The Effect of Convolutional Encoder-Decoder Architecture on Lossless Image Compression Applications Kayipsiz G r nt Siki stirma Uygulamalarinda Evri simsel Kodlayici-Kod z c Mimarinin Etkisi

Arpaci S. A., DİRİ B., VARLI S.

2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025, Bursa, Türkiye, 10 - 12 Eylül 2025, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/asyu67174.2025.11208260
  • Basıldığı Şehir: Bursa
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: encoder decoder model, Huffman, image reconstruction, lossless image compression, R2U-Net
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

According to the results we obtained, we can state that although the Huffman method fully performs the lossless compression task, quality measurements decrease depending on the synthetic images processed by the method. Therefore, this situation increases the responsibility of the image reconstruction models in the system in terms of being able to create a similar, quality image to the original image. Within the scope of the evaluation, it is shown more clearly with this study that image encoder-decoder (image reconstruction) methods, which are integrated into most current lossless compression methods, affect the performance of lossless compression methods.