Packing Automation in a High Variety Conveyor line via
Image Classification
PROJECT REPORT
submitted by
B.ARJUN
ASI16CS018
DILEEP CHANDRAN
ASI16CS023
VIDHU HARI
ASI16CS059
Under the guidance of
PROF. Ajay Basil Varghese
To
APJ Abdul Kalam Technological
University
in partial fulfillment of the requirements for the award of the
Degree of
Bachelor of Technology In Computer Science and Engineering
Department of Computer Science and Engineering
(NBA Accredited Program 2018-2021)
ADI SHANKARA INSTITUTE OF ENGINEERING AND
TECHNOLOGY KALADY
JULY,2020
Packing Automation in a High Variety Conveyor line
via
Image Classification
PROJECT REPORT
submitted by
B.ARJUN
ASI16CS018
DILEEP CHANDRAN
ASI16CS023
VIDHU HARI
ASI16CS059
Under the guidance of
PROF. Ajay Basil Varghese
To
APJ Abdul Kalam Technological University
in partial fulfillment of the requirements for the award of the
Degree of
Bachelor of Technology In Computer Science and Engineering
Department of Computer Science and Engineering
(NBA Accredited Program 2018-2021)
ADI SHANKARA INSTITUTE OF ENGINEERING AND TECHNOLOGY
KALADY
JULY,2020
DECLARATION
We undersigned hereby declare that the project report “Packing Automation in a High
Variety Conveyor line via Image Classification”, submitted for partial fulfillment of the
requirements for the award of degree of Bachelor of Technology of APJ Abdul Kalam
Technological University, Kerala is a bonafide work done by us under supervision of Prof.
Ajay Basil Varghese. This submission represents our ideas in our own words and where
ideas or words of others have been included, we have adequately and accurately cited and
referenced the original sources. We also declare that we have adhered to ethics of academic
honesty and integrity and have not misrepresented or fabricated any data or idea or fact or
source in my submission. We understand that any violation of the above will be a cause for
disciplinary action by the institute and/or the University and can also evoke penal action from
the sources which have thus not been properly cited or from whom proper permission has not
been obtained. This report has not previously formed the basis for the award of any degree,
diploma or similar title of any other University.
KALADY SIGNATURE
DATE:
B. ARJUN
DILEEP CHANDRAN
VIDHU HARI
CONTENTS
ACKNOWLEDGMENT i
VISION AND MISSION OF THE DEPARTMENT ii
ABSTRACT iii
LIST OF FIGURES v
ABBREVIATIONS vi
Chapter 1. INTRODUCTION 1
1.1 Problem Statement 3
1.2 Proposed System 4
Chapter 2. LITERATURE SURVEY 5
2.1 Description of Existing Systems 5
Chapter 3.BACKGROUND THEORY 7
3.1 TensorFlow 7
3.2 Convolutional Neural Networks 8
3.3 SSD MobileNet 11
3.4 Nvidia CUDA 13
Chapter 4. Flowcharts and Diagrams 15
4.1 Use Case Diagram 15
4.2 Data Flow Diagram 15
Chapter 5. IMPLEMENTATION 16
5.1 Image Dataset 16
5.2 Model Training 19
5.3 Object Classification 22
5.4 Advantages 24
5.5 Future Scope 25
Chapter 6. CONCLUSION 26
REFERENCES 28
ACKNOWLEDGMENT
At the very outset we would like to give the first honors to God, who gave the wisdom and
knowledge to complete this project.
Our extreme thanks to Dr. Suresh Kumar V, Principal for providing the necessary facilities
for the completion of this project in our college.
We sincerely extend our thanks to Prof. Rajaram, HOD CSE & IT for all the help,
motivation and guidance throughout the completion of this project.
We wish to extend our sincere thanks to all project coordinators Dr. Manish T I, Associate
Professor and Prof. Neetha K Nataraj, Prof. Gripsy Paul and also our project guide Prof.
Ajay Basil Varghese, for their valuable guidance and support throughout the project.
We also wish to thank all teaching and non-teaching faculty of Computer Science and
Engineering department for their cooperation.
We also thank our Parents, friends and all well-wishers who supported us directly or
indirectly during the course of this project.
VISION AND MISSION OF THE DEPARTMENT
VISION
Nurturing globally competent Computer Science and Engineering graduates capable of taking
challenges in the industry and Research & Development activities.
MISSION
● Imparting quality education to meet the needs of industry, and to achieve excellence
in teaching and learning.
● Inculcating value-based, socially committed professionalism for development of society.
● Providing support to promote quality research.
ABSTRACT
Due to the rise in computational power available, there has been a steady increase of interest
in fields such as image recognition and machine learning. Consequently,one of the best areas
for its application is in the field of factory automation since it requires processing of large
amounts of image data within strict time constraints. Implementing such systems has become
much more easier due to the rise of machine learning frameworks such as Tensorflow. Hence
implementing a Machine learning based inference model to do routine tasks such as object
identification and verification can greatly increase the overall efficiency and offer great
monetary returns by minimizing human labor. An SSD Mobilenet based model was used for
this purpose for its speed and accuracy
LIST OF FIGURES
No. Title Page No.
1.1 Basic image identification system 1
3.1.1 A computational graph 8
3.1.2 A simple computational graph 8
3.2.1 A convolution operation 10
3.2.2 CNN architecture 11
3.3.1 Mobilenet Architecture 12
3.4.1 CUDA architecture 14
4.1.1 Use Case Diagram 15
4.2.1 Data Flow Diagram 15
5.1.1 Image Dataset 16
5.1.2 Train and Test Labels 17
5.1.3 Cropping Boundary 17
5.1.4 Code Snippet 18
5.2.1 Training Process 19
5.2.2 Training Process 20
5.2.3 Loss 21
5.3.1 SSD Grid 22
5.3.2 Classified Images 23
5.3.3 Images and Barcodes 23
5.3.4 Operation Pipeline 24
ABBREVIATIONS
SSD Single Shot Detector
CNN Convolutional Neural Net
CSV Comma Separated Values
CUDA Compute Unified Device
Architecture
PW Pointwise layer
DW Depthwise layer
