Fast Intra Prediction Mode Decision for HEVC Using Random Forest
Zhuge Yan, Siu‐Yeung Cho, Sherif Welsen · 2019
In this paper, we extracted specific image features that represent CU texture, incorporate a machine learning technique, namely random forest, in HEVC intra prediction mode selection, to improve the performance of intra coding of HEVC. Compared with similar algorithms, our method extracts very specific features of image texture changes in terms of angle. Therefore the proposed method can achieve very high prediction accuracy. Having similar reduction in complexity, the proposed algorithm can gain higher video quality compared with similar algorithms.