Utilizing the similarity preserving properties of self-organizing maps in vector quantization of images.
Jari KangasPublished in: ICNN (1995)
Keyphrases
- vector quantization
- self organizing maps
- neural gas
- vector quantized
- distortion measure
- image compression
- color quantization
- vector quantizer
- input data
- image data
- som neural network
- similarity measure
- image classification
- object recognition
- competitive learning
- neural network
- image features
- image retrieval
- codebook design
- finite state vector quantization
- feature maps
- unsupervised learning
- input image
- structural similarity
- visual features
- image quality
- fractal image coding
- k means
- artificial neural networks
- computer vision
- data sets