Recently, the disease identification and classification based on the medical images has greatly attracted a lot of scientists all over the world. The human brain tumors can be diagnosed by using the computer-based solutions. The complications associated with brain tumors can be minimized if it is identified and treated promptly. Besides, the intelligent algorithms such as deep learning, neural networks, and artificial intelligence have been developing strongly and applied in the medical field. This work proposes a solution for classifying the human brain tumors using the deep learning model with the pre-trained VGG-16 architecture to classify a tumor or a non-tumor from MRI images. Our proposed method achieves the accuracy of 97% in classifying human brain tumors. The proposed approach demonstrated that the most prevalent brain tumors can be identified and promised for applying in the medical field. It can assist doctors in making prompt and precise decisions.