High resolution face matching
AssigneeCorsight.Ai
InventorsRan Vardimon, Yarden Yaniv, Matan Noga, Gadi Piran
Life of this patent
Estimating the term…
Abstract
Systems, and method and computer readable media that store instructions for high-resolution face recognition.
Claims17
A method for high resolution face matching, the method comprises:
- obtaining a visual representation of a first face and a visual representation of a second face;
- wherein the visual representations of the first and second faces are substantially aligned and are substantially of a same size;
- for each part out of a group of parts of the visual representation of a first face, (a) masking the part of the visual representation of a first face to provide a part-masked visual representation of the first face, and (b) matching the part-masked visual representation of the first face to the visual representation of the second face to provide a match result related to the part;
- determining relevancies of the parts of the group based on match results related to the parts;
- generating parts relevancy indications that are indicative of the relevancies of the parts;
- and
- performing at least one out of populating a database with the parts relevancy indications, displaying the parts relevancy indications, and transmitting the parts relevancy indications.
The method according to claim wherein the displaying of the parts relevancy indication comprises displaying a heatmap that represents parts relevancies.
A non-transitory computer readable medium for high resolution face matching, the non-transitory computer readable medium stores instructions for:
- obtaining a visual representation of a first face and a visual representation of a second face;
- wherein the visual representations of the first and second faces are substantially aligned and are substantially of a same size;
- for each part out of a group of parts of the visual representation of a first face, (a) masking the part of the visual representation of a first face to provide a part-masked visual representation of the first face, and (b) matching the part-masked visual representation of the first face to the visual representation of the second face to provide a match result related to the part;
- determining relevancies of the parts of the group based on match results related to the parts;
- generating parts relevancy indications that are indicative of the relevancies of the parts;
- and
- performing at least one out of populating a database with the parts relevancy indications, displaying the parts relevancy indications, and transmitting the parts relevancy indications.
The non-transitory computer readable medium according to claim wherein the displaying of the parts relevancy indication comprises displaying a heatmap that represents parts relevancies.
A computerized system comprising a processor that is configured to:
- obtain a visual representation of a first face and a visual representation of a second face;
- wherein the visual representations of the first and second faces are substantially aligned and are substantially of a same size;
- for each part out of a group of parts of the visual representation of a first face, (a) mask the part of the visual representation of a first face to provide a part-masked visual representation of the first face, and (b) match the part-masked visual representation of the first face to the visual representation of the second face to provide a match result related to the part;
- determine relevancies of the parts of the group based on match results related to the parts;
- generate parts relevancy indications that are indicative of the relevancies of the parts;
- and
- perform at least one out of populating a database with the parts relevancy indications, displaying the parts relevancy indications, and transmitting the parts relevancy indications.
Dependencies are inferred from the claim text.