INTERNSHIP PRESENTATION ON,
“CLASSIFY DIFFERENT TYPES OF OBJECTS”
PRESENTED BY
SRUSHTI S HULYALAD(4GM21AI052)
Project Guide: Project Co-Ordinator: Head of Department:
Miss. Snehal V Mrs. Shilpa R N Dr. Asha K
B.E, M.Tech B.E, M.Tech B.E, M.Tech, Ph.D
ABSTRACT
Object classification is the process of assigning predefined labels or
categories to objects based on their characteristics, features, and
properties. It is a fundamental task in machine learning and computer
vision, enabling machines to understand and interpret visual data. Object
classification has benefited significantly from advancements in deep
learning. Convolutional Neural Networks (CNNs) have proven highly
effective in learning complex patterns from vast amounts of image data,
achieving impressive accuracy in object recognition tasks.
CONTENT
1. Company Details
2. Introduction
3. Objectives
4. Literature Survey
5. Methodology
6. Experimental Result
7. Applications
8. Advantages
9. Future Scope
10. Conclusion
COMPANY DETAILS
• Karunadu Technologies Private Limited is an unlisted private company
incorporated on 19 July, 2018. It is classified as a private limited company and
is located in Bangalore, Karnataka.
• The last reported AGM (Annual General Meeting) of Karunadu Technologies
Private Limited, per our records, was held on 30 September, 2022.
• Karunadu Technologies Private Limited has two directors - Mahesh Deginal
and Bhavaramma S Hatti.
• In Karunadu Technologies Private Limited, I completed my Internship
program for 4 weeks, on the domain Artificial intelligence and Machine
Learning.
INTRODUCTION
 Object classification, which is a computer-based technique of artificial
intelligence that enables the identification of objects.
 Object detection is primarily based on machine learning, and it requires an
enormous amount of data for training and testing to achieve high accuracy in
recognizing objects.
 This technique involves using advanced algorithms and machine learning models
that can process large amounts of data to accurately recognize and classify
objects based on their visual features.
 Object classification has a wide range of applications in various industries such
as manufacturing, retail, and security.
OBJECTIVES
Object classification is a critical task in computer vision with several key
objectives that drive its development and application. Here are the
primary objectives:
 Accurate Identification
 Real-Time Processing
 Scalability
LITERATURE SURVEY
Paper Title Author Name Year Description
A Survey on Deep
Learning
Techniques for
Image and Video
Classification
Lei Meng,
Mingjie Wang
2020 Provides an overview of
deep learning methods,
including CNNs and
their applications in
image and video
classification tasks.
Recent Advances
in Object Detection
and Classification:
A Review
Shengjin Wang,
Zhen Liu
2021 Focuses on both
traditional and deep
learning approaches for
object detection and
classification.
METHODOLOGY
Yes
Data Collection
(Images)
Image
Preprocessing
(Resize,
Normalize)
Object Training
and Testing
Extract Features
Performance
Satisfactory?
Predict the image
Refine Model
Back to
No
PREDICTION
CHOOSING A IMAGE FROM THE
FILE
Experimental Result
APPLICATIONS
Classifying different types of objects has many applications such as:
Image and Video Recognition Medical Imaging
Autonomous Vehicles
ADVANTAGES
Object classification offers numerous benefits across various fields and
applications. Here are some of the key advantages:
 Improved accuracy
 Automatic feature learning
 Increases the efficiency
FUTURE SCOPE:
Future scope on object classification will focus on refining and
optimizing existing applications, exploring new techniques.
Advancements in computer vision will lead to increased adoption across
industries, including healthcare, autonomous vehicles, and smart
surveillance.
CONCLUSION
We can easily detect and identify the various objects present in an image.
Object detection provides a faster and accurate means to predict the
object in an image. It is useful in various applications such as image
retrieval system.
THANK YOU

object classification mini project .pptx

  • 1.
    INTERNSHIP PRESENTATION ON, “CLASSIFYDIFFERENT TYPES OF OBJECTS” PRESENTED BY SRUSHTI S HULYALAD(4GM21AI052) Project Guide: Project Co-Ordinator: Head of Department: Miss. Snehal V Mrs. Shilpa R N Dr. Asha K B.E, M.Tech B.E, M.Tech B.E, M.Tech, Ph.D
  • 2.
    ABSTRACT Object classification isthe process of assigning predefined labels or categories to objects based on their characteristics, features, and properties. It is a fundamental task in machine learning and computer vision, enabling machines to understand and interpret visual data. Object classification has benefited significantly from advancements in deep learning. Convolutional Neural Networks (CNNs) have proven highly effective in learning complex patterns from vast amounts of image data, achieving impressive accuracy in object recognition tasks.
  • 3.
    CONTENT 1. Company Details 2.Introduction 3. Objectives 4. Literature Survey 5. Methodology 6. Experimental Result 7. Applications 8. Advantages 9. Future Scope 10. Conclusion
  • 4.
    COMPANY DETAILS • KarunaduTechnologies Private Limited is an unlisted private company incorporated on 19 July, 2018. It is classified as a private limited company and is located in Bangalore, Karnataka. • The last reported AGM (Annual General Meeting) of Karunadu Technologies Private Limited, per our records, was held on 30 September, 2022. • Karunadu Technologies Private Limited has two directors - Mahesh Deginal and Bhavaramma S Hatti. • In Karunadu Technologies Private Limited, I completed my Internship program for 4 weeks, on the domain Artificial intelligence and Machine Learning.
  • 5.
    INTRODUCTION  Object classification,which is a computer-based technique of artificial intelligence that enables the identification of objects.  Object detection is primarily based on machine learning, and it requires an enormous amount of data for training and testing to achieve high accuracy in recognizing objects.  This technique involves using advanced algorithms and machine learning models that can process large amounts of data to accurately recognize and classify objects based on their visual features.  Object classification has a wide range of applications in various industries such as manufacturing, retail, and security.
  • 6.
    OBJECTIVES Object classification isa critical task in computer vision with several key objectives that drive its development and application. Here are the primary objectives:  Accurate Identification  Real-Time Processing  Scalability
  • 7.
    LITERATURE SURVEY Paper TitleAuthor Name Year Description A Survey on Deep Learning Techniques for Image and Video Classification Lei Meng, Mingjie Wang 2020 Provides an overview of deep learning methods, including CNNs and their applications in image and video classification tasks. Recent Advances in Object Detection and Classification: A Review Shengjin Wang, Zhen Liu 2021 Focuses on both traditional and deep learning approaches for object detection and classification.
  • 8.
    METHODOLOGY Yes Data Collection (Images) Image Preprocessing (Resize, Normalize) Object Training andTesting Extract Features Performance Satisfactory? Predict the image Refine Model Back to No
  • 9.
  • 10.
    CHOOSING A IMAGEFROM THE FILE
  • 11.
  • 12.
    APPLICATIONS Classifying different typesof objects has many applications such as: Image and Video Recognition Medical Imaging Autonomous Vehicles
  • 13.
    ADVANTAGES Object classification offersnumerous benefits across various fields and applications. Here are some of the key advantages:  Improved accuracy  Automatic feature learning  Increases the efficiency
  • 14.
    FUTURE SCOPE: Future scopeon object classification will focus on refining and optimizing existing applications, exploring new techniques. Advancements in computer vision will lead to increased adoption across industries, including healthcare, autonomous vehicles, and smart surveillance.
  • 15.
    CONCLUSION We can easilydetect and identify the various objects present in an image. Object detection provides a faster and accurate means to predict the object in an image. It is useful in various applications such as image retrieval system.
  • 16.