sudo apt update
sudo apt upgrade

python3 -V

sudo apt install -y python3-pip

pip3 install CMake

export PATH=$CMake_bin_folder:$PATH

pip3 install dlib
pip3 install numpy
pip3 install face_recognition
pip3 install elasticsearch

touch getVectorFromPicture.py

import face_recognition
import numpy as np
import sys
image = face_recognition.load_image_file("$PATH_TO_IMAGE")
# detect the faces from the images
face_locations = face_recognition.face_locations(image)
# encode the 128-dimension face encoding for each face in the image
face_encodings = face_recognition.face_encodings(image, face_locations)
# Display the 128-dimension for each face detected
for face_encoding in face_encodings:
      print("Face found ==>  ", face_encoding.tolist())

# Store the face 128-dimension in Elasticsearch
## Create the mapping
curl -XPUT "http://localhost:9200/faces" -H 'Content-Type: application/json' -d'
{
  "mappings" : {
      "properties" : {
        "face_name" : {
          "type" : "keyword"
        },
        "face_encoding" : {
          "type" : "dense_vector",
          "dims" : 128
        }
      }
    }
}'

## Index the face feature representation
curl -XPOST "http://localhost:9200/faces/_doc" -H 'Content-Type: application/json' -d'
{
  "face_name": "name",
  "face_encoding": [
     -0.14664565,
     0.07806452,
     0.03944433,
     ...
     ...
     ...
     -0.03167224,
     -0.13942884
  ]
}'

touch recognizeFaces.py

import face_recognition
import numpy as np
from elasticsearch import Elasticsearch
import sys

# Connect to Elasticsearch cluster
from elasticsearch import Elasticsearch
es = Elasticsearch(
cloud_id="cluster-1:dXMa5Fx...",
     http_auth=("elastic", "<password>"),
)

i=0
for face_encoding in face_encodings:
        i += 1
        print("Face",i)
        response = es.search(
        index="faces",
        body={
         "size": 1,
         "_source": "face_name",
        "query": {
        "script_score": {
                 "query" : {
                     "match_all": {}
                 },
         "script": {
                "source": "cosineSimilarity(params.query_vector, 'face_encoding')",
                 "params": {
                 "query_vector":face_encoding.tolist()
                }
           }
          }
         }
        }
        )

for hit in response['hits']['hits']:
                #double score=float(hit['_score'])
                if (float(hit['_score']) > 0.93):
                    print("==> This face  match with ", hit['_source']['face_name'], ",the score is" ,hit['_score'])
                else:
                        print("==> Unknown face")

GET /_search
{
  "query": {
    "script_score": {
      "query": {
    "bool": {
      "must": {
        "match_all": {}
      },
      "filter": {
        "geo_distance": {
          "distance": "200km",
          "pin.location": {
            "lat": 40,
            "lon": -70
          }
        }
      }
    }
  },
       "script": {
                "source": "cosineSimilarity(params.query_vector, 'face_encoding')",
                 "params": {
                 "query_vector":[
                        -0.14664565,
                       0.07806452,
                       0.03944433,
                       ...
                       ...
                       ...
                       -0.03167224,
                       -0.13942884
                    ]
                }
           }
    }
  }
}