Linear Filtering

Linear Filtering

[@newbie8051]

Mind boggling that this 1hr lecture is so information dense that the same topics were covered in 3hrs at my university. Shoutout to Prof Pritee Khanna for taking 3hrs to explain this, nptel lectures are very dense and fast-forwarded

[@ieatplantsforaliving168]

Convolution operation is translation-equivariant, not invariant as the output of the conv. operation changes when an object of interest is translated in the input. CNNs are however a bit more robust to translation, they can learn to be translation invariant (due to pooling layers).

[@ronireznik1632]

In the slide of edge filter there are misleading of opposite operation at at horizontal and vertical gradient.

[@SaurabhSingh74]

There is a typo in the 2d Gaussian function -- 2 is missing from the denominator of the exponent.

[@m.d.r3086]

great the explanation, i want the lectures as pdf plz

[@SomeshChatterjee]

Fantastic lecture!

[@jsridhar72]

May be. But I could not understand it.

[@PannagaSudarshan]

Our savior

[@muneebth5508]

Thank you very much

[@Hello_am_Mr_Jello]

Walhindi