Example 9 is a non-transitory computer readable storage medium comprising instructions that when executed configure hardware processing circuitry to perform operations, comprising: receiving an image; detecting a plurality of features in the image; detecting a subset of the plurality of features arranged linearly in the image; detecting a region of the image bounding the subset of features; determining a probability that the region includes handwriting; determining the probability is above a threshold; generating, based on the region, a plurality of metrics defining frequencies of geometric features within the region; providing, to a trained model, the plurality of metrics; and determining from the trained model, a language type of handwriting within the region.

In Example 10, the subject matter of Example 9 optionally includes the operations further comprising enhancing contrast of the image, wherein the detecting of the features is based on the enhanced contrast.

In Example 11, the subject matter of any one or more of Examples 9-10 optionally include the operations further comprising color filtering the image, wherein the detecting of the features is based on the enhanced contrast.

In Example 12, the subject matter of any one or more of Examples 9-11 optionally include the operations further comprising determining an irregularity of features within the region, wherein the determination of the probability is based on the irregularity.