SlideShare a Scribd company logo
1 of 8
Download to read offline
IMAGE PROCESSING AND OBJECT DETECTION APPLICATION:
INSURANCE CASE - ABOUT CLAIMS AND UNDERWRITING
Dr. Volkan OBAN1
1Asst. Prof., Istinye University, İstanbul TÜRKİYE
Abstract
In this study, some image processing and object detection techniques are handled for claims
processing and underwriting. Image detection and recognition provides different perspectives in
the insurance industry, especially in the demand process, as well as in traditional practices.
Insurers endeavor and concentrate on determining whether the claims are valid or not. The use
of image detection techniques allows realistic assessment of images of damaged objects loaded
and their claims by policyholders.
Keywords: Artificial Intelligence, Computer Vision, Image Processing, Object Detection, Deep
Learning, Insurance, Tensorflow, Keras, Imageai,Yolo
1. Introduction:
The insurance data contains various types of
information in the form of continuous or
discrete numbers, short texts, huge
paragraphs, and, of course, images.
Multitudes of claims, customer inquiries and
masses of data make the insurance industry
an ideal address for artificial intelligence and
cognitive technologies.
Artificial intelligence is already deeply
embedded in insurance processes. A 2017
study reports that the insurance industry has
invested $124 million in AI, compared to an
average of $70 million invested by other
industries.
According to McKinsey’s Insurance 2030
Report, with the new wave of deep learning
techniques, such as convolutional neural
networks, AI can truly mimic the perception,
reasoning, learning, and problem solving of
the human mind. AI will help the insurance
sector shift from its current state of “detect
and repair” to “predict and prevent.” While AI
has made great strides within the insurance
industry, one promising element of a robust
AI strategy must be further explored:
computer vision technologies.
Implementing computer vision technology
that enables visual insurance claims has
emerged as a solution that can transform the
entire claims process. Computer vision
guides customers through the process of
capturing visuals while recognizing objects
within those images, classifying the images,
and routing the enquiries to the to the right
agents or adjusters for immediate analysis
and incident assessment
By embedding AI within claims processes,
insurers can easily access and extract the
relevant data and reduce processing times.
AI can also identify patterns in masses of
data and help detect fraudulent claims
during the process. Using machine learning
capabilities, AI can automatically calculate
past damages and predict the costs from
historical data, aiding in the determination of
premiums. McKinsey predicts that as
insurers and their ecosystem become more
adept at using AI technologies to enhance
decision making and operations, lower costs,
and optimize the customer experience, the
pace of adoption will further accelerate.
While AI has made great strides within the
insurance industry, one promising element
of a robust AI strategy must be further
explored: computer vision technologies.
Computer vision is a field that works on
enabling computers to see, identify, and
process images/videos like a human being. It
is like imparting human intelligence and
instincts to a computer. It may sound
promising; however, in reality, it is quite
difficult to enable computers to recognize
images of different objects. It is not a new
field, but it has caught more attention and
become more precise only after the advent of
deep learning in the last decade.
[InsurAnalytics] Computer vision is based
strongly on artificial intelligence, as the
computer must gain high-level
understanding from digital images.
Some application of computer vision in the
insurance industry.
 IMAGE SIMILARITY
 FACIAL RECOGNITION
 OBJECT DETECTION AND
RECOGNITION
 MOTION ESTIMATION
 DAMAGE DETECTION
……, etc.
Positive Acquisitions of Image
Processing Technologies to Insurance
Sector:
 The use of facial and image
recognition technologies, as well
as images stamped with geo-
location and time, enables
insurance companies to reduce
their risk of fraud.
 Computer vision’s ability to
validate claims in real-time
enables expedited claim
settlements
 Computer vision improves KPIs
across the board, which
translates into significant cost
reductions in contact centre from
improved FCR and AHT, reduced
adjuster time in the field, and less
customer churn.
 With a faster AHT and increased
FCR, insurance companies can
validate and process claims
faster than ever without the need
