55 votes
Accepted

Is deep learning killing image processing/computer vision?

On the top of this answer, you can see a section of updated links, where artificial intelligence, machine intelligence, deep learning or and database machine learning progressively step of the grounds ...
25 votes

What is the difference between feature detectors and feature descriptors?

An interest point (key point, salient point) detector is an algorithm that chooses points from an image based on some criterion. Typically, an interest point is a local maximum of some function, such ...
  • 4,941
22 votes

Is deep learning killing image processing/computer vision?

First, there is nothing wrong with doing grad work in image processing or computer vision and using deep learning. Deep learning is not killing image processing and computer vision, it is merely the ...
  • 4,941
17 votes
Accepted

Why Is the Canny Edge Detection Used Instead of Sobel / Prewitt Edge Detection Before Hough Transformation?

Canny Edge Detection is considered to be a better (In False Alarm sense) edge detection than those you mentioned. This is, mainly, due to 2 steps: Non Maximum Suppression - Edges candidates which are ...
  • 42.5k
14 votes
Accepted

Auto Detection of Rotation Angle on Arbitrary Image with Orthogonal Features

If I understand your method 1 correctly, with it, if you used a circularly symmetrical region and did the rotation about the center of the region, you would eliminate the region's dependency on the ...
13 votes

Is deep learning killing image processing/computer vision?

No Deep Learning isn't killing Image Processing. You need huge datasets and lots of computational resources to do deep learning. There are plenty of applications where it is desirable to be able to do ...
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 ...
  • 5,255
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 ...
  • 5,255
10 votes
Accepted

Number of dimensions? Color image vs gray scale image? Colour video vs gray scale video? Especially in the context of MATLAB

Color images are usually modeled as a vector valued function of 2D: $$ I : \mathbb{R}^{2} \to \mathbb{R}^{3} $$ Namely for 2D coordinates input it outputs 3 values (RGB). Hence images are 2D functions....
  • 42.5k
10 votes
Accepted

Universal bases (dictionary) for image compression

This is a great and interesting question. There are 2 ways to look at it, empirically and analytically. But before we start, a major detail is that when dealing with images we mainly talk about the ...
  • 42.5k
9 votes

What are some free alternatives to SIFT/ SURF that can be used in commercial applications?

I would rather look into KAZE / AKAZE, which perform equally good with significant speed-up. The deformation cases are also tolerated. OpenCV has recently obtained an implementation through GSoC 2014. ...
  • 5,255
9 votes
Accepted

How to calculate particles sizes for spheric particles with overlapping and superposition? (Example image included)

Here is what I experimented with: Use ELSD to generate elliptic contours. You could basically use any edge detector, but since in the following stages I will benefit from circle detectors, it is good ...
  • 5,255
9 votes
Accepted

Image processing vs Computer vision?

Digital image processing is an extension of digital signal processing and linear system theory into two dimensional signals. Image processing involves all low level tasks such as filter design and ...
  • 27.1k
8 votes

Best way of segmenting veins in leaves?

Following on from the above excellent answer, here is how to do it in python using scikit funcitons. ...
8 votes
Accepted

The small red peak in the CIE standard observer

Probably you've noticed that primarities are $\mathbf{X}$, $\mathbf{Y}$, $\mathbf{Z}$, not $\mathbf{R}$, $\mathbf{G}$, $\mathbf{B}$ (which are corresponding to the color values $R$,$G$,$B$). This is ...
  • 10.7k
8 votes
Accepted

Suggested Preprocessing methods for OCR on Circular Images

Here is what I did for a client (What you are asking is the same). Assuming that you have access to certain type of a pattern on the image (or the center of the hole), you could always detect the ...
  • 5,255
8 votes

What is phase congruency?

The more that sinewaves that have a zero crossing in the same direction at the same point add up in magnitude, the greater the contrast at that point. e.g. a possible edge. Phase congruency is ...
  • 34.1k
8 votes

Why Should the Sum of Masks / Kernel / Filter in Image Processing be One?

When you're trying to create a blurring kernel (namely a weighted mean of the data) you keep the mask sum as one. This preserves the mean of the filtered image (think about the DFT, if the sum mask is ...
  • 42.5k
8 votes

How to Use Maximum a Posteriori Probability (MAP) in Classification Task

I will try to give you some intuition into it by a different example. Think we have 3 machines which can generate the numbers 1, 2, 3. The first machine generates the number 1 with 80% and the ...
  • 42.5k
8 votes

Is deep learning killing image processing/computer vision?

The short answer is, No. DL can recognize a mug in a photo, but this doesn't kill signal processing in anyway. That said, your question is quite relevant in these troubled days. There is a nice panel ...
  • 236
8 votes
Accepted

Comparison Between Guided Filter (Edge Preserving Filter) and Gaussian Filter

Create a synthetic image with abrupt change form black to white (Better yest from Dark Gray to Bright Gray). Add Gaussian Noise to it. Filter it with Guided Filter and Gaussian Filter. Look at the ...
  • 42.5k
8 votes

Difference between optical flow field and motion field?

well, have you ever seen a rotating barber's poll? It looks like the stripes are moving up (optical flow), but of course the motion of the thing is a rotation in the horizontal plane. The rationale ...
8 votes
Accepted

What's the Difference Between UQI and SSIM Measures for Image Similarity / Quality?

The developers of both are the same hence the similarity is indeed "By Design". The only difference is the addition of 2 constants in SSIM (C1 and C2). The UQI: The SSIM: As the writers write in ...
  • 42.5k
8 votes
Accepted

Simple Image Edge Preserving Filter

Recently I have seen the paper Hui Yin, Yuanhao Gong, Guoping Qiu - Side Window Filtering. They suggest a really simple filtering framework for Edge Preserving Filter: Basically, what they suggest is ...
  • 42.5k
7 votes

Looking for Open Source Image Processing Library that is equivalent to HIPS

It sounds like ImageMagick is a good fit for you. Give it a try and tell us what you think.
  • 42.5k
7 votes

camera calibration: why chessboards?

This is mostly a matter of history. Checkerboard patterns have proven in the past to: yield calibration accurate results be easy and robust to implement. This was confirmed (for example) by a ...
  • 3,887
7 votes

Convex Optimization in Signal and Image Processing

Papers Interpolation by Solving an Optimization Problem. The Chebyshev Center Problem could be thought as Robust Localization Problem. Books Daniel P. Palomar, Yonina C. Eldar - Convex Optimization ...
  • 42.5k
7 votes
Accepted

Converting from RGB to LAB Color Space to Reduce Colors

You should read about LAB Color Space. Its main advantage on RGB is by having 1 channel dedicated to the Luminosity of the Image and 2 others dedicated to the color information. This means if you ...
  • 42.5k
7 votes

Can deep neural networks achieve real-time video analysis?

Nvidia seems to have published some white papers comparing DNN inference performance between high-powered CPUs and (of course) Nvidia GPUs. (one example) Ballpark seems to be that some systems can ...
  • 34.1k
7 votes

Palm Pilot Graffiti

It seems most of the data is in Graffiti (Palm OS) - Wikipedia. It seems the technology is related to Unistrokes technology (U.S. Patent 5,596,656, granted in 1997). Since the model relies on single ...
  • 42.5k

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