Rekognition | Open Source alternative to Amazon 's Rekognition service | Computer Vision library

Scenario

Front end is basically a React Native (Expo) application where users can issue a report - this includes taking multiple photos and filling in some details.

Backend is just node.js, with Express & Multer.

Problem

I use Axios to send the images and form data through FormData(), however on the server side, req.body and req.files consist of nothing.

One thing here is that sending the SAME data through POSTMAN works COMPLETELY fine, the images were stored into S3 and the form details were stored in the database. It is through the app/emulator that does not work.

I've tried removing the "multipart/form-data" header and this is the output from console.log(req.body) (req.files show undefined):

I am doing the walkthrough for building a full stack app with Amplify and am stuck on the third module, adding auth. I followed all the instructions to a T but my build is failing saying there are invalid feature flags like so.

When I upload image to s3 bucket and call AWS Rekognition detect_labels I am getting dictionary of detected labels like below

{'Labels': [{'Name': 'Plant', 'Confidence': 99.70314025878906, 'Instances': [], 'Parents': []}, {'Name': 'Flower', 'Confidence': 98.37027740478516, 'Instances': [], 'Parents': [{'Name': 'Plant'}]}

but here I need to return the image with bounding box where the object is identified, how this can be achieved ?

I will keep this as brief as possible. I have a problem in which I need to wait for the completion of multiple AWS tasks that push to SQS/SNS on completion (Transcribe, Rekognition). Currently, my architecture is to initiate one task, wait for it to finish, then initiate the next one and so on. I would like to change this to all of the tasks initiating at once, and when all of them are complete, run a lambda script. What service / architecture should I use for this? Thank you so much!!

I am trying to create one nested Python dictionary called Results.

I am using AWS Rekognition to get an image and output the results.

The results_dict only contains one result after it's complated, and I wish to have all the results in one nested loop

I'm trying to get:

I'm running into LimitExceededException when starting new AWS Rekognition jobs with the StartFaceDetection API call, so I would like to see a list of my currently running face detection jobs. The GetFaceDetection command apparently requires you to pass in a specific single job ID, but I would like to see all jobs that are currently in progress (or even all jobs that were started recently). Is this possible?

Problem:

I'm starting to use Amazon Rekognition label detection, the problem is that I don't know how to pass a url to the DetectLabelsRequest () object. That url contains an image which is the one I need to analyze.

Code:

I am beginning to insert myself in the world of AWS, specifically in Amazon Rekognition. I can't find any example on how to use it. So, is there an example made in android studio, on how to use Amazon Rekognition, to detect objects in an image?

I am building an android app which will authenticate user with AWS Rekognition facial verification. The app might be running in remote areas where internet and cellular connectivity are not available.

It it possible to pre-download all the face metadata stored in AWS and perform facial verification offline in the android app?