The instructions below assume you have a Python interpreter version 3.8 or higher installed on your computer if that's not the case, please first install Python and familiarize yourself with running Python programs on your system. The framework for connecting to services could be expanded to support others as well (and contributions are welcome!). Services supported include Google's Google Cloud Vision API, Microsoft's Azure Computer Vision API, and Amazon's Textract and Rekognition. Finally, Handprint can use multiple processor threads for parallel execution.
It can work with individual images, directories of images, and URLs pointing to images on remote servers. Among other features, the software can also display bounding boxes, threshold results by confidence values, compare full-text results to expected/ground-truth results, and output the raw results from an HTR service as JSON and text files. Handprint can generate images with recognized text overlaid over them to visualize the results. It was developed for use with documents from the Caltech Archives, but it is completely independent and can be applied to any images of text documents. Handprint ( Handwritten Page Recognit io n Test) is a tool for comparing alternative services for offline handwritten text recognition (HTR). There are no functional or API changes in this release. It also removes the internal copy of network utilities in favor of using the network_utils module from CommonPy. Version 1.5.6: This release updates dependency versions in requirements.txt and Pipfile, to address a security issue in Pillow. It can produce annotated images showing the results, compare the recognized text to expected text, save the HTR service results as JSON and text files, and more. The Handwritten Page Recognit io n Test is a command-line program that invokes HTR (handwritten text recognition) services on images of document pages.
0 kommentar(er)
