Object detection is one of the main requirements during motherboard assembly process, especially when using SMT technology. Human fatigue is the major cause of error making while manual inspection. The grasp success rate will enhance if robot can get exact position of objects than relative to the end manipulator. With the advent of deep learning techniques the accuracy for object detection has increased drastically. A major challenge in many of the object detection systems is the dependency of other computer vision techniques for helping the deep learning based approach, which will lead to the slow and non-optimal performance. In this project a completely deep learning based approach to solve the problem of object detection in an end-to-end fashion. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. The model developed with a pre-trained model ResNet 101 and data collected from Computer Vision Lab. Mask R-CNN is easy to generalize to other tasks and also it shows better results with COCO dataset for instance segmentation, bounding box object detection and person key point detection.