Transfer learning-based Object Detection by using Convolutional Neural Networks

Project Code :TCMAPY207

Objective

In this paper we propose a transfer learning-based deep learning method, Convolutional Neural Network (CNN) for the object detection. For the improvement in the result, the majority voting scheme is used. The results obtained here have shown incredible improvement in the accuracy of the proposed work when compared to the other different CNN models.

Abstract

Object detection has become an important task for various purposes in our daily lives. Machine learning techniques have been used for this task from earlier but they are used for the classification of imagebased species to extract the feature set. This task of deciding the feature set helps to decide the desired object detection.

To overcome the object classification problem, this application proposes a transfer learning-based deep learning method. The different convolutional neural networks (CNN) are studied in this work. Here for the improvement in the result, the majority voting scheme is used. The overall work is carried out on the CUB 200-2011 dataset. The results obtained have shown incredible improvement in the accuracy of the proposed work when compared to the different CNN models. Here the Japanese comics (manga) are used for the evaluation.

Keywords: Machine Learning (ML), CNN, Object Detection, Transfer Learning, Majority Voting.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram

Specifications

H/W Configuration:

·         Processor                    :    I3/Intel Processor

·         Hard Disk                   :   160GB

·         RAM                            :    8Gb

S/W Configuration:

·         Operating System       :   Windows 7/8/10            .          

·         Server side Script       :   HTML, CSS & JS.

·         IDE                                :   Pycharm.

·         Libraries Used            :    Numpy, IO, OS, Flask, keras.

·         Technology                 :    Python 3.6+.

Learning Outcomes

  •         Practical exposure to
      •          Hardware and software tools
      •          Solution providing for real time problems
      •          Working with team/individual
      •          Work on creative ideas

  •          Testing techniques
  •          Error correction mechanisms
  •          What type of technology versions is used?
  •          Working of Tensor Flow
  •          Implementation of Deep Learning techniques
  •          Working of CNN algorithm
  •          Working of GoogleNet algorithm
  •          Working on ResNet50
  •          Working on VGG16 and VGG19
  •          Working on AlexNet
  •          Working of Transfer Learning
  •          Building of model creations
  •          Scope of project
  •          Applications of the project
  •          About Python language
  •          About Deep Learning Frameworks
  •          Use of Data Science

Demo Video

mail-banner
call-banner
contact-banner
Request Video

Related Projects

Final year projects