METHOD FOR DETERMINING AT LEAST ONE RELEVANT SINGLE IMAGE OF A DENTAL SUBJECT

• US 20150289756A1
• Filed: 10/30/2013
• Published: 10/15/2015
• Est. Priority Date: 10/30/2012
• Status: Active Grant

• Current Assignee: Sirona Dental Systems GmbH (Sirona Dental Systems Incorporated)
• Original Assignee: Sirona Dental Systems GmbH (Sirona Dental Systems Incorporated)
• Inventors: Schmitt, Bernhard
• Granted Patent: US 9,549,668 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 1/000094 extracting biological structures
• CPC Class Codes: A61B 1/04 combined with photographic or television appliances
• CPC Class Codes: A61B 1/24 for the mouth, i.e. stomatoscopes, e.g. with tongue depressors tongue depressors per se A61B13/00; Instruments for opening or keeping open the mouth combined with saliva removers A61C17/00; mouth openers for animals A61D15/00
• CPC Class Codes: A61C 9/004 Means or methods for taking digitized impressions
• CPC Class Codes: A61C 9/0053 Optical means or methods, e.g. scanning the teeth by a laser or light beam
• CPC Class Codes: A61C 9/006 projecting one or more stripes or patterns on the teeth
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 21/007 characterised by the process used
• CPC Class Codes: G10L 25/57 for processing of video signals
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: H04N 5/91 Television signal processing therefor

Abstract

The invention relates to a method for determining at least one relevant single image, wherein a plurality of single optical images are generated during a continuous optical measurement (3) of a dental subject (1) to be recorded. During the optical measurement (3) an audio recording is generated by means of a microphone (4) and at least one speech sequence (12; 15; 28) spoken by a user (6) is recorded. The relevant single image (7; 8; 24) is then selected within a specified sequence duration between a start time (17, 18) and an end time of the speech sequence (12; 15; 28).

Claims

1. A method for determining at least one relevant single image, a plurality of optical single images being generated during a continuous optical measurement of a dental object that is to be recorded, characterized in that during the optical measurement, an audio recording is generated using a microphone, and at least one speech sequence is recorded that is spoken by a user, the relevant single image being selected within a specified sequence duration between a start time and an end time of the speech sequence, wherein within the determined speech sequence, the relevant single image is selected that was recorded at a time at which a movement of the dental camera relative to the object to be recorded was at its least.

2. The method as recited in claim 1, characterized in that during the processing of the audio recording, background noise is filtered out using a filtering unit in order to improve the audio quality of the speech sequence.

3. The method as recited in claim 2, characterized in that the filtering unit remains activated within a previously defined variable time duration.

4. The method as recited in claim 1, characterized in that a maximum sequence duration and/or a minimum sequence duration of the speech sequence is defined before the method is carried out.

5. The method as recited in claim 1, characterized in that the sequence duration of the speech sequence corresponds to the duration of a contiguous flow of speech, brief interruptions of the flow of speech being ignored that are shorter than a defined interruption duration.

6. The method as recited in claim 5, characterized in that the interruption duration is a maximum of two seconds.

7. The method as recited in claim 6, characterized in that only one relevant single image is selected within a speech sequence.

8. The method as recited in claim 1, characterized in that the at least one speech sequence contains status information and/or finding information, the status information and/or the finding information being converted from speech to text by speech recognition software.

9. The method as recited in claim 1, characterized in that the recognized status information and/or the finding information is assigned, in text form, to the relevant single image of the respective speech sequence.

10. The method as recited in claim 1, characterized in that during the optical measurement of the overall object, a plurality of relevant single images are selected for the respective speech sequences, the individual relevant single images being displayed by a display device.

11. The method as recited in claim 10, characterized in that the speech sequences include anatomical position information that is converted from speech to text by speech recognition software, positions of the relevant single images relative to the recorded object being determined using the anatomical position information, wherein the relevant single images are displayed by the display device at the determined positions relative to a virtual model of the object.

12. The method as recited in claim 1, characterized in that the selected relevant single images are sorted into a plurality of categories of status information and/or finding information.

13. The method as recited in claim 1, characterized in that the optical measurement of the object takes place via a video recording, and individual video images of this video recording are the selected single images, so that a relevant video image is selected for each speech sequence.

14. The method as recited in claim 1, characterized in that the optical measurement of the object takes place via an optical three-dimensional stripe projection method, a plurality of individual 3-D images of the object being generated and combined into a three-dimensional overall recording, these individual 3-D images representing the single images that are to be selected, so that a relevant 3-D image of the object is selected for each speech sequence.