Loading…
This layer is editable and shared with the public. To prevent unwanted editing, unshare this item or approve it for public data collection.
Finish setting up your layer
Describe your item below. Add fields on the Data tab. Configure editing on the Settings tab. Configure drawing and pop-ups through Map Viewer or Visualization tab.
Open
Creating Service

Deep learning model to detect and recognize text from images. A brief summary of the item is not available. Add a brief summary about the item.

‎Deep learning package by

New notebook runtime available. You can update the runtime from the settings tab of the item details page.

Item created: May 18, 2023 Item updated: Jan 2, 2025 Number of downloads: 4,273

Snapshot last refreshed:

1987 characters left.

Description

Text labels are an integral part of cadastral maps and floor plans. Text is also prevalent in natural scenes around us in the form of road signs, billboards, house numbers and place names. Extracting this text can provide additional context and details about the places the text describes and the information it conveys. Digitization of documents and extracting texts from them helps in retrieving and archiving of important information.

This deep learning model is based on the MMOCR model and uses optical character recognition (OCR) technology to detect text in images. This model was trained on a large dataset of different types and styles of text with diverse background and contexts, allowing for precise text extraction. It can be applied to various tasks such as automatically detecting and reading text from documents, sign boards, scanned maps, etc., thereby converting images containing text to actionable data.

Using the model
Follow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.

Fine-tuning the model
This model cannot be fine-tuned using ArcGIS tools.

Input
High-resolution, 3-band street-level imagery/oriented imagery, scanned maps, or documents, with medium to large size text.

Output
A feature layer with the recognized text and bounding box around it.

Model architecture
This model is based on the open-source MMOCR model by MMLab.

Sample results
Here are a few results from the model.

Result

Result

An in-depth description of the item is not available.

Layers

Ground Layers

Tools

Tables

Basemap

Project Contents:

Solution Contents

Contents

Layers

Screenshots

Terms of Use

https://downloads.esri.com/blogs/arcgisonline/esrilogo_new.png This work is licensed under the Esri Master License Agreement.

No special restrictions or limitations on using the item's content have been provided.

Comments (8)

Sign in to add a comment.

cgoeke Item Owner commented 7 months ago Delete Reply

I have downloaded the version from May 22 2024. It detects much less text with the same settings as for the version before. I am trying to digitize numbers (with comma for decimal separator). Any suggestions why that is the case or how to get more text recognized?

krdyke Item Owner commented a year ago Delete Reply

Any advice for training this model with our own data? I'm happy to dig into the MMOCR side of things if needed, but a starting point would be very welcome. Thanks.

cgoeke Item Owner commented a year ago Delete

I just realized that I downloaded a different version https://gis-au.maps.arcgis.com/home/item.html?id=901eac288e39420bb667e52a233d8195, so my earlier comment is related to that version. I am not sure why these two versions exist and get updated in parallel

cgoeke Item Owner commented a year ago Delete

@ptuteja_geosaurus Do you know if the mmocr in the model can simply be replaced with a newer version? I can also see that the model uses v0.6.3 and v1.0.0 is already published. My problem is mainly point and comma in my sources and another language than English. Otherwise it worked very well in first attempt.

ptuteja_geosaurus Item Owner commented a year ago Delete

You could explore the open source mmocr https://github.com/open-mmlab/mmocr for finetuning. The ArcGIS API for Python does not support finetuning an OCR-based model at this time.

ecl_rexroad_a Item Owner commented 2 years ago Delete Reply

Getting an error "AccessDenied, request has expired" when trying to access the guide link in the "Using the model" section. Can you please update the hyperlink?

esri_analytics Item Owner commented 2 years ago Delete

The link has been updated. Apologies for the inconvenience.

Loprz Item Owner commented 2 years ago Delete

Same.

Item Information

LowHigh

Item Information

LowHigh

Make your item easy to find, understand, and use by providing this information.

    Details

    Dashboard views: Desktop

    Source: (Image Collection)

    Creating data in:

    Published as:

      Other Views:

        Dependent items in the recycle bin

          Applicable: 2d

          Size: 534.589 MB

          Attachments size: 0 KB

          ID: 8b56ed53e34b4304a5b8b826a7512ab0

          Image Count: 0

          Image Properties

          Layer Drawing

          Using tiles from a cache

          Dynamically from data

          Share
          Owner

          esri_analytics

          Folder

          Categories

          This item has not been categorized.

          Assign Category
          Tags

          ocr, optical character recognition, dlpk, LivingAtlasDLPK, text detection, text recognition, mmocr

          Edit Tags
          Credits (Attribution)
          No acknowledgements.

          Esri

          ArcGIS Navigator link
          URL View
          WMTS View
          Your tile layer is ready to use
          This tile layer will automatically create tiles as needed and cache them for future use. No further configuration is required. View the Settings tab to change the default options. Build tiles manually for specific scales and extents to improve display performance for the first person to view the tile layer at that scale and extent. Tiles must exist if the layer will be used offline.
          All items were exported successfully
          ${numberOfItems} item(s) were exported successfully. Some item(s) skipped or failed to export.
          See description for more information
          Cannot import
          Export packages from newer portal versions cannot be imported to older versions.
          Loading…