A comparative study of colour retinal image coding using vector quantization: K-Means & Fuzzy C-Means

Retinal colour images play an important role in supporting medical diagnosis. Digital retinal image usually are represented in such a large data volume that takes a considerable amount of time to be accessed and displayed. Digital medical image coding therefore become crucial in medical image transfer and storage in electronic medical record server. This paper is concerned to compare the vector quantization (VQ) coding using K-means and fuzzy C-means algorithms. This research investigates the performance of each algorithm: objective (PSNR value) and subjective (visual). The VQ coding scheme is conducted separately to image components in each RGB channel. Reconstructed colour image is obtained by combining the VQ decoding result of each image channel. The 444 combination (coding of the R, G and B channels by the size of 4times4) produces the best subjective and objective quality of image coding. However, the optimum colour models for teleophthalmology and electronic medical record is 848 combination due to the file size, objective and subjective quality.