Artificial Intelligence is one of the major hottest topic among every techies. Billion dollar companies like Amazon are already invested into machine learning for the last 10 years. Today we are going to talk about Amazon Rekognition Service – A Deep Learning-based Image Recognition. In my previous post I had explained How to convert your text to speech using Amazon Polly API with PHP
Amazon Rekognition serivce provides include Object and Scene detection, Facial Analysis, Face Comparison and Facial Recognition. We will start with facial analysis like celebrity identification.
Amazon Rekognition service automatically recognizes celebrities in images and provides confidence scores.
Contents
Why Amazon Rekognition?
Use Case 1 – Movie Database
In case if you have huge collection of movies in your database and if you want to find the celebrities in the movie poster, In this situation it requires more manual effort to find the celebrity name in the movie poster. Amazon Rekognition’s Celebrity Rekognition API Service will help you to automate the whole process in a minute without any manual intervention.
Use Case 2 – Web Application
In any web application like facebook, If you upload profile picture/cover picture, Amazon Rekognition’s Celebrity Rekognition API Service helps you to identify the celebrity in that picture and its saves your time to mention the celebrity name manually in your post.
We are now going to see how it works using PHP as illustrated in the above use cases
Download and Install Amazon PHP SDK Client
To get started, you must download the zip file, unzip it into your project to a location of your choosing, and include the autoloader:
require '/path/to/aws-autoloader.php';Configuring the AWS Access Keys
In order to use amazon rekognition service, you should register an account with AWS and get the AWS Access key/secret within your AWS account. Please go through this link to get the credentails. I prefer to use an IAM to generate the key.
Amazon Rekognition Client
After getting credentails from amazon account, we need to create an amazon rekognition client as below
use Aws\Rekognition\RekognitionClient;
$config = [
'version' => 'latest',
'region' => 'us-east-1', //region
'credentials' => [
'key' => 'your aws access key',
'secret' => 'your aws secret key',
]];
$client = new RekognitionClient($config);
Next we should pass the image to amazon rekognition client to analyze/detect the image and it provides the celebrity details matches in the image.
How to Pass an Image URL into Amazon Rekognition Client
In the below code, we are passing the image url into rekognition api to get the image details by analzing the image in PHP.
$data = file_get_contents($url);
$args = [
'Image' => [
'Bytes' => $data
]
];
$result = $client->recognizeCelebrities($args);
Output
After successful completion of the API, RecognizeCelebrities returns an array of recognized celebrities and an array of unrecognized faces.
JSON Array
{
"CelebrityFaces": [{
"Face": {
"BoundingBox": {
"Height": 0.617123007774353,
"Left": 0.15641026198863983,
"Top": 0.10864841192960739,
"Width": 0.3641025722026825
},
"Confidence": 99.99589538574219,
"Landmarks": [{
"Type": "eyeLeft",
"X": 0.2837241291999817,
"Y": 0.3637104034423828
}, {
"Type": "eyeRight",
"X": 0.4091649055480957,
"Y": 0.37378931045532227
}, {
"Type": "nose",
"X": 0.35267341136932373,
"Y": 0.49657556414604187
}, {
"Type": "mouthLeft",
"X": 0.2786353826522827,
"Y": 0.5455248355865479
}, {
"Type": "mouthRight",
"X": 0.39566439390182495,
"Y": 0.5597742199897766
}],
"Pose": {
"Pitch": -7.749263763427734,
"Roll": 2.004552125930786,
"Yaw": 9.012002944946289
},
"Quality": {
"Brightness": 32.69192123413086,
"Sharpness": 99.9305191040039
}
},
"Id": "3Ir0du6",
"MatchConfidence": 98.0,
"Name": "Jeff Bezos",
"Urls": ["www.imdb.com/name/nm1757263"]
}],
"OrientationCorrection": "ROTATE_0",
"UnrecognizedFaces": [{
"BoundingBox": {
"Height": 0.5345501899719238,
"Left": 0.48461538553237915,
"Top": 0.16949152946472168,
"Width": 0.3153846263885498
},
"Confidence": 99.92860412597656,
"Landmarks": [{
"Type": "eyeLeft",
"X": 0.5863404870033264,
"Y": 0.36940744519233704
}, {
"Type": "eyeRight",
"X": 0.6999204754829407,
"Y": 0.3769848346710205
}, {
"Type": "nose",
"X": 0.6349524259567261,
"Y": 0.4804527163505554
}, {
"Type": "mouthLeft",
"X": 0.5872702598571777,
"Y": 0.5535582304000854
}, {
"Type": "mouthRight",
"X": 0.6952020525932312,
"Y": 0.5600858926773071
}],
"Pose": {
"Pitch": -7.386096477508545,
"Roll": 2.304218292236328,
"Yaw": -6.175624370574951
},
"Quality": {
"Brightness": 37.16635513305664,
"Sharpness": 99.9305191040039
}
}]
}
You can parse the results by using the “CelebrityFaces” key. You can get all the datas such as Celebrity name, Matching score, Confidence etc.
UnrecognizedFaces is an array of faces that didn’t match any known celebrities. Each ComparedFace object in the array contains a bounding box (as well as other information) that you can use to locate the face in the image.
if(!empty($result['CelebrityFaces'])) {
foreach($result['CelebrityFaces'] as $key => $val)
{
$name = $val['Name'];
$MatchScore = $val['Face']['Confidence'];
$matchConfidence = $val['MatchConfidence'];
}
}
If you find this tutorial useful, please share it with your friends and in social networks.
Your suggestions/comments are most welcome.
