ABHINAW:一种AI生成图像中排版的自动评估方法
ABHINAW: A method for Automatic Evaluation of Typography within AI-Generated Images
AI总结:
针对现有AI生成图像文字排版评估体系的不足,提出名为ABHINAW的新型评估矩阵,通过逐字母匹配、简洁度调整等方法量化文字生成准确率,并分析了高低频词相关的常见错误。
摘要:
在快速发展的生成式AI领域,MidJourney、DALL-E和Stable Diffusion等平台已经革新了文本生成图像(Text-to-Image, T2I)技术。然而,尽管这些平台生成高质量图像的能力令人瞩目,它们往往难以在生成的图像中呈现准确的文字。从理论上讲,如果我们能以“零样本”方式实现AI图像中的准确文字生成,不仅会让AI生成的图像更具意义,还将推动平面设计行业的大众化。实现这一目标的第一步,是构建一个可靠的评分矩阵,用于评估AI生成图像中的文字准确性。虽然已有CLIP SCORE和T2I-CompBench++等基准测试方法,但在系统评估AI生成图像中的文字与排版方面仍存在空白,尤其是针对基于扩散的方法。本文提出了一种专门用于量化AI生成图像中文字与排版生成性能的新型评估矩阵。我们采用逐字母匹配策略,计算参考文本与AI生成文本之间的精确匹配分数。我们的新型评分计算方法可处理多种冗余问题,例如单词重复、大小写敏感、单词混淆、字母不规则嵌入等。此外,我们还开发了一种名为“简洁度调整(brevity adjustment)”的新方法,用于处理多余文本的问题。我们还对高频词和低频词导致的常见错误进行了定量分析。项目页面地址:https://github.com/Abhinaw3906/ABHINAW-MATRIX。
英文摘要:
In the fast-evolving field of Generative AI, platforms like MidJourney, DALL-E, and Stable Diffusion have transformed Text-to-Image (T2I) Generation. However, despite their impressive ability to create high-quality images, they often struggle to generate accurate text within these images. Theoretically, if we could achieve accurate text generation in AI images in a ``zero-shot'' manner, it would not only make AI-generated images more meaningful but also democratize the graphic design industry. The first step towards this goal is to create a robust scoring matrix for evaluating text accuracy in AI-generated images. Although there are existing bench-marking methods like CLIP SCORE and T2I-CompBench++, there's still a gap in systematically evaluating text and typography in AI-generated images, especially with diffusion-based methods. In this paper, we introduce a novel evaluation matrix designed explicitly for quantifying the performance of text and typography generation within AI-generated images. We have used letter by letter matching strategy to compute the exact matching scores from the reference text to the AI generated text. Our novel approach to calculate the score takes care of multiple redundancies such as repetition of words, case sensitivity, mixing of words, irregular incorporation of letters etc. Moreover, we have developed a Novel method named as brevity adjustment to handle excess text. In addition we have also done a quantitative analysis of frequent errors arise due to frequently used words and less frequently used words. Project page is available at: https://github.com/Abhinaw3906/ABHINAW-MATRIX.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。