SlideShare a Scribd company logo
1 of 3
Key details
• What is a barcode?
Barcodes are images consisting of a combination of
bars and spaces that represents numbers and letters in
a machine-readable manner. It is read by an optical
recognition device called a bar code scanner.
• What is image recognition?
Image recognition is a technology that allows
computers and machines to identify what is in an
image. In recent years, the accuracy has been further
improved by a method called deep learning. Deep
learning eliminates the need for humans to extract
features from data. It automatically extracts features
from a given image data from start to finish.
AI : Image Recognition
Hook
Do you know how Barcodes work? Bar codes, which began
to be utilized in the 1940s, are considered the oldest image
recognition technology. Many people can easily imagine it
because it appears on the packaging of various products.
Let's learn more about image recognition technology using
such barcodes as an example.
More details
https://www.denso-wave.com/
1. A bar code consists of black and white bars. A bar
code scanner shines light on these bars, captures the
reflected light, and converts the black and white into
a binary digital signal to retrieve data.
2. White areas are highly reflective and black areas are
less reflective. The sensor receives this reflected light
and obtains an analog waveform.
3. The analog signal is converted to a digital signal by an
A/D converter. (Binarization)
4. The code system is determined from the obtained
digital signal and the data is extracted. (decoding
process)
This is the basic barcode system. The basic system requires
a dedicated scanner, but with AI technology, even dark,
remote, or multiple barcodes can be read using a
smartphone camera.
Computer vision : Image recognition technology(IRT)
Hook
Have you ever heard of an A I that, upon input of text, generates an image
according to instructions? This is done through image recognition
technology. This technology has begun to spread in our daily lives, such as
face recognition in smartphones and self-driving ads in cars. How is AI
involved in image recognition technology, and what is actually so great
about it that it is becoming a hot topic? Let's deepen our understanding of
how image recognition technology works and its potential.
Key details
・About Computer Vision
Computer vision is an academic field that studies the realization of vision
using computers. It uses certain "image data" and performs some kind of
processing to achieve the same visual processing as human vision. It is a
technology that aims to extract three-dimensional information from two-
dimensional image data taken of the real world for humans to recognize
and process the information in them with their minds.
・About Image recognition technology
Image recognition technology is a technology that uses a computer to
identify objects in image or video data. For example, when a photograph of
a vegetable is loaded, the computer can instantly determine whether it is a
radish, a carrot, or a cabbage. Advances in A I, such as machine learning and
deep learning, have improved the accuracy of image recognition
technology, and it is now being used in a variety of fields.
More details
・Types of Image Recognition
①Object Detection
Technique for recognizing objects in images and videos. When a human viewer looks at an image or video, he
or she can immediately discern information about a person or object.
②Face Recognition
Refers to a technology that extracts prominent features from a facial image. It is a method that uses a
computer system to reproduce the means by which humans normally discriminate between people.
③Character Recognition
Identifying handwritten or printed characters on paper.
Example
『Image Generation AI』
A Sacred and
Wonderful Oil
Painting of a Really
Fat Cat Celebrating
the Coming of a
New Age
This picture is drawing by DALL・E2
Robots composed
of complex
structures
This picture is drawing by Midjourney
Deep learning: Face Recognitnion
Hook
Face Recognition Algorithm
Key details
More details
1. This is equal to the straight line distance or shortest distance or displacement between two points (..assume in two
dimensions but it can be in more dimensions).
3. After calculating the Euclidean distance, the algorithm either generates a new personID for the unknown type of person
(if the distance is greater than the key value) or marks the face as classified and matches the personID (if the distance is
less than the key value). In case of FACE01 GRAPHICS, the key value is usually 0.45 as the base value. Through deep
learning algorithm called ResNet, 128 dimensional feature vectors of various face images are trained to minimize the
distance between them for the same person. Therefore, the same person is determined by measuring the distance
between the vectors of each face image and calculating whether the distance is smaller than a key value.
(If you want to Algorithm which can detect mask-on face)
->The ‘CNN’ method is recommended for detecting a group of faces or faces with mask on In this case, a fast CPU and a fast
NVIDIA graphics card are required.
4. It was developed by Kaiming He at Microsoft Research, and is a 152-layer! The neural network was developed by Mr.
Kaiming He, who worked at Microsoft Research. This is the property that if the same number of neurons are to be
trained, the performance will be better if the depth of the hierarchy is deeper than if the width of each layer of the
network (the number of neurons) is wider. (This is a rule of thumb, and it is not well understood why this is the better
way to go theoretically.) But, If too many layers are added, problems such as vanishing or exploding of gradients occur,
and the system cannot learn well.
(The problem when he makes Resnet Algorithm)
-> When learning with Deep Learning, the activation function is differentiated for each layer to obtain the slope. In the
"shallow" layer, which is close to the input layer, the differential operation works well because the difference between the
input and output to that layer (accuracy) is large. However, as the learning progresses to the "deeper" layers, the accuracy of
the input-to-output conversion increases as the learning approaches convergence (as it should), and the difference between
the input and output becomes very small, making it difficult to obtain a gradient. Since propagation from layer to layer is
multiplicative in nature, the decreasing trend of the difference is exponential. In other words, as more layers are added, the
gradient quickly disappears.
*face01 graphics(Library for face detection and recognition in Python and command line. Also, It was trained on a dataset
of approximately 3 million images using deep learning.)
(Back end of software)
-> On the back end, the algorithm identifies a record with "classified = false" and uses a function to generate a 128-dimensional
vector detailing the attributes of this face. The algorithm cross-references this vector with all face entries in the database using
Euclidean distances to discover if this new face matches the face on the record.
This Photo by Unknown Author is
licensed under CC BY-SA
This Photo by Unknown Author
is licensed under CC BY
1. Euclidean distance -> This is equal to
the straight line distance or shortest
distance or displacement between two
points (..assume in two dimensions but
it can be in more dimensions).
2. Triplet training -> The training
consists of a set of three face images
and labeling each of the three images as
Positive if it’s similar to one of the
images and Negative if it’s dissimilar to
one of the images.
3. How to compare face (Algorithm) ->
Compare the learned images with the
detected facial features.
4. Resnet - > The algorithm of face
recognition
This Photo by Unknown Author
is licensed under CC BY-SA
Used like
this

