Performance Evaluation of Image Compression Algorithms for Medical Retinal Images

Şimşek A., Şimşek I. B., DÜNDAR G.

30th International Conference on Information, Communication and Automation Technologies, ICAT 2025, Sarajevo, Bosna-Hersek, 2 - 04 Eylül 2025, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/icat66432.2025.11189270
  • Basıldığı Şehir: Sarajevo
  • Basıldığı Ülke: Bosna-Hersek
  • Anahtar Kelimeler: HEIC, HEIF, HEVC, image coding, intra-coding, JPEG, JPEG2000, lossless compression, lossy compression, medical image coding, MS-SSIM, PNG, PSNR, SSIM, video coding, VVC
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Starting with the JPEG standard in the early 90s, in order to use storage space or transmission media more efficiently, various image and video compression methods have emerged. Within the scope of this study, lossy and lossless compression performances of JPEG, JPEG2000, PNG, HEVC and VVC standards for retinal fundus and retinal radial scan images of real patients were studied and for a contemporary retinal image database, the type of the compression algorithm to use was evaluated quantitatively based on the compression efficiency (number of bits produced), quality (Y-PSNR and MS-SSIM metrics) and complexity (coding time).