Collating device
View Patent ↗A collating device includes a collation list, a collation unit and a comparison unit. The collation list is configured to retain a false alarm list including a registered image, a threshold value serving as a criterion for determining whether to perform alarm activation, and a false alarm person image. The collation unit is configured to collate an input image with the registered image and the false alarm person image managed by the collation list, thereby obtaining a similarity therebetween. The comparison unit is configured to compare: a larger one of a value of the similarity between the input image and the false alarm person image, which is obtained by the collation unit, and the threshold value; and the similarity between the input image and the registered image, which is obtained by the collation unit, thereby determining whether to perform the alarm activation.
1. A collating device comprising:
a collation list configured to retain a false alarm list comprising a registered image, a threshold value serving as a criterion for determining whether to perform alarm activation, and a false alarm person image of a person who is not to be alarmed and who was previously erroneously alarmed due to having been mistaken for another person who is to be alarmed;
a collator configured to collate an input image with the registered image and the false alarm person image managed by the collation list, such that the collator obtains a similarity between the input image with the one of the registered image and the false alarm person image; and
a comparator configured to compare:
a larger one of a value of the obtained similarity between the input image and the false alarm person image, and the threshold value; and
the similarity between the input image and the obtained registered image, such that the comparator determines whether to perform the alarm activation.
2. The collating device according to claim 1 , wherein the collation list comprises the false alarm list for each registered image.
3. The collating device according to claim 1 , wherein the collation list comprises the false alarm list common to the registered images.
4. The collating device according to claim 2 , wherein the collation list adds the input image to the false alarm list as false alarm information if the alarm activation is activation of a false alarm.
5. A collating device comprising:
a collation list configured to retain a registered image feature amount, a threshold value serving as a criterion for determining whether to perform alarm activation, and a false alarm person image feature amount of a person who is not to be alarmed and who was previously erroneously alarmed due to having been mistaken for another person who is to be alarmed;
a collator configured to collate an input image with the registered image feature amount and the false alarm person image feature amount retained by the collation list, such that the collator obtains a similarity between the input image with the one of the registered image feature amount and the false alarm person image feature amount; and
a comparator configured to compare:
a larger one of a value of the obtained similarity between the input image and the false alarm person image feature amount, and the threshold value; and
the similarity between the input image and the obtained registered image feature amount, such that the comparator determines whether to perform the alarm activation.
6. A collation method comprising:
providing a collation list retaining a false alarm list comprising a registered image, a threshold value serving as a criterion for determining whether to perform alarm activation, and a false alarm person image of a person who is not to be alarmed and who was previously erroneously alarmed due to having been mistaken for another person who is to be alarmed;
collating an input image with at least one of the registered image and the false alarm person image managed by the collation list, and obtaining a similarity therebetween; and
comparing:
a larger one of a value of the obtained similarity between the input image and the false alarm person image and the threshold value; and
the obtained similarity between the input image and the registered image; and
determining, based on said comparing, whether to perform the alarm activation.