This thesis proposes a new method of combining the technique of Two Differences of Adjacent Pixels with the technique of Reversible Hiding Data Methods. In order to enhance a higher embedding capacity and keep a certain quality of PSNR, Two Data Hiding Methods is pointed out, which includes the Difference of Adjacent Pixels Algorithm and the Prediction of Adjacent in the same image. The first method, Difference of Adjacent Pixels Algorithm, is used to measure the Pixel Difference Value to produce Hiding Data. The utilization of the second method is used Prediction and dividing Stego Image to several block zones to adjust pixel values to achieve the goal Hiding Data. According to the outcome of experiments, the new method, combining Two Differences of Adjacent Pixels and Reversible Hiding Data Methods, has a better capacity of embedding, which can recover the original image without any distortion after the hidden data have been extracted. Moreover, the whole presented algorithm is quite simple and the execution time is also rather short.