PF-ViT: Parallel and Fast Vision Transformer for Offline Handwritten Chinese Character Recognition

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Dataset</td><td class="align_center">DHWDB</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Number of class</td><td class="align_center">16</td></tr><tr><td class="align_left">Number of images per class</td><td class="align_center">1810<svg height="5.65839pt" id="M32" style="vertical-align:-0.04980993pt" version="1.1" viewbox="-0.0498162 -5.60858 7.75925 5.65839" width="7.75925pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M548 311L516 323C497 274 452 240 400 240C372 240 342 260 316 278C277 305 235 330 188 330C116 330 66 268 40 199L72 187C91 236 136 270 188 270C216 270 246 250 272 232C311 205 353 180 400 180C472 180 522 242 548 311Z"></path></g></svg>2575</td></tr><tr><td class="align_left">Image size</td><td class="align_center">224 <svg height="7.35473pt" id="M33" style="vertical-align:-0.3499303pt" version="1.1" viewbox="-0.0498162 -7.0048 7.75925 7.35473" width="7.75925pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M528 54L331 254L528 455L492 493L294 291L96 493L60 455L257 254L60 54L96 16L294 217L492 16L528 54Z"></path></g></svg> 224</td></tr><tr><td class="align_left">Total number of images in the dataset</td><td class="align_center">36210</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Computational Intelligence and Neuroscience

tab3

Table 3

Table 3: PF-ViT: Parallel and Fast Vision Transformer for Offline Handwritten Chinese Character Recognition 