Segmentation-Free Keyword Spotting for Handwritten Documents Based on Heat Kernel Signature

We propose a new segmentation-free method for keyword spotting in handwritten documents based on Heat Kernel Signature (HKS). After key points are located by the key point detector for SIFT on the document pages and the query image, HKS descriptors are extracted from a local patch centered at each key point. In order to locate the positions where the query image appears in document pages, we present a searching method which tries to locate a local zone which contains enough matching key points corresponding to the query image. Our method does not need any pre-processing steps.