More Related Content

Similar to Image_recognition.pptx

Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...
Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...
Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...IJERA Editor
 
Face Recognition - Deep Learning
Face Recognition - Deep LearningFace Recognition - Deep Learning
Face Recognition - Deep LearningAashish Chaubey
 
Sign Language Recognition using Machine Learning
Sign Language Recognition using Machine LearningSign Language Recognition using Machine Learning
Sign Language Recognition using Machine LearningIRJET Journal
 
IRJET - A Review on Face Recognition using Deep Learning Algorithm
IRJET -  	  A Review on Face Recognition using Deep Learning AlgorithmIRJET -  	  A Review on Face Recognition using Deep Learning Algorithm
IRJET - A Review on Face Recognition using Deep Learning AlgorithmIRJET Journal
 
Traffic Automation System
Traffic Automation SystemTraffic Automation System
Traffic Automation SystemPrabal Chauhan
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionKavika Roy
 
AI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this pptAI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this pptPavankalayankusetty
 
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptxDeep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptxpmgdscunsri
 
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...Abdullah al Mamun
 
Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Vidyut Singhania
 
Mirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMeetupDataScienceRoma
 
The Magic Behind AI
The Magic Behind AIThe Magic Behind AI
The Magic Behind AIOthman Gacem
 
IRJET- Smart Helmet for Visually Impaired
IRJET- Smart Helmet for Visually ImpairedIRJET- Smart Helmet for Visually Impaired
IRJET- Smart Helmet for Visually ImpairedIRJET Journal
 
Face Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image ProcessingFace Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image Processingpaperpublications3
 
Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...
Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...
Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...IJMER
 

Similar to Image_recognition.pptx (20)

Ch1.pptx
Ch1.pptxCh1.pptx
Ch1.pptx
 
Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...
Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...
Smart Bank Locker Access System Using Iris ,Fingerprints,Face Recognization A...
 
