Api pdf to text12/5/2023 ![]() ![]() VisualFeatureTypes.Color, VisualFeatureTypes.Brands,Ĭonsole.WriteLine($"Analyzing the image. VisualFeatureTypes.Tags, VisualFeatureTypes.Adult, VisualFeatureTypes.Faces, VisualFeatureTypes.ImageType, VisualFeatureTypes.Categories, VisualFeatureTypes.Description, Creating a list that defines the features to be extracted from the image. ![]() Public static async Task AnalyzeImageUrl(ComputerVisionClient client, string imageUrl)Ĭonsole.WriteLine("-") Ĭonsole.WriteLine("ANALYZE IMAGE - URL") * brands, celebrities, landmarks, color scheme, and image types. Extracts captions, categories, tags, objects, faces, racy/adult content, New ComputerVisionClient(new ApiKeyServiceClientCredentials(key)) Public static ComputerVisionClient Authenticate(string endpoint, string key) * Creates a Computer Vision client used by each example. ReadFileUrl(client, READ_TEXT_URL_IMAGE).Wait() Var Brands = DetectBrandsObject(Results1) Ĭonsole.WriteLine("this is the Description of the Image") Ĭonsole.WriteLine("There are Adults in this Photos") įoreach (var i in Faces.FaceDescriptions)Ĭonsole.WriteLine(i.Age + " who is " + i.Gender ) Ĭonsole.WriteLine("There are Brands in this Photos") Ĭonsole.WriteLine("# Blood in PHOTO #") Ĭonsole.WriteLine("# racy in photos #") Var Faces = DetectFacesInImage(Results1) ReadFileUrl(client, READ_TEXT_URL_IMAGE).Wait() Extract text (OCR) from a URL image using the Read API Analyze an image to get features and other properties.ĪnalyzeImageUrl(client, ANALYZE_URL_IMAGE).Wait() it gives a description, if its adult, ages of people in the photo, racy or not, it can take a score as well.ĬomputerVisionClient client = Authenticate(endpoint, subscriptionKey) Static string subscriptionKey = "*********8" Private const string READ_TEXT_URL_IMAGE = "" (if i put a PDF link in here it says multiple bad requests errors (not discriptitve), but with this or any normal picture link it is fine ) Private const string ANALYZE_URL_IMAGE = "" // private const string ANALYZE_URL_IMAGE = "" Uto see blood warning uncomment this url Your help is greatly appreciated using System _ Read Text from URl Works if its a photo based. Validation is just a warpper class I was trying to simplify the return of the object, I know Amazon has Textetract but my client is Azure-based, and I don't really want to use Syncfusion tools if I can help it. I have looked around and I see that there is some mention of this Capability, but it is very sparse, there is no Github example I can find that does PDF documents.Īny suggestions or pointers on where to look. I have a project where I must read PDF from URLs or Blobs, and Extract the Text from them to use then Azure Cognitive Indexing / Search/ I am following the Examples using Computer Vision and only able to parse and extract text from Image Files.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |