0
$\begingroup$

Does tensorflow use opencv to covert image to numpy array ? How is feature extraction done in tensorflow ? How is it different from opencv model ?

$\endgroup$
1
  • $\begingroup$ I'm not sure what exactly you refer to? Tensorflow is handling all data as Tensors? $\endgroup$ Feb 20, 2019 at 8:27

1 Answer 1

0
$\begingroup$

TensorFlow has two ways of processing image data

  1. Built-in Image Ops ( https://www.tensorflow.org/api_guides/python/image )
  2. tf.keras Pre-processing ( https://keras.io/preprocessing/image/ )

Feature extraction is at pixels / channel level. Higher level features (Such as Edge / Contrast) are learnt typically by CNN layers.

If needed, you can feed Image Data + Features extracted by OpenCV to TensorFlow.

$\endgroup$
0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.