Symmetric Inkball Alignment with Loopy Models

Abstract

Alignment tasks generally seek to establish a spatial correspondence between two versions of a text, for example between a set of manuscript images and their transcript. This paper examines a different form of alignment problem, namely pixel-scale alignment between two renditions of a handwritten word or phrase. Using loopy inkball graph models, the proposed technique finds spatial correspondences between two text images such that similar parts map to each other. The method has applications to word spotting and signature verification, and can provide analytical tools for the study of handwriting variation.

Details of Deformable Part Models for Automatically Georeferencing Historical Map Images

“…Initially proposed by Fischler & Elschlager [10], deformable part models have more recently been applied to human pose recovery [8] and visual object recognition [7]. Work in document analysis has developed them into tools for matching 2D arrangements of curvilinear segments, with applications to word spotting [15] and signature verification [16].…”

“…Specifically, we build on prior work that provides an approximate alignment based purely on the arrangement, textual content, and typography of toponyms (place names) on the map [26,27]. This work adapts a shape-matching algorithm (related to those previously used for word spotting [15,16]) to the task of matching contours from GIS data-geographical and political boundaries, roadways, etc.-to historical map image contents.…”