Waymo Essay
Waymo EssayWaymo Essay
Waymo Essay
 
Face Recognition - Deep Learning
Face Recognition - Deep LearningFace Recognition - Deep Learning
Face Recognition - Deep Learning
 
Sign Language Recognition using Machine Learning
Sign Language Recognition using Machine LearningSign Language Recognition using Machine Learning
Sign Language Recognition using Machine Learning
 
IRJET - A Review on Face Recognition using Deep Learning Algorithm
IRJET -  	  A Review on Face Recognition using Deep Learning AlgorithmIRJET -  	  A Review on Face Recognition using Deep Learning Algorithm
IRJET - A Review on Face Recognition using Deep Learning Algorithm
 
Traffic Automation System
Traffic Automation SystemTraffic Automation System
Traffic Automation System
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
 
AI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this pptAI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
 
Computer vision
Computer visionComputer vision
Computer vision
 
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptxDeep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
 
Computer vision
Computer visionComputer vision
Computer vision
 
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
 
Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Final Report on Optical Character Recognition
Final Report on Optical Character Recognition
 
Mirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image Processing
 
The Magic Behind AI
The Magic Behind AIThe Magic Behind AI
The Magic Behind AI
 
IRJET- Smart Helmet for Visually Impaired
IRJET- Smart Helmet for Visually ImpairedIRJET- Smart Helmet for Visually Impaired
IRJET- Smart Helmet for Visually Impaired
 
Face Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image ProcessingFace Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image Processing
 
Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...
Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...
Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wirel...
 
Image processing
Image processingImage processing
Image processing
 

More from john6938

Social Media Ethics.pptx
Social Media Ethics.pptxSocial Media Ethics.pptx
Social Media Ethics.pptxjohn6938
 
Future of Information Ethics.pptx
Future of Information Ethics.pptxFuture of Information Ethics.pptx
Future of Information Ethics.pptxjohn6938
 
Bioethics.pptx
Bioethics.pptxBioethics.pptx
Bioethics.pptxjohn6938
 
Surveillance and security.pptx
Surveillance and security.pptxSurveillance and security.pptx
Surveillance and security.pptxjohn6938
 
Introduction to Expert Systems.pptx
Introduction to Expert Systems.pptxIntroduction to Expert Systems.pptx
Introduction to Expert Systems.pptxjohn6938
 
Starbuck.pptx
Starbuck.pptxStarbuck.pptx
Starbuck.pptxjohn6938
 
Unit 4 Problem breakdown.pptx
Unit 4 Problem breakdown.pptxUnit 4 Problem breakdown.pptx
Unit 4 Problem breakdown.pptxjohn6938
 
Algorithms.pptx
Algorithms.pptxAlgorithms.pptx
Algorithms.pptxjohn6938
 
Artificial_intelligence.pptx
Artificial_intelligence.pptxArtificial_intelligence.pptx
Artificial_intelligence.pptxjohn6938
 
Image_generation.pptx
Image_generation.pptxImage_generation.pptx
Image_generation.pptxjohn6938
 
Computer_Graphics.pptx
Computer_Graphics.pptxComputer_Graphics.pptx
Computer_Graphics.pptxjohn6938
 
Security.pptx
Security.pptxSecurity.pptx
Security.pptxjohn6938
 
Gravitational_wave_detection.pptx
Gravitational_wave_detection.pptxGravitational_wave_detection.pptx
Gravitational_wave_detection.pptxjohn6938
 
Embedded_Systems.pptx
Embedded_Systems.pptxEmbedded_Systems.pptx
Embedded_Systems.pptxjohn6938
 
Software_engineering.pptx
Software_engineering.pptxSoftware_engineering.pptx
Software_engineering.pptxjohn6938
 
Quantum_computers.pptx
Quantum_computers.pptxQuantum_computers.pptx
Quantum_computers.pptxjohn6938
 
Sensors_SLAM.pptx
Sensors_SLAM.pptxSensors_SLAM.pptx
Sensors_SLAM.pptxjohn6938
 
Maths.pptx
Maths.pptxMaths.pptx
Maths.pptxjohn6938
 
Recommendation_systems.pptx
Recommendation_systems.pptxRecommendation_systems.pptx
Recommendation_systems.pptxjohn6938
 

