ABSTRACT The emerging trend of ultra-high definition (4 K, UHD) video services necessitates coding efficiency, which is much higher than H.264. High-Efficiency Video Coding (HEVC) has been designed with the intention of drastically reducing the bit rate without compromising the video quality. The key feature is the introduction of a larger block structure with flexible block sizes from 64 × 64 to 8 × 8 samples. The enhanced feature has imposed higher complexity, specifically at the intra-prediction mode level of HEVC. The proposed research work has presented a novel hybrid approach to reducing the number of candidate Coding Units (CU) passing through irrelevant partition patterns and time-consuming iterative Rate-Distortion (RD) cost estimation process. The hybrid approach is implemented in two steps. In the first step gradient evaluation is performed and the CU is categorized as homogeneous or non-homogeneous. In the second step Early Termination is adopted by using machine learning for partitioning non-homogeneous CU. As the number of candidate Coding Units undergoing the time-consuming RD process is reduced by using the two-step hybrid approach, the proposed approach proves to be the best of its kind. The reduction in the number of candidate units undergoing the RD process reduces the complexity of the intra-prediction process. Encoding time is the measure of complexity and the proposed hybrid approach reduces the encoding time by an average of 36% compared with the HEVC reference model and also by an average of 26% as compared with the previous work. The Peak Signal to Noise Ratio (PSNR) reduced by an average of 0.1% indicates a slight reduction in the encoded image quality. The proposed approach significantly reduced the encoding time without affecting the RD performance of the encoder. The image quality is not compromised substantially when considering the improvement in the encoding time and the reduction in the complexity at an intra-prediction level.