Comfort is the key aspect in purchasing footwear while precision design on shoe sole and even to shoe last was the fundamental factor in influencing the comfort for the foot. Artificial intelligent technologies were applied in this field, especially on data mining and image mining, a variety of mathematical tools applied for identifying points in an image based on calculating features. Feature of an image is important for retraveling useful information from image dataset. In this paper, we used fast region-based convolutional neural network (Fast RCNN) for plantar pressure image dataset. The region of interest (ROI) extraction was deployed in the proposed model which showed the effectiveness of the proposed methods in the research. The region information extraction will be potential application for conform shoe last customization in industry