To discuss the relationship between complexity measures extracted from gray image time series and flow pattern transition in gas-liquid two-phase flow，three complexity measures，including Lempel-Ziv complexity，fractal box dimension，and Shannon information entropy were extracted from sixty flow pattern image signals of gas-liquid two-phase flow in the horizontal pipe by using digital high speed video systems.Based on the above studies，the chaos dynamic characteristics of three complexity measures in different gas superficial velocities，and the recognition capability of gas-liquid two-phase flow pattern were analyzed.The results indicated that these three complexity measures were sensitive to the flow pattern transition in gas-liquid two-phase flow.By analyzing the changes of three complexity measures with gas-liquid two-phase flow parameters，the dynamics structure inversion characteristics of gas-liquid two-phase flow could be got，which provided an efficient，supplementary diagnostic tool to reveal the flow pattern transition mechanism of gas-liquid two-phase flow and quantitatively identify flow pattern.