Scribd
Upload
3K views

Object Detection Presentation

The document discusses object detection using Python and machine learning. It introduces object detection and its applications. It describes the processes of image classification, object localization, and object detection. It also discusses methods for object detection including machine learning approaches like Viola-Jones and deep learning approaches like YOLO. The document then introduces Python and its features for machine learning. It defines machine learning and describes the main types: supervised, unsupervised, and reinforcement learning. Common machine learning algorithms are also listed. Finally, it describes the YOLO algorithm for real-time object detection and its applications.

Uploaded by

Akshat Jain
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3K views

Object Detection Presentation

The document discusses object detection using Python and machine learning. It introduces object detection and its applications. It describes the processes of image classification, object localization, and object detection. It also discusses methods for object detection including machine learning approaches like Viola-Jones and deep learning approaches like YOLO. The document then introduces Python and its features for machine learning. It defines machine learning and describes the main types: supervised, unsupervised, and reinforcement learning. Common machine learning algorithms are also listed. Finally, it describes the YOLO algorithm for real-time object detection and its applications.

Uploaded by

Akshat Jain
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 28

(USING PYTHON WITH MACHINE LEARNING)

TABLE OF CONTENTS
 Introduction to Object Detection
 Process of Object Detection
Image Classification
Object Localization
Object Detection
 Methods for Object Detection
 What is Python?
Features of Python
 Machine Learning
Definition
Types of Machine learning
 Supervised ML
 Unsupervised ML
 Semi-supervised ML
Algorithms used in ML
 YOLO Algorithm
 Uses of Object Detection
Object detection is a computer technology related
to computer vision and image processing that deals
with detecting instances of semantic objects of a
certain class (such as humans, buildings, or cars) in
digital images and videos. Well-researched domains of
object detection include face detection and pedestrian
detection. Object detection has applications in many
areas of computer vision, including image retrieval
and video survelliance.
Object Classification
Object Classification: Predict the type or class of an
object in an image.
 Input: An image with a single object, such as a
photograph.
 Output: A class label (e.g. one or more integers that are
mapped to class labels).
Object Localization
Object Localization: Locate the presence of objects in
an image and indicate their location with a bounding
box.
 Input: An image with one or more objects, such as a
photograph.
 Output: One or more bounding boxes (e.g. defined by a
point, width, and height).
Object Detection
Object Detection: Locate the presence of objects with
a bounding box and types or classes of the located
objects in an image.
 Input: An image with one or more objects, such as a
photograph.
 Output: One or more bounding boxes (e.g. defined by a
point, width, and height), and a class label for each
bounding box.
 Methods for object detection generally fall into either machine learning-
based approaches or deep learning-based approaches. For Machine
Learning approaches, it becomes necessary to first define features using
one of the methods below, then using a technique such as support vector
machine (SVM) to do the classification. On the other hand, deep
learning techniques that are able to do end-to-end object detection
without specifically defining features, and are typically based
on convolutional neural networks (CNN).
 Machine Learning approaches:
 Viola–Jones object detection framework based on Haar features
 Scale-invariant feature transform (SIFT)
 Histogram of oriented gradients (HOG) features
 Deep Learning approaches:
 Region Proposals (R-CNN, Fast R-CNN, Faster R-CNN)
 Single Shot MultiBox Detector (SSD)
 You Only Look Once (YOLO)
 Python is an interpreted, high-level, general-
purpose programming language created by Guido van
Rossum and released in 1991, Python's design
philosophy emphasizes code readability with its
notable use of significant whitespace.
 Python is dynamically typed and garbage-collected. It
supports multiple programming paradigms,
including procedural, object-oriented, and functional
programming.
Features of Python
 Easy to code and read
 Expressive
 Free and Open-Source
 Dynamically Typed
 Large Standard Library
 Embeddable
 Extensible
 Object-Oriented
 Interpreted
 Portable
Definition
 Machine Learning (ML) is basically that field of
computer science with the help of which computer
systems can provide sense to data in much the same
way as human beings do. In simple words, ML is a type
of artificial intelligence that extract patterns out of raw
data by using an algorithm or method. The key focus of
ML is to allow computer systems to learn from
experience without being explicitly programmed or
human intervention.
Types of ML
 Supervised Learning- This algorithm consist of a target / outcome variable (or
dependent variable) which is to be predicted from a given set of predictors
(independent variables). Using these set of variables, we generate a function that
map inputs to desired outputs. The training process continues until the model
achieves a desired level of accuracy on the training data. Examples of Supervised
Learning: Regression, Decision tree,Random forest,Logistic Regression etc.

 Unsupervised Learning- In this algorithm, we do not have any target or


outcome variable to predict / estimate. It is used for clustering population in
different groups, which is widely used for segmenting customers in different
groups for specific intervention. Examples of Unsupervised Learning: Apriori
algorithm, K-means.

 Reinforcement Learning- Using this algorithm, the machine is trained to make


specific decisions. It works this way: the machine is exposed to an environment
where it trains itself continually using trial and error. This machine learns from
past experience and tries to capture the best possible knowledge to make accurate
business decisions. Example of Reinforcement Learning: Markov Decision
Process.
Algorithms used in ML
 Linear Regression
 Logistic Regression
 Decision Tree
 SVM
 Naive Bayes
 kNN
 K-Means
 Random Forest
 YOLO is an extremely fast real time multi object detection algorithm.
YOLO stands for “You Only Look Once”.
 The algorithm applies a neural network to an entire image. The network
divides the image into an S x S grid and comes up with bounding boxes,
which are boxes drawn around images and predicted probabilities for
each of these regions.
 The method used to come up with these probabilities is logistic
regression. The bounding boxes are weighted by the associated
probabilities. For class prediction, independent logistic classifiers are
used.
 YOLO uses a totally different approach. YOLO is a clever convolutional
neural network (CNN) for doing object detection in real-time. The
algorithm applies a single neural network to the full image, and then
divides the image into regions and predicts bounding boxes and
probabilities for each region. These bounding boxes are weighted by the
predicted probabilities.
 YOLO is extremely fast
 YOLO sees the entire image during training and test time
so it implicitly encodes contextual information about
classes as well as their appearance.
 YOLO learns generalizable representations of objects so
that when trained on natural images and tested on
artwork, the algorithm outperforms other top detection
methods.
 Optical Character Recognition
 Self Driving Cars
 Tracking Objects
 Face Detection & Face Recognition
 Identity Verification through Iris Code
 Object extraction from an image or a video
 Smile Detection
 Activity Recognition
 Pedestrian Detection
 Digital Watermarking
 Medical Imaging
Ayushi Jain
Aditi Shrivastava
Nishi Kalar

You might also like