Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection

TL;DR

This paper introduces a clustering-based feature learning method that leverages prior knowledge from a font library to improve the detection of Oracle Bone Inscriptions in degraded images, enhancing existing detection frameworks.

Contribution

It presents a novel clustering-based feature representation learning approach that utilizes a font library dataset to improve detection accuracy of OBIs in challenging conditions.

Findings

Significant performance improvements across three detection frameworks.

Effective handling of noise and degradation in OBI images.

Enhanced feature extraction through clustering-based loss function.

Abstract

Oracle Bone Inscriptions (OBIs), play a crucial role in understanding ancient Chinese civilization. The automated detection of OBIs from rubbing images represents a fundamental yet challenging task in digital archaeology, primarily due to various degradation factors including noise and cracks that limit the effectiveness of conventional detection networks. To address these challenges, we propose a novel clustering-based feature space representation learning method. Our approach uniquely leverages the Oracle Bones Character (OBC) font library dataset as prior knowledge to enhance feature extraction in the detection network through clustering-based representation learning. The method incorporates a specialized loss function derived from clustering results to optimize feature representation, which is then integrated into the total network loss. We validate the effectiveness of our method by conducting experiments on two OBIs detection dataset using three mainstream detection frameworks: Faster R-CNN, DETR, and Sparse R-CNN. Through extensive experimentation, all frameworks demonstrate significant performance improvements.