In this paper, analysis of directional wave spectra in shallow water area estimated by video images data has been compared with numerical model of SWAN. Estimation of directional wave spectra from video images is based on the Bayesian Directional Method using a group of pixels brightness on the image. For this study, the pixels can be considered equivalent to fixed instruments as wave probe sensor after rectification process. The results show that there is a good agreement between directional wave spectra estimated by video images data and the SWAN model. Both methods estimate similar shape of directional wave spectra in the shallow water. In addition, the energy distribution of directional wave spectra in shallow water is concentrated significantly in frequency and direction.