for staff augmentation.
 The visual upload process is fast,
interactive, and eliminates the
need to wait for a field adjustor
or live agent to approve the
claim. When claims are
processed faster, customers are
happier. [TechSee] and
[Andrew Mort]
Fraudulent claims
It has been commonly observed that many
people tend to file fraudulent claims. For
instance, people filing health insurance
claims multiple times and across multiple
insurance companies. Similar is the scenario
for motor insurance – frauds are increasing
at an alarming rate. As per a report by
economic times, “a combination of poor due
diligence in writing policies by insurance
companies and the organizational
efficiencies of criminals in identifying those
who are on deathbed and in enlisting doctors
to produce fake certificates led to frauds
which are estimated
to have cost over Rs 10,000 crore annually to
the industry.” These frauds directly affect the
profitability of the industry. In order to make
up for the fraudulent claims, companies tend
to raise premiums, meaning innocent
customers must pay higher amounts of
premiums.
THREE WAYS COMPUTER VISION IS
CHANGING P&C INSURANCE [Capco]
Computer vision, a field of artificial
intelligence (AI), has developed rapidly over
the last ten years, with the end goal of a
computer learning to see as a human would.
The application of computer vision has the
potential to transform the property and
casualty insurance (P&C) industry, by
helping individuals and insurance
companies throughout virtually all the stages
of the underwriting and claims life cycles.
Read on as we examine three scenarios that
highlight how computer vision can enhance
safety, accuracy and efficiency throughout
the insurance process.
2. IMAGE SIMILARITY
Image Similarity compares two
images and returns a value that tells
you how visually similar they are.
Here is used hashing algorithms by
Python. (hashlib module- import
hashlib).
The lower the the score, the more
contextually similar the two images
are with a score of ‘0’ being identical.
3. FACIAL RECOGNITION
Recognize and manipulate faces from
Python. Built using dlib’s state-of-the-art face
recognition. Built with deep learning. The
model has an accuracy of 99.38% on the
Labeled Faces in the Wild benchmark.
Face Detection:
Face detection is a computer vision
technology that helps to locate/visualize
human faces in digital images. Face detection
has gained a lot of importance especially in
fields like photography, security, and
marketing.
4.OBJECT DETECTION AND
RECOGNITION
Object detection is the craft of
detecting instances of a certain class,
like animals, humans and many more
in an image or video Object Detection
(Tensorflow models in Python)
makes it easy to detect objects by
using pretrained object detection
models
number of person(insan sayısı) : 13
number of car(arac sayısı) : 8
number of truck(kamyon sayısı) : 2
number of bus(otobüs sayısı) : 1
number of backpack(sırt çantası sayısı) : 1
Is there any ambulance at the scene of the accident?
ambulance : 82.00276494026184
police van: 15.833474695682526
minibus: 1.516808196902275
Garbage truck: 0.15010888455435634
fire engine : 0.11310353875160217
moving van: 0.08072283817455173
trolleybus : 0.07773929974064231
snowplow : 0.04561058012768626
tow truck : 0.037757077370770276
crane : 0.024561924510635436
number of person(insan sayısı) : 20
number of car(arac sayısı) : 12
number of truck(kamyon sayısı) : 1
number of bus(otobüs sayısı) : 0
number of traffic lights(trafik lambasısayısı) : 2
Are there any traffic sign and lights?
number of person(insan sayısı) : 1
number of car(arac sayısı) : 4
number of truck(kamyon sayısı) 2
number of traffic lights(trafik lambası sayısı) 3
number of pedestrian(yaya sayısı) : 6
number of person(insan sayısı) : 12
number of car(arac sayısı) : 4
number of truck(kamyon sayısı) 1
number of traffic lights(trafik lambası sayısı) 0
Car Speed Detection
5.Conclusion:
Claims processing is a key touch point in the
customer life cycle, and insurers have only a
short opportunity to wow or disappoint their
policyholders. With much at stake, insurers
must adopt innovative tools and
technologies in order to transform the claims
function. Implementing computer vision
technology that enables visual insurance
claims has emerged as a solution that can
transform the entire claims process.
Computer vision guides customers through
the process of capturing visuals while
recognizing objects within the images,
classifying the images. Artificial intelligence
(computer vision, image processing …)
techniques have been studied for the current
situation in the industry.

