Vector Quantization

Vector Quantization

Quantization(量化)

Definition:

• a process of representing a large–possibly infinite – set of values with a much smaller set.
• Widely Used in Lossy Compression
• Represent certain image components with fewer bits (compression)
• With unavoidable distortions (lossy)

Design:
Find the best tradeoff between maximal compression <---> minimal distortion

Scalar quantization (标量量化)

• A mapping of an input value x into a finite number of output values,y:
  $$Q: x---> y$$

Vector Quantization (VQ)

• Vector Quantization is used in many applications such as data compression, data correction, and pattern recognition.
• Vector quantization is a lossy data compression method.
• It works by dividing a large set of vectors into groups having approximately the same number of points closest to them.
• Each group is represented by its centroid point, as in k-means and some other clustering algorithms