Abstract. In this paper,we have done image processing as a project to identify an object. In order to find the unlabeled data with images, we proposed the project with the Faster-RCNN-v2-COCO model. This is processed by convolution neural network model with the region proposal network (RPN) method labeled data has been trained to learn the object of a particular image. This algorithm proposed for faster accuracy and better performance in detection by training N number of labeled data. Moreover, the error propagated during the training phase is reduced by including several pseudo annotations that are generated in the previous training phase. The result of the experiment reveals Currency detection, Signal detector, real time household objects are basic applications that are developing by object detection.