiency

Vol. 6 No. 08 (2026): Volume 06 Issue 08 Pages 139-149
Authors
  • Nguyen Minh Anh
    Department of Artificial Intelligence, Vietnam Institute of Digital Technology, Hanoi, Vietnam
  • Tran Quang Huy
    Department of Computer Science and Intelligent Systems, Advanced Technology University, Ho Chi Minh City, Vietnam
RESEARCH OVERVIEW

Abstract

The increasing complexity of software systems has created substantial challenges for conventional testing approaches, particularly in environments characterized by frequent releases, heterogeneous software artifacts, and continuously changing requirements. AI-powered software testing provides a potential mechanism for improving test analysis, automation, defect identification, and development efficiency by incorporating machine learning, deep learning, reinforcement learning, and adaptive decision-making techniques into testing workflows. This research and review paper develops a conceptual framework for AI-powered software testing by synthesizing the supplied literature on deep learning, segmentation, recognition, clustering, attention mechanisms, and AI-driven test automation. Although much of the reviewed literature originates from document-image analysis rather than software testing, its methodological contributions are relevant to the broader design of intelligent testing pipelines because they demonstrate how complex, noisy, and structured information can be automatically segmented, classified, and interpreted. The analysis positions AI-powered testing as a multi-layer framework consisting of test-input processing, intelligent test generation, execution and observation, defect-oriented analysis, adaptive prioritization, and continuous feedback. The findings indicate that deep learning can support complex pattern recognition, while reinforcement learning and attention-based mechanisms can potentially improve adaptive test selection and resource allocation. However, limitations involving data dependency, explainability, generalization, computational cost, and integration complexity remain significant. The paper concludes that effective AI-powered testing should be designed as a human-supervised, feedback-driven framework rather than as a completely autonomous replacement for software quality engineering.

Keywords

  • Artificial Intelligence
  • Software Testing
  • Test Automation
  • Machine Learning
SOURCES & CITATIONS

References

1. Abtahi, F., Zhu, Z., & Burry, A. M. (2015). A deep reinforcementlearning approach to character segmentation of license plateimages. InProceedings of the International Conference onMachine Vision Applications, 539–542.
2. Al-Rawi, M., Bazazian, D., & Valveny, E. (2019). Can generativeadversarial networks teach themselves text segmentation. InIEEE/CVF International Conference on Computer VisionWorkshop, 3342–3350.
3. Alberti, M., Seuret, M., Pondenkandath, V., Ingold, R., & Liwicki,M. (2017). Historical document image segmentation withLDA-initialized deep neural networks. InProceedings of theInternational Workshop on Historical Document Imagingand Processing,95–100.
4. Badjatiya, P., Kurisinkel, L. J., Gupta, M., & Varma, V. (2018).Attention-based neural text segmentation. InProceedings of theEuropean Conference on Information Retrieval, 180–193.
5. Bhat, S. S., & Balachandra Achar, H. V. (2016). Characterrecognition and Period prediction of ancient KannadaEpigraphical scripts.In National Conference on Recenttrends in Technology,3.
6. Chandrakala, H. T., & Thippeswamy, G. (2019). Deep convolutionalneuralnetworksforrecognitionofhistoricalhandwrittenkannadacharacters. InFrontiers in Intelligent Computing: Theory andApplications. Advances in Intelligent Systems and Computing,1014.
7. Chen, K., Liu, C., Seuret, M., Liwicki, M., Hennebert, J., & Ingold,R. (2016). Page segmentation for historical document imagesbased on superpixel classification with unsupervised featurelearning. InProceedings of the IAPR Workshop on DocumentAnalysis Systems,299–304.
8. Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of ComputerVision,59, 167–181.
9. Hu, R., Odobez, J.-M., & Gatica-Perez, D. (2017). Extracting mayaglyphs from degraded ancient documents via imagesegmentation.ACM Journal of Computational. Cultural.Heritage,10,71–93.
10. Jo, J., Koo, H. I., Soh, J. W.,et al.(2020). Handwritten textseg mentation via end-to-end learning of convolutional neural networks. Multimedia Tools Applications,79, 32137–32150.
11. Kavitha, A. S., Shivakumara, P., Kumar, G. H., & Lu, T. (2016). Textsegmentation in degraded historical document images. Egyptian Informatics Journal,17, 189–197.
12. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems,6,1097–1105.
13. Li, X., Zhang, X., Yang, B., & Xia, S. (2017). Characterse gmentation in text line via convolutional neural network. In Proceedings of the International Conference on Systemsand Informatics, 1175–1180.
14. Likforman- Sulem, L., Zahour, A., & Bruno, T. (2007). Text linesegmentation of historical documents: A survey. International Journal on Document Analysis and Recognition,9,123–138.
15. Manigandan, T. V. V. D. V. N. B., Vidhya, V., Dhanalakshmi, V., &Nirmala, B. (2017). Tamil character recognition fromancient epigraphical inscription using OCR and NLP. InProceedings of the International Conference on Energy, Communication, Data Analytics and Soft Computing,1008–1011.
16. Mohana, H. S., Navya, K., Rajithkumar, B. K., & Nagesh, C. (2014). Interactive segmentation for character extraction in stoneinscriptions. InProceedings of the International Conferenceon Current Trends in Engineering and Technology,87–96.
17. Murthy, K. S., & Kumar, H. (2004). Nearest neigh bouring clustering based approach for line and character segmentation inepigraphical scripts. InThe Proceedings of International Conference on Cognitive Systems, 132–140.
18. Ramamurthy, K. (2023). AI-Driven Test Automation Frameworks for the Modern Software Quality Engineering. International Journal of Emerging Trends in Computer Science and Information Technology, 4(4), 257-269.
19. Philip, P. G. (2024). Artificial Intelligence-Driven Project Risk Prediction Models: Enhancing Decision-Making Accuracy in Large-Scale Infrastructure Projects . American Journal of Technology, 3(1), 52–69. https://doi.org/10.58425/ajt.v3i1.571
DISCOVER RELATED RESEARCH

Similar Articles

Continue exploring the collection ↗
21-30 of 342
CONTINUE YOUR READING

Most read articles by the same author(s)

Explore more published work ↗