More from john6938 (20)

Social Media Ethics.pptx
Social Media Ethics.pptxSocial Media Ethics.pptx
Social Media Ethics.pptx
 
Future of Information Ethics.pptx
Future of Information Ethics.pptxFuture of Information Ethics.pptx
Future of Information Ethics.pptx
 
Bioethics.pptx
Bioethics.pptxBioethics.pptx
Bioethics.pptx
 
Surveillance and security.pptx
Surveillance and security.pptxSurveillance and security.pptx
Surveillance and security.pptx
 
Introduction to Expert Systems.pptx
Introduction to Expert Systems.pptxIntroduction to Expert Systems.pptx
Introduction to Expert Systems.pptx
 
Starbuck.pptx
Starbuck.pptxStarbuck.pptx
Starbuck.pptx
 
Unit 4 Problem breakdown.pptx
Unit 4 Problem breakdown.pptxUnit 4 Problem breakdown.pptx
Unit 4 Problem breakdown.pptx
 
Algorithms.pptx
Algorithms.pptxAlgorithms.pptx
Algorithms.pptx
 
Artificial_intelligence.pptx
Artificial_intelligence.pptxArtificial_intelligence.pptx
Artificial_intelligence.pptx
 
Image_generation.pptx
Image_generation.pptxImage_generation.pptx
Image_generation.pptx
 
Computer_Graphics.pptx
Computer_Graphics.pptxComputer_Graphics.pptx
Computer_Graphics.pptx
 
Security.pptx
Security.pptxSecurity.pptx
Security.pptx
 
Gravitational_wave_detection.pptx
Gravitational_wave_detection.pptxGravitational_wave_detection.pptx
Gravitational_wave_detection.pptx
 
Embedded_Systems.pptx
Embedded_Systems.pptxEmbedded_Systems.pptx
Embedded_Systems.pptx
 
Software_engineering.pptx
Software_engineering.pptxSoftware_engineering.pptx
Software_engineering.pptx
 
Quantum_computers.pptx
Quantum_computers.pptxQuantum_computers.pptx
Quantum_computers.pptx
 
NLP.pptx
NLP.pptxNLP.pptx
NLP.pptx
 
Sensors_SLAM.pptx
Sensors_SLAM.pptxSensors_SLAM.pptx
Sensors_SLAM.pptx
 
Maths.pptx
Maths.pptxMaths.pptx
Maths.pptx
 
Recommendation_systems.pptx
Recommendation_systems.pptxRecommendation_systems.pptx
Recommendation_systems.pptx
 

Recently uploaded

POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17Celine George
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...M56BOOKSTORE PRODUCT/SERVICE
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdfssuser54595a
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxRoyAbrique
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docxPoojaSen20
 
Presiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsPresiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsanshu789521
 
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting DataJhengPantaleon
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

Recently uploaded (20)

POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docx
 
Presiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsPresiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha elections
 
