Communication efficiency of existing screen content transmission methods is constrained by the Shannon limit, which is not able to satisfy the communication demand for massive screen content data. Considering that text contents widely exist in screen content images, this paper unearths the text semantic information and proposes a novel screen content image transmission method based on semantic communication. First, an end-to-end communication framework is designed, which could extract text semantic information and compress irrelevant data. Then, a dynamic encoding strategy utilizing channel state information (CSI) feedback is proposed, which optimizes the encoding process by real-time acquisition of wireless channel characteristics to enhance transmission robustness and efficiency. Finally, experimental results demonstrate that compared with the state-of-the-art transmission methods, the proposed approach achieves higher communication efficiency under different channel conditions and bit rates.