特征提取

 

在模式识别和图像处理领域中，特征提取是一种特殊的维数降阶的形式。

算法的输入数据太多而难以处理以及一些信息量很少的冗余数据，该方法转变该数据为降阶特征表示集，也称为特征向量。将输入数据转变为特征集的过程称为特征提取。 如果谨慎的选择提取的特征，特征集从输入数据中提取出相关信息，实现不使用全数据量输入的降阶表示。

 

In pattern recognition and in image processing, Feature extraction is a special form of dimensionality reduction.

When the input data to an algorithm is too large to be processed and it is suspected to be notoriously redundant (much data, but not much information) then the input data will be transformed into a reduced representation set of features (also named features vector). Transforming the input data into the set of features is called features extraction. If the features extracted are carefully chosen it is expected that the features set will extract the relevant information from the input data in order to perform the desired task using this reduced representation instead of the full size input.

[edit]General

Feature extraction involves simplifying the amount of resources required to describe a large set of data accurately. When performing analysis of complex data one of the major problems stems from the number of variables involved. Analysis with a large number of variables generally requires a large amount of memory and computation power or a classification algorithm which overfits the training sample and generalizes poorly to new samples. Feature extraction is a general term for methods of constructing combinations of the variables to get around these problems while still describing the data with sufficient accuracy.

Best results are achieved when an expert constructs a set of application-dependent features. Nevertheless, if no such expert knowledge is available general dimensionality reduction techniques may help. These include:

• Principal components analysis
• Semidefinite embedding
• Multifactor dimensionality reduction
• Nonlinear dimensionality reduction
• Isomap
• Kernel PCA
• Latent semantic analysis
• Partial least squares
• Independent Component Analysis

[edit]Image processing

It can be used in the area of image processing which involves using algorithms to detect and isolate various desired portions or shapes (features) of a digitized image or video stream. It is particularly important in the area of Optical Character Recognition.

[edit]Low-level

• Edge detection
• Corner detection
• Blob detection
• Ridge detection
• Scale-invariant feature transform

[edit]Curvature

• Edge direction, changing intensity, autocorrelation.

[edit]Image motion

• Motion detection. Area based, differential approach. Optical flow.

[edit]Shape Based

• Thresholding

• Blob extraction

• Template matching

• Hough transform
  • Lines
  • Circles/Ellipse
  • Arbitrary shapes (Generalized Hough Transform)

[edit]Flexible methods

• Deformable, parameterized shapes
• Active contours (snakes)

[edit]References

• JMLR Special Issue on Variable and Feature Selection

[edit]See also

• Cluster analysis
• Dimensionality reduction
• Feature detection
• Feature selection
• Data mining
• Connected component labeling
• Segmentation (image processing)

  This computer graphics-related article is a stub. You can help Wikipedia by expanding it.