Enhancing Historical Image Retrieval with Compositional Cues
This work addresses the limitation of existing retrieval methods for historical images by incorporating non-semantic compositional information, offering an incremental improvement for researchers and archivists in digital humanities.
The paper tackled the problem of historical image retrieval by integrating compositional cues from computational aesthetics, resulting in a method that outperforms content-only approaches in aligning with human perception.
In analyzing vast amounts of digitally stored historical image data, existing content-based retrieval methods often overlook significant non-semantic information, limiting their effectiveness for flexible exploration across varied themes. To broaden the applicability of image retrieval methods for diverse purposes and uncover more general patterns, we innovatively introduce a crucial factor from computational aesthetics, namely image composition, into this topic. By explicitly integrating composition-related information extracted by CNN into the designed retrieval model, our method considers both the image's composition rules and semantic information. Qualitative and quantitative experiments demonstrate that the image retrieval network guided by composition information outperforms those relying solely on content information, facilitating the identification of images in databases closer to the target image in human perception. Please visit https://github.com/linty5/CCBIR to try our codes.