The invention discloses a calligraphy
stroke feature extraction method and
system based on a fixed-size grid. The method relates to the technical field of
stroke feature extraction, and comprises the following steps of calligraphy
stroke image preprocessing and grid division, grid-based stroke space distribution
feature extraction, size feature extraction, grid-based stroke direction feature extraction and
feature fusion and output. The method comprises the following steps: S1, normalizing a
binary image of calligraphy strokes to a fixed canvas and dividing the
binary image into grids; s2, calculating the stroke density of each grid and constructing a density
feature vector; S3, refining the image to obtain a skeleton, calculating a direction field and generating a direction
feature vector; and finally, the two vectors are connected in series and fused, and a joint
feature vector is output for a subsequent task, so that the calligraphy stroke feature extraction accuracy is improved, and the problem of low calligraphy stroke feature extraction accuracy caused by insufficient understanding of dynamic essence, complex form and high-level
semantics of calligraphy art in the prior art is solved.