We developed a new video coding model that combines block-based finite ridgelet transform with H.264/AVC. This model is based on H.264/AVC codec and a new video coding mode called the ridgelet mode is added to it in order to incorporate the directional transform feature. In the ridgelet mode, residuals of each block after intra or inter predictions are transformed into a prime-number-sized block by a scaling filter to fit the finite Radon transform. Then the finite Radon transform and the 1D DCT are applied to the block. The ridgelet mode can adapt to such texture regions that have strong correlation along a specific direction and it can enhance the coding efficiency of the H.264/AVC by its directional feature of the finite Radon transform. We implemented the ridgelet mode onto a H.264/AVC based video encoder. The experimental results show the potential of this method for higher compression efficiency.