More Related Content

Similar to Conference Paper:IMAGE PROCESSING AND OBJECT DETECTION APPLICATION: INSURANCE CASE - ABOUT CLAIMS AND UNDERWRITING

How Computer Vision is reshaping the finance and insurance industry
How Computer Vision is reshaping the finance and insurance industryHow Computer Vision is reshaping the finance and insurance industry
How Computer Vision is reshaping the finance and insurance industryAddepto
 
How hci is driving digital transformation in the insurance firms to enable pr...
How hci is driving digital transformation in the insurance firms to enable pr...How hci is driving digital transformation in the insurance firms to enable pr...
How hci is driving digital transformation in the insurance firms to enable pr...Tyrone Systems
 
Accenture video-analytics-operational-marketing-and-security-insights-from-cctv
Accenture video-analytics-operational-marketing-and-security-insights-from-cctvAccenture video-analytics-operational-marketing-and-security-insights-from-cctv
Accenture video-analytics-operational-marketing-and-security-insights-from-cctvSunanda Balla
 
The Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSI
The Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSIThe Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSI
The Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSIPT Datacomm Diangraha
 
Utilizing artificial intelligence potential in financial services & insurance
Utilizing artificial intelligence potential in financial services & insuranceUtilizing artificial intelligence potential in financial services & insurance
Utilizing artificial intelligence potential in financial services & insuranceCANOPY ONE SOLUTIONS
 
Insurtech Cyber Boxer
Insurtech Cyber BoxerInsurtech Cyber Boxer
Insurtech Cyber BoxerAmit Rai
 
The Journey Towards AI: The Impact on European Insurers
The Journey Towards AI: The Impact on European InsurersThe Journey Towards AI: The Impact on European Insurers
The Journey Towards AI: The Impact on European InsurersPeerasak C.
 
Aws mining intelligent_insights_with_machine_learning_financial_services_e_book
Aws mining intelligent_insights_with_machine_learning_financial_services_e_bookAws mining intelligent_insights_with_machine_learning_financial_services_e_book
Aws mining intelligent_insights_with_machine_learning_financial_services_e_bookamir527123
 
Get Ready For What's New In Insurance Technology Trends For 2021
Get Ready For What's New In Insurance Technology Trends For 2021Get Ready For What's New In Insurance Technology Trends For 2021
Get Ready For What's New In Insurance Technology Trends For 2021Mindbowser Inc
 
Research on object detection and recognition using machine learning algorithm...
Research on object detection and recognition using machine learning algorithm...Research on object detection and recognition using machine learning algorithm...
Research on object detection and recognition using machine learning algorithm...YousefElbayomi
 
Artificial intelligence in insurance 3 trends - venkat k - medium
Artificial intelligence in insurance  3 trends - venkat k - mediumArtificial intelligence in insurance  3 trends - venkat k - medium
Artificial intelligence in insurance 3 trends - venkat k - mediumusmsystem
 
Insurtech what’s in it for the customer
Insurtech what’s in it for the customerInsurtech what’s in it for the customer
Insurtech what’s in it for the customerMatteo Carbone
 
Blockchain's impact on insurance industry
Blockchain's impact on insurance industryBlockchain's impact on insurance industry
Blockchain's impact on insurance industryEudore Pirmez
 
Blockchain's Impact on Insurance
Blockchain's Impact on InsuranceBlockchain's Impact on Insurance
Blockchain's Impact on InsuranceMelody Ucros
 
Insurance Technology Trends 2021
Insurance Technology Trends 2021Insurance Technology Trends 2021
Insurance Technology Trends 2021insureedge
 

Similar to Conference Paper:IMAGE PROCESSING AND OBJECT DETECTION APPLICATION: INSURANCE CASE - ABOUT CLAIMS AND UNDERWRITING (20)

How Computer Vision is reshaping the finance and insurance industry
How Computer Vision is reshaping the finance and insurance industryHow Computer Vision is reshaping the finance and insurance industry
How Computer Vision is reshaping the finance and insurance industry
 
Claims Registration Automation by SwiftAnt
Claims Registration Automation by SwiftAntClaims Registration Automation by SwiftAnt
Claims Registration Automation by SwiftAnt
 
How hci is driving digital transformation in the insurance firms to enable pr...
How hci is driving digital transformation in the insurance firms to enable pr...How hci is driving digital transformation in the insurance firms to enable pr...
How hci is driving digital transformation in the insurance firms to enable pr...
 
Accenture video-analytics-operational-marketing-and-security-insights-from-cctv
Accenture video-analytics-operational-marketing-and-security-insights-from-cctvAccenture video-analytics-operational-marketing-and-security-insights-from-cctv
Accenture video-analytics-operational-marketing-and-security-insights-from-cctv
 
The Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSI
The Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSIThe Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSI
The Long Awaited Cloud Solution - How Cloud Computing Benefits Insurance & FSI
 
Machine Leaning Insurance
Machine Leaning InsuranceMachine Leaning Insurance
Machine Leaning Insurance
 
Machine Learning In Insurance
Machine Learning In InsuranceMachine Learning In Insurance
Machine Learning In Insurance
 
Utilizing artificial intelligence potential in financial services & insurance
Utilizing artificial intelligence potential in financial services & insuranceUtilizing artificial intelligence potential in financial services & insurance
Utilizing artificial intelligence potential in financial services & insurance
 
