Computer Science Stack Exchange
Computer Science Stack Exchange

Questions tagged [features]

A feature is a property which can be used to describe objects in machine learning. Most of the time those are values in R^n, but not always.

34 questions
9
votes
1 answer

What is the difference between 'features' and 'descriptors' in computer vision / machine learning?

I've read multiple time sentences similar to Finally, for standard image classification bag-of-words features based on SIFT descriptors have been found critical for high performances. We first compute a standard SIFT discriptor at regular…
Martin Thoma
  • 2,360
  • 1
  • 22
  • 41
7
votes
2 answers

Why do AlphaGo and AlphaGo Zero include board history in the input features

Both AlphaGo and AlphaGo Zero include prior board states as input features (the "Turns Since" planes for AlphaGo, and the repeated 8-step history planes for AlphaGo Zero). What is the purpose of including this history information in the input to the…
Mankarse
  • 183
  • 5
4
votes
0 answers

What are the best features to identify heads from any angle?

I want to automatically track heads in CCTV records. Sometimes I need to re-identify heads because of multiple heads crossing each other. So I continually need to extract features from tracked heads so that I will be able to re-identify them when…
Dubrzr
  • 141
  • 3
3
votes
1 answer

Classification training data, but regression prediction

Suppose I'm performing machine learning on a simple dataset, and have a bunch of training data of the form: x (feature) y (label) ----------------------- 1 0 2 1 3 1 4 0 5 1 6 …
sir_thursday
  • 219
  • 2
  • 7
3
votes
1 answer

Convolutional Neural Network Feature Engineering?

I'm working through the tensorflow tutorial, and I see how you go from 28 x 28 to zero-padding and applying a 5x5x32 convolution to get 28x28x32 and max-pooling etc. What I'm confused about is the 32 outputs seem to be described as filters acting…
Rob
  • 314
  • 1
  • 2
  • 12
3
votes
1 answer

Largest isomorphic subgraphs of two graphs with features

the following question came up in a problem I am working on: Suppose you have two graphs $G_1=(V_1, E_1), G_2=(V_2,E_2)$ that have features attached to them, i.e. to every $v\in V_1$ or $v\in V_2$ there is a vector $w_v\in\mathbb R^n$ with fixed $n$…
Tobias Kietreiber
  • 33
  • 3
2
votes
0 answers

How to find the matched SIFT features that are spatially consistent?

I have extracted DenseSIFT from the query and database image and quantized by kmeans. The challenge is to find those SIFT features that quantized to the same visual words and be spatially consistent (have a similar position to object centers). I…
S.EB
  • 121
  • 1
2
votes
1 answer

Computer vision methods without "pre-training"

I'm new to computer vision and I have a common question that I couldn't figure out with Internet or books. As I understood, in general, there are two main approaches in modern computer vision: neural networks based methods and more "classical"…
John Racer
  • 21
  • 1
2
votes
0 answers

Name of technique of counting pixels above geographic center line

I heard about a technique today which is sometimes used in the classification of 2D images of handwritten glyphs. It goes like this: Find the highest activated pixel of the image, the lowest activated pixel of the image, and average their heights.…
Mahkoe
  • 121
  • 3
2
votes
3 answers

Computation of normalized first derivative in discrete case

I am reading a paper on recognition of online handwritten characters. One of the features proposed in the paper is "normalized first derivatives, $(\hat{x}'_t,\hat{y}'_t)$", which they have defined as…
user7080
  • 21
  • 2
2
votes
1 answer

Description of shape in a vector form

I would like to ask for references to algorithms that can project shape information about an object to 1 dimension. Specifically I am training a neural network to be able to identify objects with similar shape as the ones in the training set. The…
tevang
  • 121
  • 3
2
votes
0 answers

How the SIFT results vary by changing some parameters

I'm studying the SIFT algorithm and I have some problem understanding its operation, in particular I don't understand how the results vary according to the parameters: number of octaves, number of levels and sigma0. I've read Lowe's original paper…
sleepwalking
  • 267
  • 1
  • 2
  • 9
2
votes
1 answer

How to detect Farkas or MPEG4 FDP points on image with a face?

Brief problem description I'm using a Basel Morphable Face Model, which was labeled with MPEG4 and Farkas landmarks. I can generate different faces, use different lighting conditions, rotations, perspective etc. I want to use it to train an…
Charlie
  • 131
  • 4
2
votes
1 answer

Use of Activation Units in Facial Expression Understanding

The topic of extracting the Facial Action Coding System (FACS) Action Units (AUs) [1] from images and it's translation into emotion prediction [2] is pretty well studied, but I'm not clear on how it stacks up against alternative approaches such as…
Seanny123
  • 651
  • 8
  • 23
2
votes
1 answer

Feature values range

Suppose I am about to use SVM for learning a classification or ranking function. Suppose that my feature vectors are two dimensional and that values for one dimension are, say, natural numbers and the values for the other dimension are real numbers…
zpavlinovic
  • 1,664
  • 10
  • 19
1
2 3