Towards a Joint Khmer Text Recognition and Word Segmentation

The paper introduces a unified model that jointly performs Khmer text recognition and word segmentation, eliminating the need for a separate segmentation step. Using a connectionist-temporal-classification decoder, the model can be instructed to output Khmer text with or without word boundaries. Experiments across document, scene, and handwritten image datasets demonstrate that the model accurately recognizes characters and locates word boundaries, reducing error and latency compared to traditional sequential pipelines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• rag
• computer-vision
• benchmarks