I'm finding the right way to use AWS Rekognition service.
My problem is How to verify a person image on multi collections, I'm reading Build Your Own Face Recognition Service Using Amazon Rekognition | AWS Machine Learning Blog from Amazon but cannot find the implementation document for it. My point is Face verification title.
Update 1:
My target is: Using AWS Rekognition to get person's info by their face.
My problem is: How to make AWS Rekognition improves its accuracy when recognizing a face.
What I tried:
Upload multi captured portraits of a person with same ExternalImageID but I'm not sure it works or not.
Finding a way to create Collection for each person, then upload person's portraits to their Collection but I don't how to search a face through multiple Collections.
I'm trying use S3 for storage people's images then using Lambda function to do something that I've not got yet.
Update 2:
What is your input material: Input materials are some people's portrait photo with ExternalImageID is their name (eg: my portrait photo will have ExternalImageID is "Long").
What are you trying to do: I'm trying to get ExternalImageID when I send a portrait photo of a registered person. (eg: with my other portrait photo, AWS has to response ExternalImageID is "Long").
Do you have it working, but it is not recognizing some people? Yes, it's work but sometimes it cannot recognize exactly people.
Please tell us your use-case / scenario and what you are trying to accomplish:
Create an AWS Rekognition collection with sample name (eg facetest).
Register some people with their name is ExternalImageID.
Submit an image to AWS Rekognition API to get ExternalImageID - his name.
Okay, so basically you have it working but it doesn't always recognise the person. I'll assume it does not even list the person in the response, even with a low percentage.
I would recommend adding multiple images of the same person to the Face Collection, specifying the same ExternalImageId for each image. (Use one Face Collection with all people in it, including multiple images of the same person.)
Please note that "If you provide the same image, specify the same collection, and use the same external ID in the IndexFaces operation, Amazon Rekognition doesn't save duplicate face metadata." However, adding different images with the same ExternalImageId should be fine.
Related
I've followed these tutorials:
Amazon's - https://docs.aws.amazon.com/sagemaker/latest/dg/sms-getting-started.html
Medium.com - https://medium.com/#bruceyanghy/end-to-end-guide-for-setting-up-aws-sagemaker-ground-truth-public-data-labeling-jobs-8732cf49b865
I'm attempting to run a basic object detection (images with bounding boxes) Ground Truth labeling job with Mechanical Turk. I've tried multiple times, opening up any and all security on the S3 bucket containing the images. My past two attempts have been the closest, but still only manage 32/389 images labeled (357 Failed) and 62/389 images labeled (327 Failed). The images are exactly the same in both attempts.
Checking the manifest file for clues, the only error I get is:
<Code>InvalidArgument</Code>
<Message>Requests specifying Server Side Encryption with AWS KMS managed keys require AWS Signature Version 4.</Message>
<ArgumentName>Authorization</ArgumentName>
<ArgumentValue>null</ArgumentValue>
I can't find any references anywhere as to what I need to change to make this work. I've tried with and without server-side encryption on the S3 bucket.
How do I change this signature version?
I'm trying to do a quick PoC on the AWS Rekognition custom labels feature. I'd like to try using it for object detection.
I've had a couple of attempts at setting it up using only tools in the AWS Console. I'm using images imported from the Rekognition bucket in S3, then I added bounding boxes using the tools in the Rekognition console.
All of my images are marked up with bounding boxes, no whole image labels have been used. I have 9 labels, all of which appear in at least 1 drawing.
I've ensured my images are less than 4096x4096 in size (which is mentioned on this AWS forums thread as a possible cause of this issue.
When I attempt to train my model I get the "The manifest file contains too many invalid data objects" error.
What could be wrong here? An error message complaining about the format of a file I didn't create manually, that I can't see or edit isn't exactly intuitive.
I can manage to add an image to AWS Rekognition Collection using the IndexFacesRequest.
However, to improve accuracy I would like to add more images of the same user. How do I let the request know it is the same user?
Rekognition does not allow you to provide multiple face images for a single face ID. But you can upload multiple faces of the same person and give them the same ExternalImageId. That's the ID that you typically use to correlate a face match to your person database. When your app later presents a face for matching, Rekognition will return zero or more face matches.
I have a collection of profile images from customers I need to be able to pass a selfie of the person and scan it across the collection of images and pull up the customer information.
Need to do the following using AWS Rekognition -
Create a collection - Done
Add Images to the collection - Whats the REST API syntax for this
While adding the images to the collection also tag it with the customer name.
Take a selfie portrait and search across the collection and return the tag information which matches.
Im using Flutter as a platform hence there is no support for AWS SDK so will need to make REST API calls.
However the AWS docs don't provide much information for REST support.
The APIs are documented. For example to detect faces in an image and add them to a collection, see IndexFaces.
I'd personally recommend getting comfortable with Rekognition via the awscli (or Python/boto3) briefly before you move to the Rest API.
On the name tagging front, you assign an 'external ID' to faces when adding them to a collection. That external ID is the correlator that you supply and that Rekognition stores. Later, when you ask Rekognition if a given face matches one already in a collection, Rekognition will return you the external ID. That can then be used as a lookup into some database that you have to identify the person's name, date of birth, or whatever.
In Azure Cognitive Image processing the returned json have a "caption" field which summarizes the content of the image. However, I didn't find anything similar in AWS.
In Amazon Rekognition for image processing how do I get the caption for an image?
You would use the DetectLabels - Amazon Rekognition command:
Detects instances of real-world entities within an image (JPEG or PNG) provided as input. This includes objects like flower, tree, and table; events like wedding, graduation, and birthday party; and concepts like landscape, evening, and nature.