Generates pnm image files containing random words from the wamerican dictionary.
Generates png image files containing random words from the wamerican dictionary.
The number of words are held constant at 100, and the `mono` font is used for all runs. The dpi of the image is varied to judge how more visual details affects OCR accuracy and performance.
The number of words are held constant at 100, and the `mono` font is used for all runs. The dpi of the image is varied to judge how more visual details affects OCR accuracy and performance.
Generates pnm image files containing random words from the wamerican dictionary.
Generates png image files containing random words from the wamerican dictionary.
The number of words is held constant at 100, but a different font is used to render the text. Generally, `mono` performs the best, followed by `URW Gothic`, followed by `Lobster Two`, which is a stylistic font that performs quite poorly.
The number of words is held constant at 100, but a different font is used to render the text. Generally, `mono` performs the best, followed by `URW Gothic`, followed by `Lobster Two`, which is a stylistic font that performs quite poorly.
Generates pnm image files containing random words from the wamerican dictionary.
Generates png image files containing random words from the wamerican dictionary.
The number of words are varied between 1, 10, 100 in order to assess how the size of text OCRed affects the execution profile of the sandbox serving the request.
The number of words are varied between 1, 10, 100 in order to assess how the size of text OCRed affects the execution profile of the sandbox serving the request.
This is a larger OCR example. The \*.pnm file is 5mb or so.
This is a larger OCR example.
In the future, this OCR example might be a good use case for a "step-wise" function, as the file is substantially smaller before conversion to the \*.pnm format.