Number of input and output field

Number of input field	:	Two
Number of output field	:	One

This transformation function is used to calculate the similarity between an image and the frames of a video.

The output of this transformation function is a string in the following format:
<frame_no>,<similarity>;<frame_no>,<similarity>;...

This output can be split and transposed in the next assembly to obtain relevant and structured results.

This transformation function uses the following parameters:

1. Key Point Descriptor
   Specifies the descriptor used to compare the image with video frames.
2. Lower Bound Similarity
   Specifies the minimum similarity threshold.
   Only similarity values greater than or equal to this threshold are passed to the next assembly.

Available key point descriptor methods:

• SIFT
  (Scale Invariant Feature Transform) face-image descriptor.
• SURF
  (Speeded-Up Robust Features) face-image descriptor.
• BRIEF
  (Robust Independent Elementary Features) image descriptor
• ROOTSIFT
  (Normalized Scale Invariant Feature Transform) face-image descriptor..