Since working with 2d arrays is computationally efficient than working with 3d arrays, in some use cases we might prefer to work with grayscale image to save time and resources. This is preferred because grayscale images retain most of the relevant details of an image except the color data. But if our use case is to say for example classify images of red and blue balls then grayscale conversation will be useless. We should keep that in mind
Trivia question from the video: What is the need for
converting a color image to greyscale when building computer vision algorithms?
Because its easy and efficient to work with 2-d array(grayscale) rather than a 3-d. Although both have same amount of details
Since working with 2d arrays is computationally efficient than working with 3d arrays, in some use cases we might prefer to work with grayscale image to save time and resources. This is preferred because grayscale images retain most of the relevant details of an image except the color data. But if our use case is to say for example classify images of red and blue balls then grayscale conversation will be useless. We should keep that in mind
Love the explanation provided 👌🏻
Thanks Sahil
Sir can you please upload the jupyter code on your github respository
Please cover the course fast