CAPTOR Enhanced Search Now Leveraging the Power of OCR and Speech Recognition
Josh Bohls
With the introduction of CAPTOR iOS v3.6.4, Enhanced Search now uses both Optical Character Recognition (OCR) and Speech Recognition technology to enable users to quickly find relevant content with a simple text search. The Search feature now spans audible words spoken in videos and audio recordings, as well as any text/words detected in photos and documents.
The OCR process for photos and documents always occurs on the device, allowing the content to remain in the secure managed container at all times. Because the data is guaranteed to remain in the container, we have enabled OCR processing automatically for all customers (you do not have to specifically enable it by an app configuration). This feature is supported for all of the current CAPTOR localization options, including English, Spanish, French, Italian, Dutch, and German.
The app uses OCR to find any visible text within photos or documents, and allows that text to be searchable. For example, if you took a picture of someone standing at an intersection and the street sign was visible in the background, you would be able to find that photo later by searching for the street name. Similarly, you might be able to find all scanned documents and PDFs that mention a specific client or project name, for example.
The Speech Recognition process essentially creates a transcript of any audio and video recording. This feature has been engineered to primarily occur on the device, allowing the data to remain in the container, however, Apple does not guarantee that this will always be the case. Therefore, we released this feature as a double opt-in. In other words, first the IT Admin of your EMM platform must enable the feature by adding a new app configuration “allowspeechrecognition” with value “True” (or for BlackBerry, by checking the box to “Enable Speech Recognition”). Secondly, the end user will be asked whether to grant CAPTOR permission to use Speech Recognition. Only when both of these factors are satisfied will the app begin processing audio and video files for Enhanced Search.
When Speech Recognition is enabled by policy and granted permission by the app user, CAPTOR will begin processing all audio and video recordings to be searchable by the audio transcripts. For example, if you use CAPTOR to record voice memos, and want to find the memo where you mentioned a specific subject, you would be able to type in the subject and quickly identify the audio recording. Similarly, a video could be located by simply typing in a word that was said during the recording.
For all existing customers, when you first launch CAPTOR v3.6.4 there will be a new button on the home screen asking you to “Upgrade your files”. Tap this option to allow the app to process your existing files. You can start and stop this process as time allows, and as soon as all content has finished processing the button will disappear.
CAPTOR Enhanced Search is now available for all supported iOS devices running iOS 13 and 14. We will be adding the same search capabilities to our family of Android apps over the next few months.
As always please share comments and questions through our support page.