A deep neural network based cephalometric landmark identification model is proposed. Two neural networks, named patch classification and point estimation, are trained by multi-scale image patches cropped from 935 Cephalograms (of Japanese young patients), whose size and orientation vary based on landmark-dependent criteria examined by orthodontists. The proposed model identifies both 22 hard and 11 soft tissue landmarks. In order to evaluate the proposed model, (i) landmark estimation accuracy by Euclidean distance error between true and estimated values, and (ii) success rate that the estimated landmark was located within the corresponding norm using confidence ellipse, are computed. The proposed model successfully identified hard tissue landmarks within the error range of 1.32 - 3.5 mm and with a mean success rate of 96.4%, and soft tissue landmarks with the error range of 1.16 - 4.37 mm and with a mean success rate of 75.2%. We verify that considering the landmark-dependent size and orientation of patches helps improve the estimation accuracy.