Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
85 views

Image Classification - Digital Image Processing

Image classification uses spectral information from digital images to categorize image content. It involves preprocessing images, extracting features, selecting training data, performing classification, and assessing accuracy. There are two main approaches: supervised classification where the user specifies training samples to guide classification, and unsupervised classification where computer algorithms automatically group pixels based on spectral properties. Key assumptions in classification methods include whether algorithms are parametric and assume known data distributions, or non-parametric with no assumptions. Classifiers can also provide hard classification with single class membership per pixel, or soft classification with partial membership across multiple classes.

Uploaded by

Sharmishtha Sarkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
85 views

Image Classification - Digital Image Processing

Image classification uses spectral information from digital images to categorize image content. It involves preprocessing images, extracting features, selecting training data, performing classification, and assessing accuracy. There are two main approaches: supervised classification where the user specifies training samples to guide classification, and unsupervised classification where computer algorithms automatically group pixels based on spectral properties. Key assumptions in classification methods include whether algorithms are parametric and assume known data distributions, or non-parametric with no assumptions. Classifiers can also provide hard classification with single class membership per pixel, or soft classification with partial membership across multiple classes.

Uploaded by

Sharmishtha Sarkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

IMAGE

CLASSIFICATIO
N
SHARMISTHA SARKAR
ENTC-2
ROLL NO. 84
Image classification
Digital image classification uses the quantitative spectral information contained in an image, which is
related to the composition or condition of the target surface. Classification system of consists of database
that contains predefined patterns that compares with detected object to classify into proper category.
The objective of image classification is to identify and portray, as a unique gray level (or color), the
features occurring in an image in terms of the object or type of land cover these features actually represent
on the ground. Image classification is perhaps the most important part of digital image analysis.
Classification of image consists of following stages

DIGITAL DATA

PREPROCESSING

FEATURE EXTRACTION

SELECTION OF TRAINING DATA

DECISION AND CLASSIFICATION

CLASSIFICATION OUTPUT

ACCURACY ASSESMENT
IMAGE CLASSIFICATION STEPS
1. DIGITAL DATA :- Digital data is an image which is captured by the use of a digital camera or any
mobile phone.

2. PREPROCESSING:- Improvement of the image data.


3. Feature extraction:- The process of measuring or calculating or detecting the features from the image
samples.
The most two common types of feature extraction are:-
i. Geometric feature extraction
ii. Color feature extraction
4. Selection of training data:- Selection of a particular attribute which best describes the pattern.
5. Decision and classification:- Categorizes the detected object into predefined classes by using suitable
methods that compares the image pattern with the target patterns .

6. Classification output:-
7. Accuracy assessment:- An accuracy assessment is realized to identify the
possible sources of errors and as an indicator used in comparisions.
IMAGE CLASSIFICATION
APPROACHES
TYPES OF LEARNING
1. SUPERVISED CLASSIFICATION:- In supervised classification the user or
image analyst “supervises” the pixel classification process. The user specifies the various
pixels values or spectral signatures that should be associated with each class. This is done by
selecting representative sample sites of a known cover type called training sites or areas. The
computer algorithm then uses the spectral signatures from these training areas to classify the
whole image. Ideally, the classes should not overlap or should only minimally overlap with
other classes.
The process of using samples of known informational classes (training sets) to classify pixels
of unknown identity.
ADVANTAGES:- Supervised classification can be much more accurate than
unsupervised classification, but depends heavily on the training sites, the skill of the
individual processing the image, and the spectral distinctness of the classes.

DISADVANTAGES:- If the training data is poor or not representative the


classification results will also be poor. Therefore supervised classification generally
requires more times and money compared to unsupervised.
2. UNSUPERVISED CLASSIFICATION:- Unsupervised classification is a form of pixel
based classification and is essentially computer automated classification. The user specifies the
number of classes and the spectral classes are created solely based on the numerical information in
the data (i.E. The pixel values for each of the bands or indices). Clustering algorithms are used to
determine the natural, statistical grouping of the data. The pixels are grouped together into based on
their spectral similarity. The computer uses feature space to analyze and group the data into classes.
Roll over the below image to see how the computer might use feature space to group the data into ten
classes.
Advantages
Unsupervised classification is fairly quick and easy to run. There is no
extensive prior knowledge of area required, but you must be able to identify
and label classes after the classification. The classes are created purely based
on spectral information, therefore they are not as subjective as manual visual
interpretation.

Disadvantages
One of the disadvantages is that the spectral classes do not always correspond
to informational classes. The user also has to spend time interpreting and label
the classes following the classification. Spectral properties of classes can also
change over time, so you can’t always use the same class information when
moving from one image to another.
ASSUMTIONS ON DATA
DISTRIBUTIONS
1. PARAMETRIC CLASSIFIER:- The performance of parametric classifier
depends largely on how well the data match the pre-defined models and on the accuracy of the
estimation of the model parameters. The parameters like mean vector and covariance matrix are
used.

2. NON-PARAMETRIC CLASSIFIER:- There is no assumptions about the data.


Non-parametric classifier do not make use of statistical parameters to calculate class seperation.
NUMBER OF OUTPUTS FOR EACH
SPATIAL UNIT
1. HARD CLASSIFICATION:- Each pixel is required to show membership to a single class.

2. SOFT CLASSIFICATION:- Each pixel may exhibit numerous and partial class membership
THANK YOU

You might also like