As one of the primary computer vision problems, object detection aims to find and locate semantic objects in digital images. Different with object classification, which only recognizes an object to a certain class, object detection also needs to extract accurate locations of objects. In the state-of-the-art object detection algorithms, bounding box regression plays a critical role in order to achieve high localization accuracy. Almost all the popular deep learning based object detection algorithms have utilized bounding box regression for fine tuning of object locations. However, while bounding box regression is widely used, there is few study focused on the underlying rationale, performance dependencies, and performance evaluation. In this paper, we proposed a dedicated deep neural network for bounding box regression, and presented several methods to improve its performance. Some ad hoc experiments are conducted to prove the effectiveness of the network. Also, we apply the network as an auxiliary module to the faster R-CNN algorithm and test them on some real-world images. Experiment results show certain performance improvements on detection accuracy in term of mean IOU.