Insurtech Cyber Boxer
Insurtech Cyber BoxerInsurtech Cyber Boxer
Insurtech Cyber Boxer
 
CII: Addressing Gender Bias in Artificial Intelligence
CII: Addressing Gender Bias in Artificial IntelligenceCII: Addressing Gender Bias in Artificial Intelligence
CII: Addressing Gender Bias in Artificial Intelligence
 
The Journey Towards AI: The Impact on European Insurers
The Journey Towards AI: The Impact on European InsurersThe Journey Towards AI: The Impact on European Insurers
The Journey Towards AI: The Impact on European Insurers
 
Aws mining intelligent_insights_with_machine_learning_financial_services_e_book
Aws mining intelligent_insights_with_machine_learning_financial_services_e_bookAws mining intelligent_insights_with_machine_learning_financial_services_e_book
Aws mining intelligent_insights_with_machine_learning_financial_services_e_book
 
Get Ready For What's New In Insurance Technology Trends For 2021
Get Ready For What's New In Insurance Technology Trends For 2021Get Ready For What's New In Insurance Technology Trends For 2021
Get Ready For What's New In Insurance Technology Trends For 2021
 
Research on object detection and recognition using machine learning algorithm...
Research on object detection and recognition using machine learning algorithm...Research on object detection and recognition using machine learning algorithm...
Research on object detection and recognition using machine learning algorithm...
 
Artificial intelligence in insurance 3 trends - venkat k - medium
Artificial intelligence in insurance  3 trends - venkat k - mediumArtificial intelligence in insurance  3 trends - venkat k - medium
Artificial intelligence in insurance 3 trends - venkat k - medium
 
Insurtech what’s in it for the customer
Insurtech what’s in it for the customerInsurtech what’s in it for the customer
Insurtech what’s in it for the customer
 
AI Redefines Insurance
AI Redefines InsuranceAI Redefines Insurance
AI Redefines Insurance
 
Blockchain's impact on insurance industry
Blockchain's impact on insurance industryBlockchain's impact on insurance industry
Blockchain's impact on insurance industry
 
Blockchain's Impact on Insurance
Blockchain's Impact on InsuranceBlockchain's Impact on Insurance
Blockchain's Impact on Insurance
 
Insurance Technology Trends 2021
Insurance Technology Trends 2021Insurance Technology Trends 2021
Insurance Technology Trends 2021
 

More from Dr. Volkan OBAN

Covid19py Python Package - Example
Covid19py  Python Package - ExampleCovid19py  Python Package - Example
Covid19py Python Package - ExampleDr. Volkan OBAN
 
Object detection with Python
Object detection with Python Object detection with Python
Object detection with Python Dr. Volkan OBAN
 
Python - Rastgele Orman(Random Forest) Parametreleri
Python - Rastgele Orman(Random Forest) ParametreleriPython - Rastgele Orman(Random Forest) Parametreleri
Python - Rastgele Orman(Random Forest) ParametreleriDr. Volkan OBAN
 
Linear Programming wi̇th R - Examples
Linear Programming wi̇th R - ExamplesLinear Programming wi̇th R - Examples
Linear Programming wi̇th R - ExamplesDr. Volkan OBAN
 
"optrees" package in R and examples.(optrees:finds optimal trees in weighted ...
"optrees" package in R and examples.(optrees:finds optimal trees in weighted ..."optrees" package in R and examples.(optrees:finds optimal trees in weighted ...
"optrees" package in R and examples.(optrees:finds optimal trees in weighted ...Dr. Volkan OBAN
 
k-means Clustering in Python
k-means Clustering in Pythonk-means Clustering in Python
k-means Clustering in PythonDr. Volkan OBAN
 
Naive Bayes Example using R
Naive Bayes Example using  R Naive Bayes Example using  R
Naive Bayes Example using R Dr. Volkan OBAN
 
k-means Clustering and Custergram with R
k-means Clustering and Custergram with Rk-means Clustering and Custergram with R
k-means Clustering and Custergram with RDr. Volkan OBAN
 
Data Science and its Relationship to Big Data and Data-Driven Decision Making
Data Science and its Relationship to Big Data and Data-Driven Decision MakingData Science and its Relationship to Big Data and Data-Driven Decision Making
Data Science and its Relationship to Big Data and Data-Driven Decision MakingDr. Volkan OBAN
 
Data Visualization with R.ggplot2 and its extensions examples.
Data Visualization with R.ggplot2 and its extensions examples.Data Visualization with R.ggplot2 and its extensions examples.
Data Visualization with R.ggplot2 and its extensions examples.Dr. Volkan OBAN
 
