SCD: Statistical color distribution-based objective image colorization quality assessment

Lyu, Hongjin, Elangovan, Hareeharan, Rosin, Paul ORCID: https://orcid.org/0000-0002-4965-3884 and Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 2025. SCD: Statistical color distribution-based objective image colorization quality assessment. Presented at: Computer Graphics International, Geneva, Switzerland, 1-5 July 2024. Advances in Computer Graphics. Lecture Notes in Computer Science , vol.15338 Springer, pp. 54-67. 10.1007/978-3-031-81806-6_4

Preview

PDF - Accepted Post-Print Version Download (21MB) | Preview

Abstract

Colorization research has long been a focal point in computer vision and image processing. However, due to its inherently ill-posed nature, a reasonable assessment of the quality of their outcomes remains a challenge. Subjective evaluations are often restricted to a limited number of participants due to the high costs. This along with the existence of individual differences and subjective biases makes it difficult to derive convincing conclusions. Despite no need for participants in objective evaluation metrics, the currently widely applied objective metrics fail to accurately reflect the quality of colorization results, thereby impeding the attainment of consistency with subjective user opinions. Facing the above problems, we propose a novel Statistical Color Distribution-based Objective Evaluation Metric (SCD) for better consistency with human opinions. We first segment images into semantic regions. For each semantic type, a novel two-dimensional natural color distribution w.r.t. hue and saturation is collected to better align with human perceptual observations during image assessment. An adjacency weighted matrix considering surrounding neighboring regions smooths the color distribution table, enabling a more reliable quality assessment. The application of probability density eliminates the issue of frequency anomalies caused by human visual insensitivity, ensuring more accurate evaluation.Through extensive and comprehensive experiments involving two distinct datasets with the participation of 1321 volunteers, this paper demonstrates that the proposed SCD is more consistent with subjective user opinions compared with current objective metrics for evaluating colorization.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	Springer
ISBN:	978-3-031-81805-9
Date of First Compliant Deposit:	18 July 2024
Date of Acceptance:	5 June 2024
Last Modified:	08 Apr 2025 14:30
URI:	https://orca.cardiff.ac.uk/id/eprint/170665

Actions (repository staff only)

Edit Item