OCR is a technology that identifies characters from printed books, handwritten papers, or images. Modern OCR applications are especially poor in processing documents with poor image quality, some alphabets like less commonly used Arabic fonts such as Nastaliq, handwriting and cursive handwriting. In most practical applications, it is still far below human level accuracy. However, OCR provides outstanding results only on particular use cases. This leads some experts to claim that OCR is a “solved” problem, and no further progress is required. In the featured image, we observe that the interest in OCR is relatively stable in the last three years. Today OCR is a relatively mature technology and it is not even called AI any more which is a good example of Pulitzer Prize winner Douglas Hofstadter’s quote : AI is whatever hasn’t been done yet. Optical Character Recognition (OCR) is one of the earliest areas of artificial intelligence research.
0 Comments
Leave a Reply. |