Handwritten word image matching based on Heat Kernel Signature

• Handwritten word image matching based on Heat Kernel Signature (HKS) is proposed.
• HKS can capture local characteristics of detected keypoints.
• The triangular mesh structure is used to present global characteristics.
• The use of HKS can tolerate large variations in handwritten images.
• Our proposed method does not require pre-processing.

Keyword spotting is an alternative method for retrieving user specified text or query word images, without Optical Character Recognition (OCR), by calculating the similarity between features of word images rather than ASCII content. However, because of unconstrained writing styles with large variations, the retrieving results are always not very satisfactory. In this paper, we propose a novel method, which is based on Heat Kernel Signature (HKS) and triangular mesh structure to achieve handwritten word image matching. HKS can tolerate large variations in handwritten word images and capture local features. On the other hand, the triangular mesh structure is used to present global characteristics. Moreover, our method does not need pre-processing steps.