Hacker News Reader

Comment by Diti | Hacker News Reader

This is DEFINITELY NOT explained like I’m five. More like late high school level (mathematical planes, frequencies) and above (matrixes). I appreciate the author’s attempt at vulgarization but the title is wrong.

View on HN

You mean you didn't understand this when you were 5?

> In simple terms, the Discrete Cosine Transform takes a set of N correlated (similar) data-points and returns N de-correlated (dis-similar) data-points (coefficients) in such a way that the energy is compacted in only a few of the coefficients M where M << N.

Did you even nursery?

Props for use of "vulgarization"; I hadn't seen this word as a noun or process before but it seems to fit nicely in context.

Never seen this word before :)

Simple explanation of the concept and the use of DCT though. Perhaps, written for a person who is Five times 5? :)

Is this can be used as a feature extraction for image recognition task ? I read some time ago someone used jpeg compression as a feature extraction before DNN.

Can be for sure by examining the coefficients. It's a little hard but can be a way to do feature detection in the frequency transform.

This depends on the kind of features you're interested in.

If the features lead to clustering in the frequency domain, then yes. Otherwise it'd be detrimental.

Examples for features that'd work well are edges and lines. Features based on gradients wouldn't work well.

Reply on news.ycombinator.com