gcloud alpha ml vision detect-document

gcloud alpha ml vision detect-document - detect dense text in an image

gcloud alpha ml vision detect-document IMAGE_PATH [--language-hints=[LANGUAGE_HINTS,…]] [--model-version=MODEL_VERSION; default="builtin/stable"] [GCLOUD_WIDE_FLAG …]

Google Cloud Vision uses OCR (Optical Character Recognition) to analyze text. This is a premium feature for dense text such as books, research reports, and PDFs. To detect small amounts of text such as on signs, use detect-text instead. For more information on this feature, see the Google Cloud Vision documentation at https://cloud.google.com/vision/docs/.

Language hints can be provided to Google Cloud Vision API. In most cases, an empty value yields the best results since it enables automatic language detection. For languages based on the Latin alphabet, setting language_hints is not needed. Text detection returns an error if one or more of the specified languages is not one of the supported languages. (See https://cloud.google.com/vision/docs/languages.) To provide language hints run:

gcloud alpha ml vision detect-document --language-hints ja,ko

IMAGE_PATH

Path to the image to be analyzed. This can be either a local path or a URL. If you provide a local file, the contents will be sent directly to Google Cloud Vision. If you provide a URL, it must be in Google Cloud Storage format (gs://bucket/object) or an HTTP URL (http://... or https://…)

--language-hints=[LANGUAGE_HINTS,…]

List of languages to use for text detection.

--model-version=MODEL_VERSION; default="builtin/stable"

Model version to use for the feature. MODEL_VERSION must be one of: builtin/latest, builtin/stable.

Run $ gcloud help for details.