Face Recognition for the Education Industry

• Identify the orientation of the image whether it is portrait or landscape.
• The team did an implementation using pillow tools to reject those images that have a landscape view.

Support multiple image [JPEG, JPG, PNG] format when uploading

• VIPL team implements a solution for image quality validation.
• Different types of checks have been implemented as below,

  Blur

  

  Bad Contrast

  

  Glare/Over-Exposure

  
• With the above check it will pass for further analysis of facial recognition.

• The Variance Team uses a technique to validate the face to verify that the image contains the face of the person at the proper angle.
• Also, the face of the person should cover some percentage of the image e.g., if there was a need that the face must cover 60% of the image otherwise the image is of no use.

• Image comparison technique for fraud detection in examination centers.
• The Variance AI team implemented image comparison with stored Photos during registration with the real-time photo of the student.
• As per the criteria set it will allow/reject students from appearing for the examination if the image is mismatched.

• Image comparison also validates Background Verification with color based on the RGB values of the image.

• The Image resizing technique is used to resize images based on aspect ratio.
• The Variance AI team used the following scenarios to manage image resizing.
• From The aspect ratio and height, it will calculate the width.
• From The height, it will calculate the width and aspect ratio and resize the image accordingly.
• From The height and width, it will auto-resize the image accordingly.

• With image resizing, it will be easy for the exam center to properly validate face detection.

This feature was developed by the Variance AI team to compress images using various algorithms without lossing the image quality.

The following technique has been used to compress images.

• RLE (Run-length encoding)