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
 

Image_recognition.pptx

  • 1. Key details • What is a barcode? Barcodes are images consisting of a combination of bars and spaces that represents numbers and letters in a machine-readable manner. It is read by an optical recognition device called a bar code scanner. • What is image recognition? Image recognition is a technology that allows computers and machines to identify what is in an image. In recent years, the accuracy has been further improved by a method called deep learning. Deep learning eliminates the need for humans to extract features from data. It automatically extracts features from a given image data from start to finish. AI : Image Recognition Hook Do you know how Barcodes work? Bar codes, which began to be utilized in the 1940s, are considered the oldest image recognition technology. Many people can easily imagine it because it appears on the packaging of various products. Let's learn more about image recognition technology using such barcodes as an example. More details https://www.denso-wave.com/ 1. A bar code consists of black and white bars. A bar code scanner shines light on these bars, captures the reflected light, and converts the black and white into a binary digital signal to retrieve data. 2. White areas are highly reflective and black areas are less reflective. The sensor receives this reflected light and obtains an analog waveform. 3. The analog signal is converted to a digital signal by an A/D converter. (Binarization) 4. The code system is determined from the obtained digital signal and the data is extracted. (decoding process) This is the basic barcode system. The basic system requires a dedicated scanner, but with AI technology, even dark, remote, or multiple barcodes can be read using a smartphone camera.
  • 2. Computer vision : Image recognition technology(IRT) Hook Have you ever heard of an A I that, upon input of text, generates an image according to instructions? This is done through image recognition technology. This technology has begun to spread in our daily lives, such as face recognition in smartphones and self-driving ads in cars. How is AI involved in image recognition technology, and what is actually so great about it that it is becoming a hot topic? Let's deepen our understanding of how image recognition technology works and its potential. Key details ・About Computer Vision Computer vision is an academic field that studies the realization of vision using computers. It uses certain "image data" and performs some kind of processing to achieve the same visual processing as human vision. It is a technology that aims to extract three-dimensional information from two- dimensional image data taken of the real world for humans to recognize and process the information in them with their minds. ・About Image recognition technology Image recognition technology is a technology that uses a computer to identify objects in image or video data. For example, when a photograph of a vegetable is loaded, the computer can instantly determine whether it is a radish, a carrot, or a cabbage. Advances in A I, such as machine learning and deep learning, have improved the accuracy of image recognition technology, and it is now being used in a variety of fields. More details ・Types of Image Recognition ①Object Detection Technique for recognizing objects in images and videos. When a human viewer looks at an image or video, he or she can immediately discern information about a person or object. ②Face Recognition Refers to a technology that extracts prominent features from a facial image. It is a method that uses a computer system to reproduce the means by which humans normally discriminate between people. ③Character Recognition Identifying handwritten or printed characters on paper. Example 『Image Generation AI』 A Sacred and Wonderful Oil Painting of a Really Fat Cat Celebrating the Coming of a New Age This picture is drawing by DALL・E2 Robots composed of complex structures This picture is drawing by Midjourney
  • 3. Deep learning: Face Recognitnion Hook Face Recognition Algorithm Key details More details 1. This is equal to the straight line distance or shortest distance or displacement between two points (..assume in two dimensions but it can be in more dimensions). 3. After calculating the Euclidean distance, the algorithm either generates a new personID for the unknown type of person (if the distance is greater than the key value) or marks the face as classified and matches the personID (if the distance is less than the key value). In case of FACE01 GRAPHICS, the key value is usually 0.45 as the base value. Through deep learning algorithm called ResNet, 128 dimensional feature vectors of various face images are trained to minimize the distance between them for the same person. Therefore, the same person is determined by measuring the distance between the vectors of each face image and calculating whether the distance is smaller than a key value. (If you want to Algorithm which can detect mask-on face) ->The ‘CNN’ method is recommended for detecting a group of faces or faces with mask on In this case, a fast CPU and a fast NVIDIA graphics card are required. 4. It was developed by Kaiming He at Microsoft Research, and is a 152-layer! The neural network was developed by Mr. Kaiming He, who worked at Microsoft Research. This is the property that if the same number of neurons are to be trained, the performance will be better if the depth of the hierarchy is deeper than if the width of each layer of the network (the number of neurons) is wider. (This is a rule of thumb, and it is not well understood why this is the better way to go theoretically.) But, If too many layers are added, problems such as vanishing or exploding of gradients occur, and the system cannot learn well. (The problem when he makes Resnet Algorithm) -> When learning with Deep Learning, the activation function is differentiated for each layer to obtain the slope. In the "shallow" layer, which is close to the input layer, the differential operation works well because the difference between the input and output to that layer (accuracy) is large. However, as the learning progresses to the "deeper" layers, the accuracy of the input-to-output conversion increases as the learning approaches convergence (as it should), and the difference between the input and output becomes very small, making it difficult to obtain a gradient. Since propagation from layer to layer is multiplicative in nature, the decreasing trend of the difference is exponential. In other words, as more layers are added, the gradient quickly disappears. *face01 graphics(Library for face detection and recognition in Python and command line. Also, It was trained on a dataset of approximately 3 million images using deep learning.) (Back end of software) -> On the back end, the algorithm identifies a record with "classified = false" and uses a function to generate a 128-dimensional vector detailing the attributes of this face. The algorithm cross-references this vector with all face entries in the database using Euclidean distances to discover if this new face matches the face on the record. This Photo by Unknown Author is licensed under CC BY-SA This Photo by Unknown Author is licensed under CC BY 1. Euclidean distance -> This is equal to the straight line distance or shortest distance or displacement between two points (..assume in two dimensions but it can be in more dimensions). 2. Triplet training -> The training consists of a set of three face images and labeling each of the three images as Positive if it’s similar to one of the images and Negative if it’s dissimilar to one of the images. 3. How to compare face (Algorithm) -> Compare the learned images with the detected facial features. 4. Resnet - > The algorithm of face recognition This Photo by Unknown Author is licensed under CC BY-SA Used like this

