Ekanayake, AMudalige, TDhanawardhana, IJayawardena, SHaddela, P. SShyamalee, T2026-10-302025-07-03A. Ekanayake, T. Mudalige, I. Dhanawardhana, S. Jayawardena, P. S. Haddela and T. Shyamalee, "Contextual Bias Score - A Quantitative Metric for Gender Bias Detection in Visual Datasets," 2025 5th International Conference on Electrical, Computer and Energy Technologies (ICECET), Paris, France, 2025, pp. 1-7, doi: 10.1109/ICECET63943.2025.11471883.979-833153559-9https://rda.sliit.lk/handle/123456789/5378Artificial Intelligence (AI) systems in computer vision often inherit contextual biases from training datasets, resulting in unintended gender associations during visual recognition. This paper introduces the Contextual Bias Score (CBS), a novel metric for quantifying gender bias in image datasets by evaluating object prominence, 3D spatial relationships, and scene-level semantics. Unlike conventional approaches that rely on co-occurrence statistics, CBS integrates object-person spatial features, relative size, depth, and distance with CLIP-based scene embeddings to assess how visual context influences bias. The framework is evaluated across nine experimental approaches using eight COCO-derived datasets, leveraging SHAP-based interpretability, PCA-based feature weighting, and Ridge regression modeling. Approach 9 (SHAP + Ridge) achieves 85% agreement with human-annotated misclassification labels and strong score stability. Validation includes statistical significance testing, human perception alignment, and cross-approach correlation analysis. CBS offers a dataset-independent, interpretable tool for auditing contextual bias in high-impact domains. Limitations include binary gender assumptions and computational overhead (~90 seconds per image), with future work aimed at extending the framework to non-binary and culturally diverse contexts.enContextual biasfairness in AIgender biasmodel interpretabilityobject-person relationshipsscene embeddingsConference Paperdoi: 10.1109/ICECET63943.2025.11471883