摘要 |
Vertically segmented characters are pre-processed for optical character recognition so as to remove skew and noise by convolution with a mask consisting of parallel vertical lines with a one-pixel spatial frequency. The horizontal alignment of the mask with respect to each segmented character is adjusted until a maximum cross-correlation is found. Then, the product of the mask and the character image is formed. A histogram of the number of pixels in the product image along each vertical line of the mask is compared with a library of such histograms of known symbols and the best match identifies the symbol represented by the character image. Alternatively, the histogram is converted to a binary codeword which is compared with a library of such codewords corresponding to a set of known symbols.
|