Editor's Notes

  1. https://aize.jp/%E7%94%BB%E5%83%8F%E8%AA%8D%E8%AD%98%E3%81%A3%E3%81%A6%E4%BD%95%E3%81%A0%E3%82%8D%E3%81%86%EF%BC%9F/  https://aismiley.co.jp/ai_news/what-is-image-recognition/ https://www.denso-wave.com/ja/adcd/fundamental/barcode/scan/index.html#:~:text=1.%E3%83%90%E3%83%BC%E3%82%B3%E3%83%BC%E3%83%89%E3%81%AF%E3%80%81%E7%99%BD,%E3%82%A2%E3%83%8A%E3%83%AD%E3%82%B0%E6%B3%A2%E5%BD%A2%E3%82%92%E5%BE%97%E3%81%BE%E3%81%99%E3%80%82 https://prtimes.jp/main/html/rd/p/000000002.000053429.html
  2. My topic is Image recognition.   Have you ever heard of an AI that, upon input of text, generates an image according to instructions? This is done through image recognition technology. This technology has begun to spread in our daily lives, such as face recognition in smartphones and self-driving ads in cars. How is AI involved in image recognition technology, and what is actually so great about it that it is becoming a hot topic? Let's deepen our understanding of how image recognition technology works and its potential.   First, I would like to introduce about computer vision and image recognition technology. Let’s talk about computer vision first. Computer vision is an academic field that studies the realization of vision using computers. It uses certain "image data" and performs some kind of processing to achieve the same visual processing as human vision. It is a technology that aims to extract three-dimensional information from two-dimensional image data taken of the real world for humans to recognize and process the information in them with their minds. Second, I would like to introduce about Image recognition technology。mage recognition technology is a technology that uses a computer to identify objects in image or video data. For example, when a photograph of a vegetable is loaded, the computer can instantly determine whether it is a radish, a carrot, or a cabbage. Advances in A I, such as machine learning and deep learning, have improved the accuracy of image recognition technology, and it is now being used in a variety of fields.   Next, I’m going to talk more details about Image recognition. There are 3 types focus on image recognition.  First is object recognition. Object recognition is Technique for recognizing objects in images and videos. When a human viewer looks at an image or video, he or she can immediately discern information about a person or object. Second is face recognition. Face recognition refers to a technology that extracts prominent features from a facial image. It is a method that uses a computer system to reproduce the means by which humans normally discriminate between people. And finally, is character recognition. Character recognition is Identifying handwritten or printed characters on paper. Here is the picture created by the AI according to the text. I think all kinds of possibilities for this kind of technology.   Thank you for listening. Do you guys have any questions? Is there anyone have questions?         What can you expect from incorporating image recognition technology?   When a computer performs image discrimination, it can remove noise and distortion from the image and adjust brightness and color, making it possible, for example, to recognize the details of a criminal more clearly when using security camera footage. This is expected to facilitate problem solving.   What do you think are the possible disadvantages of the spread of image recognition technology?   I believe that the increased value of pictures created by AI will affect the designer industry. I can expect to see a decrease in the number of people in the designer industry as the earnings of some designers decrease.