Tagging visual media on a mobile device
This document describes techniques enabling tagging of visual media on a mobile device. In some cases the techniques determine, based on meeting a threshold of manual tagging of a person or object, to “bulk” tag visual media stored on the mobile device. Thus, the techniques can present, in rapid succession, photos and videos with the recognized person or object to enable the user to quickly and easily confirm or reject the recognition. Also, the techniques can present numerous faces for recognized persons or sub-images for recognized objects on a display at one time, thereby enabling quick and easy confirmation or rejection of the recognitions.
1. A computer-implemented method comprising:
receiving, at a processor, an indication of a manual tagging selection to tag a person or object in a particular visual image;
responsive to determining, by the processor, that the manual tagging selection of the person or of the object meets or exceeds a manual-selection tagging threshold for the person or object, performing, by the processor, facial or object recognition on multiple visual images to determine visual images having a face or sub-image recognized as matching the person or the object;
enabling, by the processor and for each of the determined visual images, selection to confirm or reject the face or sub-image recognized as matching the person or the object in a particular determined visual image;
responsive to receipt, at the processor, of an indication confirming the face or sub-image recognized in a particular determined visual image, tagging the face or the sub-image in the particular determined visual image to confirm that the face or the sub-image is correctly recognized as being the person or the object; and
responsive to not receiving, at the processor, an indication rejecting the face or sub-image recognized in a particular determined visual image, tagging the face or the sub-image in the particular determined visual image to confirm that the face or the sub-image is correctly recognized as being the person or the object.
2. The method of claim 1 , wherein the manual tagging selection is received through a mobile device, at least some of the multiple visual images are stored locally on the mobile device, and performing the facial or object recognition is performed on a majority of the visual images stored locally on the mobile device.
3. The method of claim 1 , wherein determining that the manual tagging selection meets or exceeds a manual-selection tagging threshold determines that the manual tagging selection meets or exceeds a tagging threshold number.
4. The method of claim 3 , wherein determining that the manual tagging selection meets or exceeds the tagging threshold number determines that the manual tagging selection meets or exceeds the threshold number within a tagging threshold time.
5. The method of claim 1 , wherein enabling selection to confirm or reject the face or sub-image recognized in the determined visual images as matching the person or the object in a particular visual image presents each of the determined visual images with indicia indicating the face or the sub-image.
6. The method of claim 5 , wherein presenting each of the determined visual images with indicia indicating the face or the sub-image is performed in rapid succession.
7. The method of claim 6 , wherein a speed of the rapid succession is based on a confidence that the recognition of the faces or the sub-images is correct.
8. The method of claim 1 , wherein enabling selection to confirm or reject the face or sub-image recognized in the determined visual images as matching the person or the object in a particular visual image presents portions of each of the determined visual images at one time or in one interface, the portions at least including the face or the sub-image.
9. The method of claim 8 , wherein the faces or sub-images presented at one time or in one interface are tagged responsive to confirming the faces or the sub-images.
10. The method of claim 8 , wherein sizes or numbers of the faces or the sub-images presented at one time or in one interface are determined based on a confidence that the recognition of the faces or the sub-images is correct.
11. The method of claim 1 , wherein receipt of an indication confirming the face or sub-image in a particular determined visual image is an explicit confirmation, and wherein not receiving an indication rejecting the face or sub-image recognized in a particular determined visual image is an implicit confirmation.