How to detect people in a photo in Java

Any good photo app needs to be able to locate people. Setting this functionality up from scratch is quite a process. Luckily, there’s a very quick and easy way around it, which is the subject of today’s post. We will be using an API to get set up in just a couple minutes.

First we need to set some references in our Maven POM file. This will allow Jitpack to dynamically compile our API library.

Repository reference:

<repositories>
    <repository>
        <id>jitpack.io</id>
        <url>https://jitpack.io</url>
    </repository>
</repositories>

Dependency reference:

<dependencies>
<dependency>
    <groupId>com.github.Cloudmersive</groupId>
    <artifactId>Cloudmersive.APIClient.Java</artifactId>
    <version>v2.75</version>
</dependency>
</dependencies>

Now we will use the following code to call recognizeDetectPeople and provide it with an image to process:

// Import classes:
//import com.cloudmersive.client.invoker.ApiClient;
//import com.cloudmersive.client.invoker.ApiException;
//import com.cloudmersive.client.invoker.Configuration;
//import com.cloudmersive.client.invoker.auth.*;
//import com.cloudmersive.client.RecognizeApi;
ApiClient defaultClient = Configuration.getDefaultApiClient();
// Configure API key authorization: Apikey
ApiKeyAuth Apikey = (ApiKeyAuth) defaultClient.getAuthentication("Apikey");
Apikey.setApiKey("YOUR API KEY");
// Uncomment the following line to set a prefix for the API key, e.g. "Token" (defaults to null)
//Apikey.setApiKeyPrefix("Token");
RecognizeApi apiInstance = new RecognizeApi();
File imageFile = new File("/path/to/file"); // File | Image file to perform the operation on.  Common file formats such as PNG, JPEG are supported.
try {
ObjectDetectionResult result = apiInstance.recognizeDetectPeople(imageFile);
System.out.println(result);
} catch (ApiException e) {
System.err.println("Exception when calling RecognizeApi#recognizeDetectPeople");
e.printStackTrace();
}

That’s it! It’s just that easy. Below is an example response for this photo:

{
  "Successful": true,
  "Objects": [
    {
      "ObjectClassName": "person",
      "Height": 300,
      "Width": 173,
      "Score": 0.8973171710968018,
      "X": 3,
      "Y": 94
    },
    {
      "ObjectClassName": "person",
      "Height": 305,
      "Width": 477,
      "Score": 0.8843736052513123,
      "X": 356,
      "Y": 119
    },
    {
      "ObjectClassName": "person",
      "Height": 319,
      "Width": 408,
      "Score": 0.8814287185668945,
      "X": 231,
      "Y": 105
    },
    {
      "ObjectClassName": "person",
      "Height": 311,
      "Width": 251,
      "Score": 0.799172580242157,
      "X": 141,
      "Y": 107
    }
  ],
  "ObjectCount": 4
}

For each person, we are given a location, dimensions, and a score of how likely it is in fact a person. Note that this function works best when each the faces of each person are visible and undistorted.