Object Detection & Classification

Object Detection and Classification

Analyse the image and extract various information about objects, people and scenes.

You can load your picture by selecting “CHOOSE FILE”

Select what kind of information should be extracted.

The result are shown on the picture and published at the bottom of the page.

Demo of Audience Analytics


Request parameters

Parameter’s name Parameter’s type Description
out_filters string Optional. Comma separated list of model outputs to return.
input image image to analyze
detect_objects bool Detect objects and tag image
detect_faces bool Detect faces on image
detect_poses bool Detect poses for persons on image
build_caption bool Build caption for image
curl -X POST \
    -H 'Authorization: Bearer YOUR_USER_TOKEN' \
    -H 'Content-Type: multipart/form-data' \
    -F "out_filters=output" \
    -F "input=input_value" \
    -F "detect_objects=detect_objects_value" \
    -F "detect_faces=detect_faces_value" \
    -F "detect_poses=detect_poses_value" \
    -F "build_caption=build_caption_value" \
curl -X POST \
    -H 'Authorization: Bearer YOUR_USER_TOKEN' \
    -H 'Content-Type: application/json' \
    -d '
        "build_caption": true,
        "detect_faces": true,
        "detect_objects": true,
        "detect_poses": true,
        "input": "base64_encoded_input_contents"
import kclient
from kclient.utils import client, request

cl = client.with_bearer_token("YOUR_USER_TOKEN")
serving_api = kclient.api.serving_api.ServingApi(cl)

data = request.make(data={
    "detect_objects": true,
    "detect_faces": true,
    "detect_poses": true,
    "build_caption": true,
}, files={
    "input": "/path/to/input_file",
resp = serving_api.serving_proxy(data, "hpc", "photo-inside-picture")

Response format

  "output": "base64_encoded_image",
  "table_output": [
      "type": "object",
      "name": "person",
      "prob": 0.99,
      "image": "base64_encoded_image"
  "caption_output": [
    "a group of people walking down a street."