Matlab - Face Recognition


Identification is a more complex task than verification. In this case, the Face Recognition is provided a probe image to attempt to match it with a biometric reference in the gallery (or not). This represents a one-to-many problem. In addition, we need to further differentiate between closed-set identification problems and open-set identification problems.

In a closed-set identification problem we want to identify a person that we know is in the reference database or gallery (in other words for any possible identification we want to make we know beforehand that the person to be identified is in the database).

Open-set identification is more complex in that we do not know in advance whether the person to be identified is or is not in the reference database.


Activity Diagram

State Chart Diagram

Sequence Diagram

Use Case Diagram


  • User should be able to save image through the application.

  • Image must be displayed on the User Interface and user must be able to perform different operations through the UI.

  • Application should have both live image clicking feature and offline image storage feautre.

User Interface:

  • User can capture live images by clicking the start camera feature or click browse photo to select pictures


  • Database gets initializated after image capture

Browse Photos:

  • User can browse photos from directory

Select Photos:

  • Photo selection from directory

Intensity Scale:

  • Scaling image according to intensity


  • Binarization operation performed on image pixels


  • Skeletonizing the image for shape and boundary detection

Skin Detection:

  • Skin grabbing operation applied to the image


  • Successful recognition of the image

Brief :

Face Recognition app tries to solve closed-set identification problem, with the use of multiple techniques i.e. skin grabbing, Principal component analysis and feature based recognition.