Palmprint decomposer separates and edits texture from base appearance

Palmprint Decomposer: Interpretable and Editable Factorization via Synthetic Learning and Instance-Wise Refinement

Computer Vision and Pattern Recognition

Summary

Recognizing palmprints usually means looking at detailed textures, but that makes it hard to change or analyze the background skin separately. The authors created a system called Palmprint Decomposer that breaks a palmprint image into parts, separating the texture from the base skin tone and lighting. They trained it with fake palm images to teach the system exactly what to separate, then refined real photos by adjusting the parts directly. This leads to clear, editable palmprint images that still work well for recognizing people.

What this means in practice

  • For security system engineers: Generate palmprint images with independently editable texture and appearance factors to improve biometric authentication systems.
  • For digital artists: Edit palmprint texture and skin appearance separately in images for customized biometric image synthesis and creative applications.

Authors

Licheng Yan, Yuqi Wang, Jingtao Wang, Bob Zhang, Andrew Beng Jin Teoh, Lu Leng, Shuyi Li, Ziyuan Yang

Abstract

Palmprint recognition and synthesis methods focus on extracting discriminative textures or generating images with varied textures and appearances. However, they do not generally provide an explicit image-level representation that separates palmprint texture from its underlying base appearance for independent analysis or controlled editing. We introduce Palmprint Decomposer, an interpretable framework that represents a palmprint through independently editable factors and reconstructs the image through a multiplicative composition model. A color map and a light map characterize the base appearance, while a structure map and a global texture strength parameter describe texture modulation. However, accurate reconstruction alone does not guarantee separation of palmprint texture from base appearance, as fine palmprint textures may leak into the estimated base appearance. To mitigate this ambiguity, we train the decomposer exclusively on synthetic data with direct factor supervision, using asymmetric decoding paths and decomposition constraints to suppress texture leakage. Instance-Wise Refinement further improves real-image reconstruction by directly optimizing the predicted factors for each input without relying on the trained network. Experiments across seven datasets demonstrate high reconstruction fidelity, with the extracted structure maps generally achieving verification performance comparable to the original images. Compared with existing methods, our approach achieves better factor separation while preserving more discriminative palmprint texture information.