Azure Computer Vision Image Recognition using C# .NET


The code below uses Azure Cognitive Services Vision to classify images accordingly. The images are classified with a confidence score.

Microsoft provides three Vision APIs:

Service NameService Description
Computer VisionThe Computer Vision service provides you with access to advanced cognitive algorithms for processing images and returning information.
Custom VisionThe Custom Vision Service lets you build, deploy, and improve your own image classifiers. An image classifier is an AI service that applies labels to images, based on their visual characteristics.
FaceThe Face service provides access to advanced face algorithms, enabling face attribute detection and recognition.

This architecture will use Computer Vision. Azure Custom Vision is an image recognition service that lets you build, deploy, and improve your own image identifier models. An image identifier applies labels to images, according to their detected visual characteristics.


  1. Azure Computer Vision.
  2. Azure Blob Storage.

The code below requires a Computer Vision resource created. Once created save the Key and the Endpoint details.

using Microsoft.Azure.CognitiveServices.Vision.ComputerVision;
using Microsoft.Azure.CognitiveServices.Vision.ComputerVision.Models;
using Serilog;
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using System.Threading.Tasks;

namespace ComputerVision
    public class Process
        // Subscription Key & Endpoint
        private static readonly string subscriptionKey = "{KEY}";

        private static readonly string endpoint = "{ENDPOINT}";

        // Run Process
        public static void Run(string filename)
            string imageUrl = $"https://{BLOBSTORAGE}{container}/{filename}";

            // Create a client
            ComputerVisionClient client = Authenticate(endpoint, subscriptionKey);

            // Analyze an image to get features and other properties.
            AnalyzeImageUrl(client, imageUrl).Wait();

        public static ComputerVisionClient Authenticate(string endpoint, string key)
            ComputerVisionClient client =
              new ComputerVisionClient(new ApiKeyServiceClientCredentials(key))
              { Endpoint = endpoint };
            return client;

        public static async Task<ImageAnalysisViewModel> AnalyzeImageUrl(ComputerVisionClient client, string imageUrl)
                // Download image locally
                using (WebClient webClient = new WebClient())
                    webClient.DownloadFile(imageUrl, "image.png");

                // Create the Vision Taxonomy
                List<VisualFeatureTypes?> features = new List<VisualFeatureTypes?>() {
                    VisualFeatureTypes.Categories, VisualFeatureTypes.Description,
                    VisualFeatureTypes.Faces, VisualFeatureTypes.ImageType,
                    VisualFeatureTypes.Tags, VisualFeatureTypes.Adult,
                    VisualFeatureTypes.Color, VisualFeatureTypes.Brands,

                ImageAnalysis results;

                // Process the downloaded file
                using (Stream imageStream = File.OpenRead("image.png"))
                    results = await client.AnalyzeImageInStreamAsync(imageStream, visualFeatures: features);

                // Create a new Image Analysis Model
                ImageAnalysisViewModel imageAnalysis = new ImageAnalysisViewModel
                    ImageAnalysisResult = results

                // Search and apply appropriate tags
                foreach (var result in imageAnalysis.ImageAnalysisResult.Tags)
                    string tag = result.Name;
                    string hint = result.Hint;
                    string confScore = result.Confidence.ToString();

                return imageAnalysis;
            catch (Exception e)

            return null;

        public class ImageAnalysisViewModel
            public ImageAnalysis ImageAnalysisResult { get; set; }

GitHub code is available here:

Leave a comment