1

I am building a Convolutional Neural Network(CNN) Model for Face recognition.

As a initial step of training data collection, what would be the preferable image format for training, Grey or RGB?

I have gone through few articles saying grey-scale images are best for face recognition, but have not get the satisfactory information for why so?

For this approach, what are the advantages & disadvantages of using grey over RGB?

For Face recognition model, is is necessary to have color information or will I lose the useful information from the image upon grey conversion?

How the prediction accuracy varies from one to another?

Nicolas Raoul
  • 58,567
  • 58
  • 222
  • 373
Pushpa
  • 892
  • 1
  • 12
  • 30

1 Answers1

0

Rather than considering face recognition as a specific problem, we can also consider the general field of image analysis, particularly with the use of CNNs.

We generally like to simplify problems in machine learning to reduce noise and the volumne of data which needs to be processed.

Simplicity - Many image processing operations work on a plane of image data (e.g., a single color channel) at a time. So if you have an RGBA image you might need to apply the operation on each of the four image planes and then combine the results. Gray scale images only contain one image plane (containing the gray scale intensity values).

Data reduction - Suppose you have a RGBA image (red-green-blue-alpha). If you converted this image to gray scale you would only need to process 1/4 of the data compared to the color image. For many image processing applications, especially video processing (e.g., real-time object tracking), this data reduction allows the algorithm to run in a reasonable amount of time.

Is conversion to gray scale a necessary step in Image preprocessing?

Community
  • 1
  • 1
JP1
  • 731
  • 1
  • 10
  • 27