TY - GEN
T1 - Deep Convolutional AutoEncoder-based Lossy Image Compression
AU - Cheng, Zhengxue
AU - Sun, Heming
AU - Takeuchi, Masaru
AU - Katto, Jiro
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/5
Y1 - 2018/9/5
N2 - Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture to replace the conventional transforms and train this CAE using a rate-distortion loss function. Second, to generate a more energy-compact representation, we utilize the principal components analysis (PCA) to rotate the feature maps produced by the CAE, and then apply the quantization and entropy coder to generate the codes. Experimental results demonstrate that our method outperforms traditional image coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak database images compared to JPEG2000. Besides, our method maintains a moderate complexity similar to JPEG2000.
AB - Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture to replace the conventional transforms and train this CAE using a rate-distortion loss function. Second, to generate a more energy-compact representation, we utilize the principal components analysis (PCA) to rotate the feature maps produced by the CAE, and then apply the quantization and entropy coder to generate the codes. Experimental results demonstrate that our method outperforms traditional image coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak database images compared to JPEG2000. Besides, our method maintains a moderate complexity similar to JPEG2000.
KW - Convolutional autoencoder
KW - Deep learning
KW - Image compression
KW - Principal component analysis
UR - http://www.scopus.com/inward/record.url?scp=85053930037&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85053930037&partnerID=8YFLogxK
U2 - 10.1109/PCS.2018.8456308
DO - 10.1109/PCS.2018.8456308
M3 - Conference contribution
AN - SCOPUS:85053930037
SN - 9781538641606
T3 - 2018 Picture Coding Symposium, PCS 2018 - Proceedings
SP - 253
EP - 257
BT - 2018 Picture Coding Symposium, PCS 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 33rd Picture Coding Symposium, PCS 2018
Y2 - 24 June 2018 through 27 June 2018
ER -