1. Pattern Recognition
prepared by eng:Mohmed Ahmed Mustafa
abdelati.
Luxor university.
Faculty of computers and information
,computer science department.
2. Foreword
using big data and machine learning technologies emergence, a lot of data
became available that was previously either deduced or speculated but by using
a pattern recognition we moved to analyzing and understanding this data.
Big data depends on pattern recognition as main tools ,it gets the core of data
concerned in it hidden meaning.
3. Objectives
The focus of this chapter on two fundamental questions:
• What is Pattern Identification and it’s techniques.
• What is the Use Cases for Pattern Recognition and it’s apps.
4. What is Pattern Identification?
is the process of distinguishing and segmenting data according to set criteria or
by common elements, which is performed by special algorithms.
Imagine that the data is a group of number:
0
5
10
15
20
؟
0
5
10
15
20
25
6. Pattern Recognition Techniques
There are three main models of pattern recognition:
It’s a
cake.
Statistical
The word is
‘through’
Syntactic Template
Matching
tem
Check w
7. Pattern recognition process
Pattern recognition algorithm
explorative descriptive
recognize commonalities in the data categorize the commonalities in a certain manner
8. Use Cases for Pattern Recognition
Data Analytics.
Natural Language Processing.
Optical Character Recognition.
Image Recognition.
voice Recognition.
Sentiment Analysis.
9. Data Analytics
pattern recognition is used to describe data, show its distinct features and
put it into a broader context as Stock market forecasting using yard charts
and Audience research as Google analytics.
12. Image Recognition
OCR aimed at understanding what is on the picture but image recognition aimed
at describing the picture to be searchable and comparable with the other
images.
They are two main use case for image recognition :
Visual Search Face Detection
13. voice Recognition
Like Personal Assistant apps, Speech-to-text and text-to-speech
transformation and Automatic Captions
14. Sentiment Analysis
is a subset of pattern recognition that takes an extra step to define its nature and
what it can mean.
Audience Research, Customer Service, Prescription, Recommendation -
Sentiment Analysis.
15. conclusion
Pattern recognition is the key to the further evolution of computational
technology. With its help, big data analytics can progress further and we can all
benefit from the machine learning algorithms getting smarter and smarter.
As you can see, pattern recognition can be implemented in any kind of industry
because where there is data, there are similarities in the data. Therefore, it's wise
to consider the possibility of implementing this technology into your business
operations to make them more efficient.
16. Summary
An active example for pattern recognition :
Teaching :the prof should teach scientific content he should Explains the meanings
hidden behind the words not just Indoctrination.
Replacing:
prof------>programmer.
students-------->machines.
scientific content --------->data.
we can got the meaning of pattern recognition.
17. Summary…..
Most of Thoughts that uses in technology that have effect in our society are
based on pattern recognition.
A message for all: learning pattern recognition work manly to help all in their
graduation projects .
18. Summary….
Part I like it in this presentation is sentiment analysis and transform sentiment to a
data that can be process ,it’s imaginary.
Editor's Notes
Any information on the sequential nature can be processed by pattern recognition algorithms, making the sequences comprehensible and enabling its practical use.
data can be :
1-text.
2-image.
3-Voice.
4-Sentiments, and others.
Statistical : uses supervised machine learning.
Syntactic : uses semi-supervised machine learning.
Template Matching : One of the uses of such a model is plagiarism checking.
Data is gathered from its sources (via tracking or input)
Data is cleaned up from the noise
Information is examined for relevant features or common elements
These elements are subsequently grouped in specific segments;
The segments are analyzed for insights into data sets;
The extracted insights are implemented into the business operation.
used in such fields as:Text analysis, Plagiarism detection, Text summarization and contextual extraction and others
The most common source of the optical characters are scanned documents or photographs, but the thing can also be used on computer-generated unlabeled images*
As Text Transcription and Document Classification.
A famous example for visual search is Google lens.
Facebook and instagram used face detection.
Note:voice recognition works on the same principles as OCR. The only difference is the source of information.