13 votes

Is deep learning killing image processing/computer vision?

Today we had a discussion with a friend of mine. It was a rainy day here in Munich, while a large portion of Europe was having a kind of sunny atmosphere. People were sharing photographs in social ...
Tolga Birdal's user avatar
  • 5,465
10 votes
Accepted

When is a network called end-to-end training?

From feature extraction to learning the desired result, deep learning algorithms can act as full pipelines for solving tasks at hand. End-to-end learning usually refers to omitting any hand-crafted ...
Tolga Birdal's user avatar
  • 5,465
9 votes

A Machine Learning Based Algorithm as an Alternative to the Matched Filter

Sure, you can learn the matched filter, as convolution with a filter is just a function applied to a signal, and e.g. Neural Networks (through the universal approximation theorem) are good function ...
Marcus Müller's user avatar
6 votes

Is deep learning killing image processing/computer vision?

Data engineering is still used in machine learning to preprocess and select the data fed to DNNs to improve their learning time and their evaluation efficiency. Image processing (the stuff between ...
hotpaw2's user avatar
  • 35.3k
6 votes
Accepted

Downsampling audio for use in Machine Learning

Is this necessary if I only intend to use the data in the Neural Network toolkit provided by the repo I linked? Yes. Whether or not you are downsampling (instead of just decimating) has nothing to ...
A_A's user avatar
  • 10.7k
6 votes

Is there a penis-detection demo similar to face-detection?

Is there a script / tutorial / demo for penis detection? [...] Fairly serious quesion, future of internet memes is at stake Yes, there is. Common Pattern Recognition techniques will be able to spot ...
A_A's user avatar
  • 10.7k
6 votes
Accepted

Resource recommendations to learn audio processing

Here are a few books that might be helpful: The Scientist and Engineer's Guide to Digital Signal Processing A good resource for you to get familiarized with DSP in general. Understanding Digital ...
Ahsan Yousaf's user avatar
  • 1,533
5 votes
Accepted

Relationship between information retrieval and source separation in signal processing

There are, a few discrepancies that might be making a difference here. My suggestion would be to edit the question for clarity. There are quite a few assumptions that lead to non-straightforward ...
A_A's user avatar
  • 10.7k
5 votes

Is deep learning killing image processing/computer vision?

A thorough understanding of signal processing (along with linear algebra, vector calculus, mathematical statistics etc.) is imo indispensable for non-trivial work in the field of deep learning, ...
AruniRC's user avatar
  • 180
5 votes

Converting speech audio to telephone audio

Band-pass filtering with cut-off frequencies of 300 Hz and 3400 Hz should result in a good approximation. Try with a Chebychev filter or order not more than 6. Then you may need to downsample your ...
Juancho's user avatar
  • 5,016
4 votes

Feature extraction for sound classification

Non-verbal Audio (let alone environmental) seems to be the little brother to main stream machine learning media types like images, speech, text. To answer your question is it possible to train a ...
beeCwright's user avatar
4 votes

What is the type of these signals?

Types of signals: According to their range set (values): Real Valued, Complex valued ; According to their dimensions: Scalar, Vector ; According to their values: Continuous Amplitude, Quantized ; ...
Fat32's user avatar
  • 28.2k
4 votes
Accepted

Deep Learning: Classification vs. Convolution for Signal Restoration

By deep learning, I'll assume you mean neural network. To develop a neural network, you'll need labeled data. This means you need a bunch of example inputs ($r$) and outputs ($X$). Once you have that, ...
Engineer's user avatar
  • 3,032
4 votes

Help with denoising signal and periodogram analysis resources

Firstly, I am confused if I am supposed to filter my signals to get rid of any frequencies above the Nyquist frequency. My sampling frequency is 32Hz and my time series is somewhat noisy and has some ...
Marcus Müller's user avatar
4 votes

Recommendation for courses / studies on digital signal processing

I've kind of grouped your subjects into larger overall subjects. Note that there's a lot of overlap here, with the possible exception of actually making it work in a microprocessor (except -- in my ...
TimWescott's user avatar
  • 12.7k
4 votes

Resource recommendations to learn audio processing

Julius O. Smith's original book is here: Julius O. Smith III,'s Spectral Audio Signal Processing, which is available online. And for a music background, I'd recommend: Bill Sethares' Tuning, Timbre,...
Peter K.'s user avatar
  • 25.7k
3 votes

Is deep learning killing image processing/computer vision?

My perspective from university was that many signal processing people were a bit hostile toward ML, I suspect because they felt threatened that it was encroaching on their domain. But recently there's ...
Austin's user avatar
  • 281
3 votes

What does it mean to train and test a data for feature extraction?

This is a concept in supervised machine learning. Train data: Used to train your supervised ML model. This data contains both the input and the desired output, which is compared with the output from ...
V Shreyas's user avatar
  • 131
3 votes

Feature extraction for sound classification

Here is a solution for sound classification for 10 classes: dog barking, car horn, children playing etc. It is based on tensorflow library using neural networks. Features are extracted by converting ...
abggcv's user avatar
  • 151
3 votes
Accepted

How we calculate Precision-Recall Curve?

You're right. When you just have a single precision and a single recall value, you get a precision-recall point, not a curve. However, machine learning models typically do not output discrete ...
Dave's user avatar
  • 296
3 votes
Accepted

Lloyd Max Quantization and Clustering : Part 1

Different. Lloyd-Max is a special type of scalar quantizer design which is optimized (in terms of MSE) to source pdf. Hence the quantizer is generally non-uniform. Lloyd's algorithm (and the more ...
msm's user avatar
  • 4,285
3 votes

Formula to calculate Cepstral coefficients (not MFCC)

Linear Prediction Cepstral Coefficients (LPCC) can easily be computed from LPC (Linear Prediction Coefficients) and I think that a LPC function is implemented in the same package as the MFCC. All you ...
Louis Lac's user avatar
  • 378
3 votes
Accepted

Apply Principal Component Analysis (PCA) for RGB Images

General Idea The general idea of Principal Component Analysis (PCA) is as following (Intuition over formalism): Given a set of points in space (Inner Product Space) find a set of vectors (Directions) ...
Royi's user avatar
  • 19.6k
3 votes

Machine learning for denoising MRI images

My personal feeling is that you should do each things separately and compare the results. For example, take your MRI dataset and denoise using "standard algorithm 1", "standard algorithm 2" and "...
brechmos's user avatar
  • 131
3 votes

Modeling audio effects, reverse engineering

Now is there a general method to analyze and determine the exact function of that effect No, there can't be. Effects can (and will be) arbitrary, non-linear, memory-affected mappings. You will have ...
Marcus Müller's user avatar
3 votes

Time Frequency Analysis by Frequency Contour Detection in Spectrogram

The OP is interested in detecting the presence of frequencies in the 155 to 165 Hz frequency band within a block of data (or any other defined frequency band). The spectrogram is useful to observe ...
Dan Boschen's user avatar
  • 51.4k
3 votes

Upsampling vs downsampling. Which to use when?

You should use the one you need for your problem, when you know which components of your signal are of interest to you. Let's say you have in your electronic editing an ADC digitizing 40M samples per ...
Nathan Huchon's user avatar
3 votes

Help with denoising signal and periodogram analysis resources

The Fourier transform of a sampled (discrete time) signal can only have information between -Fs/2 and +Fs/2, and that information repeats such that X(f +Fs) = X(f), such that Fs is the sampling ...
Dan Szabo's user avatar
  • 1,038

Only top scored, non community-wiki answers of a minimum length are eligible