Image identification, retrieval, transformation, and arrangement
Image identification, retrieval, transformation and arrangement systems, methods, and computer-program products are configured to access a family tree of a user in a family tree database, identify one or more additional persons of interest in the family tree, determine whether the one or more persons of interest is associated with an image, retrieve the image, and transform the image of the one or more additional persons of interest with an image of the user or other person such as in an image arrangement template. Whether an image pertains to a person is determined using a machine learning classifier. A plurality of candidate lineages from a root or self node may be evaluated based on the number and/or quality of images associated therewith and/or based on filtering the one or more characteristics of the nodes in the candidate lineages.
1 . A computer-implemented method for generating an image arrangement from records in a stitched family tree genealogical database, the computer-implemented method comprising:
accessing a stitched tree of a person of interest in a genealogical database, the person of interest defining a base node of the stitched tree for generating an image arrangement, wherein the stitched tree is stored in the genealogical database and comprises a plurality of linked nodes corresponding to images stored in the genealogical database;
generating, from the images corresponding to the stitched tree in the genealogical database, the image arrangement for the base node of the stitched tree by:
identifying, from the genealogical database, a first image depicting the person of interest corresponding to the base node and a second image depicting a person represented by an additional node connected to the base node in the stitched tree;
determining that a first confidence associated with a first prediction by a machine learning classification model that the first image comprises a first face is above a predetermined confidence threshold;
determining that a second confidence associated with a second prediction by the machine learning classification model that the second image comprises a second face is above the predetermined confidence threshold;
generating, based on the predetermined confidence threshold, a plurality of candidate lineages extending from the base node in the stitched tree;
selecting, from among the plurality of candidate lineages, a candidate lineage comprising the additional node connected to the base node of the stitched tree;
traversing the stitched tree along the candidate lineage from the base node to identify, from the genealogical database, the second image depicting the person represented by the additional node along the candidate lineage; and
transforming the first image and the second image into the image arrangement for the candidate lineage; and
providing the image arrangement for display on a user device.
2 . The computer-implemented method of claim 1 , wherein identifying the first image comprises:
applying the machine learning classification model to the first image; and
determining, using the machine learning classification model, that the first image comprises a face.
3 . The computer-implemented method of claim 1 , further comprising transforming a second candidate lineage extending from the base node into a second image arrangement for display on the user device.
4 . The computer-implemented method of claim 1 , wherein generating the plurality of candidate lineages extending from the base node comprises:
generating a first candidate lineage comprising a first set of nodes extending from the base node; and
generating a second candidate lineage comprising a second set of nodes extending from the base node.
5 . The computer-implemented method of claim 1 , further comprising:
generating the plurality of candidate lineages comprising respective paths of linked nodes extending from the base node in the stitched tree.
6 . The computer-implemented method of claim 5 , wherein candidate lineages among the plurality of candidate lineages are based on a template image arrangement.
7 . The computer-implemented method of claim 1 , wherein transforming the first image and the second image into the image arrangement comprises automatedly adjusting at least one of:
a size and a shape of at least one of the first image and the second image such that faces of the first image and the second image fit corresponding spaces of a template; and
a color scheme of at least one of the first image and the second image such that the first image and the second image have matching color schemes.
8 . A computer system comprising:
one or more processors; and
a non-transitory computer-readable medium comprising instructions that, when executed by the one or more processors, cause the computer system to:
access a stitched tree of a person of interest in a genealogical database, the person of interest defining a base node of the stitched tree for generating an image arrangement, wherein the stitched tree is stored in the genealogical database and comprises a plurality of linked nodes corresponding to images stored in the genealogical database;
generate, from the images corresponding to the stitched tree in the genealogical database, the image arrangement for the base node of the stitched tree by:
identifying, from the genealogical database, a first image depicting the person of interest corresponding to the base node and a second image depicting a person represented by an additional node connected to the base node in the stitched tree;
determining that a first confidence associated with a first prediction by a machine learning classification model that the first image comprises a first face is above a predetermined confidence threshold;
determining that a second confidence associated with a second prediction by the machine learning classification model that the second image comprises a second face is above the predetermined confidence threshold;
generating, based on the predetermined confidence threshold, a plurality of candidate lineages extending from the base node in the stitched tree;
selecting, from among the plurality of candidate lineages, a candidate lineage comprising the additional node connected to the base node of the stitched tree;
traversing the stitched tree along the candidate lineage from the base node to identify, from the genealogical database, the second image depicting the person represented by the additional node along the candidate lineage; and
transforming the first image and the second image into the image arrangement for the candidate lineage; and
provide the image arrangement for display on a user device.
