How to Compare Two Images in Swift

Building an image similarity model for a website is a useful method for suggesting potential products or material that may pique a customer’s interest. However, the actual process can be difficult to accomplish when attempting it manually. In this brief tutorial, we will demonstrate how you can use an API in Swift to compare two images for similarity. The API employs Deep Learning to generate an image similarity score between 0 and 1, with 1 indicating the greatest similarity.

All you’ll need for this process is the base image, comparison image, and API key to input into the following code:

import Foundation
#if canImport(FoundationNetworking)
import FoundationNetworking
#endif
var semaphore = DispatchSemaphore (value: 0)
let parameters = [
     [
          "key": "baseImage",
          "src": "/path/to/file",
          "type": "file"
     ],
     [
          "key": "comparisonImage",
          "src": "/path/to/file",
          "type": "file"
     ]] as [[String : Any]]
let boundary = "Boundary-\(UUID().uuidString)"
var body = ""
var error: Error? = nil
for param in parameters {
     if param["disabled"] == nil {
          let paramName = param["key"]!
          body += "--\(boundary)\r\n"
          body += "Content-Disposition:form-data; name=\"\(paramName)\""
          if param["contentType"] != nil {
               body += "\r\nContent-Type: \(param["contentType"] as! String)"
          }
          let paramType = param["type"] as! String
          if paramType == "text" {
               let paramValue = param["value"] as! String
               body += "\r\n\r\n\(paramValue)\r\n"
          } else {
               let paramSrc = param["src"] as! String
               let fileData = try NSData(contentsOfFile:paramSrc, options:[]) as Data
               let fileContent = String(data: fileData, encoding: .utf8)!
               body += "; filename=\"\(paramSrc)\"\r\n"
                 + "Content-Type: \"content-type header\"\r\n\r\n\(fileContent)\r\n"
          }
     }
}
body += "--\(boundary)--\r\n";
let postData = body.data(using: .utf8)
var request = URLRequest(url: URL(string: "https://api.cloudmersive.com/image/recognize/similarity/compare")!,timeoutInterval: Double.infinity)
request.addValue("<string>", forHTTPHeaderField: "recognitionMode")
request.addValue("multipart/form-data", forHTTPHeaderField: "Content-Type")
request.addValue("YOUR-API-KEY-HERE", forHTTPHeaderField: "Apikey")
request.addValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")
request.httpMethod = "POST"
request.httpBody = postData
let task = URLSession.shared.dataTask(with: request) { data, response, error in 
     guard let data = data else {
          print(String(describing: error))
          semaphore.signal()
          return
     }
     print(String(data: data, encoding: .utf8)!)
     semaphore.signal()
}
task.resume()
semaphore.wait()

You will receive an immediate result indicating the image similarity score, which you can leverage to organize your images accordingly.