Low complexity H.264 encoder using Machine learning

The macroblock mode decision in inter frames is computationally the most expensive process due to the use of features such as variable block size, motion estimation and quarter pixel motion compensation. Hence, the goal of this project is to reduce the encoding time while conserving the quality and compression ratio. Machine learning has been used to decide the mode decisions and hence reduce the motion estimation time. The proposed machine learning method on an average decreases the encoding time by 42.864% for mode decisions in H.264 encoder and .01% decrease in SSIM.