9 . The computer system of claim 8 , wherein the instructions are further executable by the one or more processors to cause the computer system to:
apply the machine learning classification model to the first image and the second image; and
determine, using the machine learning classification model, that the first image comprises a first face and the second image comprises a second face.
10 . The computer system of claim 8 , wherein the instructions are further executable to cause the computer system to transform a second candidate lineage extending from the base node into a second image arrangement for display on the user device.
11 . The computer system of claim 8 , wherein the instructions are further executable by the one or more processors to cause the computer system to generate the plurality of candidate lineages extending from the base node by:
generating a first candidate lineage comprising a first set of nodes extending from the base node; and
generating a second candidate lineage comprising a second set of nodes extending from the base node.
12 . The computer system of claim 8 , wherein the instructions are further executable by the one or more processors to cause the computer system to:
generate the plurality of candidate lineages comprising respective paths of linked nodes extending from the base node in the stitched tree.
13 . The computer system of claim 12 , wherein candidate lineages among the plurality of candidate lineages are based on a template image arrangement.
14 . The computer system of claim 8 , wherein the instructions are further executable to cause the computer system to transform the first image and the second image into the image arrangement for the candidate lineage by automatedly adjusting at least one of:
a size and a shape of at least one of the first image and the second image such that faces of the first image and the second image fit corresponding spaces of a template; and
a color scheme of at least one of the first image and the second image such that the first image and the second image have matching color schemes.
15 . A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors of a computer system, cause the computer system to:
access a stitched tree of a person of interest in a genealogical database, the person of interest defining a base node of the stitched tree for generating an image arrangement, wherein the stitched tree is stored in the genealogical database and comprises a plurality of linked nodes corresponding to images stored in the genealogical database;
generate, from the images corresponding to the stitched tree in the genealogical database, the image arrangement for the base node of the stitched tree by:
identifying, from the genealogical database, a first image depicting the person of interest corresponding to the base node and a second image depicting a person represented by an additional node connected to the base node in the stitched tree;
determining that a first confidence associated with a first prediction by a machine learning classification model that the first image comprises a first face is above a predetermined confidence threshold;
determining that a second confidence associated with a second prediction by the machine learning classification model that the second image comprises a second face is above the predetermined confidence threshold;
generating, based on the predetermined confidence threshold, a plurality of candidate lineages extending from the base node in the stitched tree;
selecting, from among the plurality of candidate lineages, a candidate lineage comprising the additional node connected to the base node of the stitched tree;
traversing the stitched tree along the candidate lineage from the base node to identify, from the genealogical database, the second image depicting the person represented by the additional node along the candidate lineage; and
transforming the first image and the second image into the image arrangement for the candidate lineage; and
provide the image arrangement for display on a user device.
16 . The non-transitory computer-readable medium of claim 15 , wherein the instructions are further executable by the one or more processors to cause the computer system to:
apply the machine learning classification model to the first image and the second image; and
determine, using the machine learning classification model, that the first image comprises a first face and the second image comprises a second face.
17 . The non-transitory computer-readable medium of claim 15 , wherein the instructions are further executable by the one or more processors to cause the computer system to transform a second candidate lineage extending from the base node into a second image arrangement for display on the user device.
18 . The non-transitory computer-readable medium of claim 15 , wherein the instructions are further executable by the one or more processors to cause the computer system to:
generate the plurality of candidate lineages comprising respective paths of linked nodes extending from the base node in the stitched tree.
19 . The non-transitory computer-readable medium of claim 18 , wherein candidate lineages among the plurality of candidate lineages are based on a template image arrangement.
20 . The non-transitory computer-readable medium of claim 15 , wherein the instructions are further executable by the one or more processors to cause the computer system to transform the first image and the second image into the image arrangement for the candidate lineage by automatedly adjusting at least one of:
a size and a shape of at least one of the first image and the second image such that faces of the first image and the second image fit corresponding spaces of a template; and
a color scheme of at least one of the first image and the second image such that the first image and the second image have matching color schemes.