Face Recognition System deployed in a Govt recognized Export House

CUSTOMER :

Customer is a leading Govt recognized Export House having Oeko – Tex Certification from Hohenstein Textile Testing Institute GmbH & Co., Germany and BSCI Certified by SGS India Pvt Ltd. A professionally managed company having its major presence in Home Furnishing Products.

A community of over 240 Artisans, Craftsmen, Tailors, Weavers, Tufters, Designers and Talented Professionals and their very own product development team of 25, they provide to many customers all over the world from single store owners to huge multi-national retailers.

 

CHALLENGE :

Given the size of their infrastructure sprawled over an area of 2,00,000 sq.ft. , with their  entire manufacturing operations from dyeing ,weaving, tufting to fabrication & confectioning being in-house, the Customer decided to implement a solution for a robust attendance management system which will automatically mark the attendance of the person as soon as he/she comes within the detection range of the camera.

The goal of the project was to recognize faces of the people entering the company premises and  add information about them into the database for further analysis.

As the same people enter the company again, their faces would be recognized based on the recorded data to enable the Customer to track attendance and eliminate false attendance thereby enhancing the customer’s productivity , reducing cost and increasing security.

 

 

SOLUTION :

Synergylabs divided this face recognition solution process into two main stages to enable:

• Face image capture

• Face recognition

 

 

OUR APPROACH :

• Preprocessing with specifically processed input images to make customers’ faces recognizable.

• Calculating landmarks, i.e. some particular facial features.

• Face recognition using calculated landmarks and special criteria.

During the work on this project the team investigated a set of algorithms and methods which allowed to implement the Customer’s requirements and build the system that works with a high percentage of correct results.

 

RESULTS : 

Our FaceRec solution was able to detect all subjects successfully with an accuracy of recognition over 90% and the Customer received a solution that allowed to recognize employees and unknown visitors.