Data compression with Deep Autoencoder

Initial Situation

• Estimation of wooden log rotation angle by comparison with N reference images
• Loading time of raw reference images too slow for real time system
• Requirement: Decrease loading time, while keeping accuracy

Solution

• Development of Deep Autoencoder for Image compression
• Evaluation of different image compression algorithms for faster loading/storing times

Results

• Faster loading times (x10) by compressing the reference images with the Deep Autoencoder
• Similar accuracy for the rotation estimation
• Concept for improved rotation matching strategy