Speech based Object Identification using Region Proposal Faster RCNN Algorithm
Samiksha Choyal1, Ajay Kumar Singh2
1Samiksha Choyal, Department of Computer Science and Engineering, Mody University of Science and Technology, Lakshmangarh (Rajasthan), India.
2Ajay Kumar Singh, Department of Computer Science and Engineering, Mody University of Science and Technology, Lakshmangarh (Rajasthan), India.
Manuscript received on 28 March 2019 | Revised Manuscript received on 09 April 2019 | Manuscript Published on 18 April 2019 | PP: 943-946 | Volume-7 Issue-6S March 2019 | Retrieval Number: F03910376S19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper describes the applications of object detection and demonstrates the methodology along with the results of one of the object recognition models that is Faster Regions with Convolutional Neural Network (Faster R-CNN). This experiment of object detection has been conducted on a new proposed dataset of everyday objects. The implementation has been done with the help of tensorflow object detection models. The results obtained after testing and training the images with this model are depicted in the form of a graph. Further, the final output of the recognized object is shown to the user in the form of a speech.
Keywords: Convolutional Neural Network, Deep Learning, Faster RCNN, Object Recognizition.
Scope of the Article: Speech interface; Speech processing