US 12,217,467 B2
System and method for image compression based on machine learning
Omar Ahmad Abdo Al Tamimi, Amman (JO); and Tareq Aljaber, Brentwood, CA (US)
Filed by Averroes.ai Inc., San Mateo, CA (US)
Filed on Jan. 10, 2022, as Appl. No. 17/571,538.
Claims priority of provisional application 63/135,552, filed on Jan. 8, 2021.
Prior Publication US 2022/0222865 A1, Jul. 14, 2022
Int. Cl. G06T 9/00 (2006.01); G06N 3/045 (2023.01); G06T 3/4046 (2024.01)
CPC G06T 9/002 (2013.01) [G06N 3/045 (2023.01); G06T 3/4046 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method for dynamic compression of image data with high compression ratio and high fidelity, the method implemented in a system comprising a processor and a memory, the method comprising the steps of:
constructing a convolution neural network based quantized autoencoder network comprising an encoder network, a bottleneck network, and a decoder network,
wherein the encoder network comprises one or more convolution compression blocks each having two convolution layers, the encoder network upon execution by the processor receives an input image data and reduces dimensions of the input image data by dynamic processing the input image data using the one or more convolution compression blocks in series,
wherein the bottleneck network upon execution by the processor receives an unquantized compression representation of the input image data as an output of the encoder network, wherein the bottleneck network comprises fake quantization module, a secondary encoder, and a secondary decoder,
wherein the decoder network upon execution by the processor receives a quantized compressed representation of the input image data as an output of the bottleneck network, restructure the quantized compressed representation of the input image data to obtain a compressed output image, the decoder network comprises a plurality of forward blocks.