Smart assistants can be configured in image questions for use in the Survey123 field app. For more information, see Smart assistants.
Surveys can be configured to show detection results in the live camera preview. You may see minor differences between the live camera preview and the final image. This is due to the difference in resolution between the video input shown in the camera preview and the still image output. Generally, the still image is higher resolution and provides more accurate results than the live camera preview.
Use smart attributes in a survey
Smart attributes can be configured for image questions in Survey123. When you take a photo or select an image from device storage in the field app the image is analyzed to detect objects. The detection results are stored as attributes in the image's metadata. Questions that have been configured to accept these attributes display the values. Values can be edited before the survey is submitted if the questions are not read-only.
Use smart annotation in a survey
Smart annotation can be configured for image annotation questions in Survey123. When you take a photo or select an image from device storage in the field app, bounding boxes and labels for detected objects are drawn on the canvas as graphic elements. You can modify, add, or delete graphic elements. For more information, see Draw and annotate.
Once the annotation is accepted, the image is saved with the annotation included. The annotation cannot be undone.
Use smart redaction in a survey
Smart redaction can be configured for image questions in Survey123. When you take a photo or select an image from device storage in the field app regions of the image are redacted automatically. Alternatively, you can manually redact the image.
Depending on how the author has configured the survey, you may need to turn on enhanced camera features to enable smart redaction on Android and iOS. To enable enhanced camera features, tap Settings > Privacy and Security > Enable enhanced camera features. On iOS only, surveys may be configured to use the Apple built-in Vision API for face detection.
Caution:
Enhanced camera features use Google ML Kit. When you enable enhanced camera features in the field app, usage statistics may be sent to Google to measure performance, debug, maintain and improve products, and detect misuse or abuse. Image processing happens entirely on the device and no images are sent to Google servers. For more information, see Google ML Kit Terms & Privacy on the Google developers website.
On iOS, barcode scanning and surveys that include the engine=vision property for smart redaction automatically use Apple built-in Vision APIs. These APIs may send analytics data to Apple. Analytics data may include details about hardware and operating system specifications, performance statistics, and data about how you use your devices and applications. You can review this information in the privacy and security settings on your iOS device. This information is used to help Apple improve and develop its products and services. None of the collected information identifies you personally. Personal data is not logged, is subject to privacy preserving techniques such as differential privacy, or is removed from any reports before being sent to Apple. For more information, see Device Analytics & Privacy and Data & Privacy on the Apple website.
You can manually edit the regions detected by smart redaction after the image is captured. Bounding boxes can be modified, deleted, or added.
- Add—Tap on the region of the image you want to redact. A bounding box appears with the redaction effect specified by the survey author.
- Modify—Tap a bounding box to select it. Four corner handles and a rotate icon appear that can be used to resize or rotate the bounding box. Tap the selected active bounding box again to deselect it. Bounding boxes are not shown on the final image, only the effect.
- Delete—Tap a bounding box to select it. Then tap the delete button to delete the selected bounding box. You can also drag the bounding box to the trash can.
- Undo—Tap to undo the last deletion. Once you add a new bounding box or modify an existing bounding box, the undo button is unavailable until another deletion is made.
Once the redaction result is accepted, the image is saved with regions redacted. The redaction cannot be undone.