A color video image quantization method with stable and efficient color selection capability

Gong, Yongyi; Zen, Heitou; Ohsawa, Yusuke; Sakauchi, Masao

doi:10.1109/icpr.1992.201921

Cited by 5 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Colour quantisation has applications in visualisation [8,9,25,26], colour image segmentation [18], data compression [19,27] and image retrieval [28]. Early applications of colour quantisation were addressed to visualisation tasks [8,25].…”

Section: End Applications Of Colour Quantisationmentioning

confidence: 99%

“…Most work in the literature reports their application to stationary VQ problems, such as the codification of still images. As we have said before, the most successful adaptive vector quantisation strategy is that of codebook replenishment [1,12,15,19,20] whose optimality, however, has only been proved for stationary sources [21]. Codebook replenishment algorithms also pose serious parameter tuning problems that have not been properly addressed in the literature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Basic Competitive Neural Networks as Adaptive Mechanisms for Non-Stationary Colour Quantisation

González

Graña

Cottrell³

1999

NCA

View full text Add to dashboard Cite

In this paper we consider the application of two basic Competitive Neural Networks (CNN) to the adaptive computation of colour representatives on image sequences that show non-stationary distributions of pixel colours. The tested algorithms are the Simple Competitive Learning (SCL) algorithm and the Frequency-Sensitive Competitive Learning (FSCL) algorithm. Both, SCL and FCSL are the simplest adaptive methods based, respectively, on minimising the distortion and on the search for a uniform quantisation. The aim of this paper is to study several computational properties of these methods when applied to non-stationary clustering as adaptive vector quantisation algorithms. Nonstationary colour quantisation is, therefore, representative of the more general class of non-stationary clustering problems. We expect our results to be meaningful for other algorithms that involve either the minimisation of the distortion or the search for uniform quantisers. We study experimentally the effect of the size of the image sample employed in the one-pass adaptation, their robustness to initial conditions, and the effect of local versus global scheduling of the learning rate.

show abstract