Character Transformation Artifact: Perception, Prediction, and Representative Application in Image Quality Assessment

Text screen content images (TSCIs) have been extensively applied in multimedia applications. When a TSCI is compressed by an encoder, the reconstructed image often exhibits changes of text stroke structures, leading to a novel and intriguing distortion, namely character transformation artifact (CTA). Specifically, CTA makes the original characters being transformed into other characters with varying degrees, causing inaccurate or even misleading perception of text semantic information, thereby affecting the quality of TSCIs. This paper systematically focuses on the quantitative representation of CTA for the first time, taking the advanced Versatile Video Coding (H.266/VVC) standard and English text as examples. First, the perceptual forms of CTA and the variation of CTA perceptual degree (CTA-PD) with the quantization parameter (QP) of H.266/VVC are explored. Second, a method for predicting the CTA-PD, referred to as P-CTA-PD, is formulated is formulated by extracting and quantifying the stroke features of distorted characters. Finally, P-CTA-PD is further applied to form a TSCI quality assessment method, namely CTA-based image quality assessment (CTA-IQA). Experimental results demonstrate that P-CTA-PD can achieve high accuracy in predicting perceptual degree of CTA, with an accuracy of 95.64%. Meanwhile, CTA-IQA scores show a stronger correlation with the mean opinion score compared to state-of-the-art quality assessment methods. This paper lays the groundwork for CTA, providing fundamental support for future exploration on CTA for other video coding standards, text types, and application scenarios.