Hey, Greetings for the day… Hope you are doing well. I am writing this mail because of, came across your post in allbestr.com, knows that your team was looking for Application Developers. We are glad to introduce our self as One-Data Software Solutions located in the United States and India. We are the team involved in Big data Analytics, Io T, Development and Branding. I am believing that our team has strong and well-stuffed skills in fulfilling your requirements. Visit: http://www.onedatasoftware.com And we do have a ready-made site for task tracking and assigning. visit http://www.intrac.io Reach me with your requirement at harish@onedatasoftware.com

We do have similar case studies that listed below:

Product Overview:
The main goal of the product is to monitor, using Artificial Intelligence, suspects and blacklisted vehicles that enter the commercial and non-commercial buildings and inform Local Police Authority.
Challenges:
– Retrieve video stream from camera
– Recognize the frames through detection algorithm using tensor flow, keras, yolo, open cv python
– Data analysis for each frame find out specific data about car object, person object
– Recognize the face and compare matching faces with the images of suspects stored in S3 provided by police
– Send car object with number plate presented frame into license plate AWS text recognition
– License Plate Number matching with the data of suspicious vehicle numbers stored in S3
– Store suspicious found video in s3 and get metadata about that video.
Ou Solution:
Recognition Process:
System should be able to retrieve the live stream from camera without any issues. System should be able to identify the face and car license plate number for each of the video frames retrieved using tensor flow, yolo, keras, open cv python (Object and scene detection, Text analysis).
System should be able to compare the detected face, text analysis obtained from the video recognized with the suspects and suspicious plate number data stored in S3.
1)Multi-camera face detection and recognition applied to people tracking
3 Case study of face recognition system
This is a two-step process, first there is an offline procedure where the face model of each individual is captured and stored. Then, people in the scene can be reliably tracked and identified. There are three connected components that make this system work:
a) a people detector which gives probabilities of people standing at a point in the scene,
b) a face detector which searches for faces at the locations were people are expected to be found,
c) a face modelling technique to capture the information of each individual which can then be stored to a face database and used by the Face recognition algorithm to identify the individuals. Those recognitions are finally used by the people tracker to track their movement in the space and preserve their identities.
2)Images dataset
We evaluated the algorithms on the MIT+CMU frontal faces publicly available dataset that comes with annotations for the landmarks of a face (mouth, eyes and nose). From those landmarks we generated the bounding boxes of the faces and evaluated the algorithms using the MODA score.
4 Case study of face recognition system
Alert timecode stamping using Amazon SNS
System should be able to gather all metadata about the suspicious vehicle that needs to be pushed to S3 storage and alert message will send to the local police authority
Key Benefits:
 Ensure customer satisfaction through increased trust and creditability by providing accurate suspected details
 Reduces manpower required to suspect finding job.
Technical Stack:
 Open CV- Python
 Tensor Flow, yolo, keras, Face-recognition modules
 NLP procedures
A. VIOLA – JONES METHOD
B. Head location estimation
AWS:
Dynamo DB – Store Trained Faces in database for retrieve at any instance
S3 – To Store suspect detected Video with metadata
Hardware stack:
Operating Environment Local Linux Box CPU Intel Atom x5-Z8350 Processor (2M Cache, up to 1.92 GHz) OS Ubuntu 14 RAM 2GB DDR3; ROM: Onboard eMMC Flash 32 GB