Scikit-learn Cheatsheet-Python
Scikit-learn Cheatsheet-PythonScikit-learn Cheatsheet-Python
Scikit-learn Cheatsheet-PythonDr. Volkan OBAN
 
Python Pandas for Data Science cheatsheet
Python Pandas for Data Science cheatsheet Python Pandas for Data Science cheatsheet
Python Pandas for Data Science cheatsheet Dr. Volkan OBAN
 
Pandas,scipy,numpy cheatsheet
Pandas,scipy,numpy cheatsheetPandas,scipy,numpy cheatsheet
Pandas,scipy,numpy cheatsheetDr. Volkan OBAN
 
ReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an exampleReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an exampleDr. Volkan OBAN
 
ReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an exampleReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an exampleDr. Volkan OBAN
 
R-ggplot2 package Examples
R-ggplot2 package ExamplesR-ggplot2 package Examples
R-ggplot2 package ExamplesDr. Volkan OBAN
 
R Machine Learning packages( generally used)
R Machine Learning packages( generally used)R Machine Learning packages( generally used)
R Machine Learning packages( generally used)Dr. Volkan OBAN
 
treemap package in R and examples.
treemap package in R and examples.treemap package in R and examples.
treemap package in R and examples.Dr. Volkan OBAN
 

More from Dr. Volkan OBAN (20)

Covid19py Python Package - Example
Covid19py  Python Package - ExampleCovid19py  Python Package - Example
Covid19py Python Package - Example
 
Object detection with Python
Object detection with Python Object detection with Python
Object detection with Python
 
Python - Rastgele Orman(Random Forest) Parametreleri
Python - Rastgele Orman(Random Forest) ParametreleriPython - Rastgele Orman(Random Forest) Parametreleri
Python - Rastgele Orman(Random Forest) Parametreleri
 
Linear Programming wi̇th R - Examples
Linear Programming wi̇th R - ExamplesLinear Programming wi̇th R - Examples
Linear Programming wi̇th R - Examples
 
"optrees" package in R and examples.(optrees:finds optimal trees in weighted ...
"optrees" package in R and examples.(optrees:finds optimal trees in weighted ..."optrees" package in R and examples.(optrees:finds optimal trees in weighted ...
"optrees" package in R and examples.(optrees:finds optimal trees in weighted ...
 
k-means Clustering in Python
k-means Clustering in Pythonk-means Clustering in Python
k-means Clustering in Python
 
Naive Bayes Example using R
Naive Bayes Example using  R Naive Bayes Example using  R
Naive Bayes Example using R
 
R forecasting Example
R forecasting ExampleR forecasting Example
R forecasting Example
 
k-means Clustering and Custergram with R
k-means Clustering and Custergram with Rk-means Clustering and Custergram with R
k-means Clustering and Custergram with R
 
Data Science and its Relationship to Big Data and Data-Driven Decision Making
Data Science and its Relationship to Big Data and Data-Driven Decision MakingData Science and its Relationship to Big Data and Data-Driven Decision Making
Data Science and its Relationship to Big Data and Data-Driven Decision Making
 
Data Visualization with R.ggplot2 and its extensions examples.
Data Visualization with R.ggplot2 and its extensions examples.Data Visualization with R.ggplot2 and its extensions examples.
Data Visualization with R.ggplot2 and its extensions examples.
 
Scikit-learn Cheatsheet-Python
Scikit-learn Cheatsheet-PythonScikit-learn Cheatsheet-Python
Scikit-learn Cheatsheet-Python
 
Python Pandas for Data Science cheatsheet
Python Pandas for Data Science cheatsheet Python Pandas for Data Science cheatsheet
Python Pandas for Data Science cheatsheet
 
Pandas,scipy,numpy cheatsheet
Pandas,scipy,numpy cheatsheetPandas,scipy,numpy cheatsheet
Pandas,scipy,numpy cheatsheet
 
ReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an exampleReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an example
 
ReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an exampleReporteRs package in R. forming powerpoint documents-an example
ReporteRs package in R. forming powerpoint documents-an example
 
R-ggplot2 package Examples
R-ggplot2 package ExamplesR-ggplot2 package Examples
R-ggplot2 package Examples
 
R Machine Learning packages( generally used)
R Machine Learning packages( generally used)R Machine Learning packages( generally used)
R Machine Learning packages( generally used)
 
treemap package in R and examples.
treemap package in R and examples.treemap package in R and examples.
treemap package in R and examples.
 
Mosaic plot in R.
Mosaic plot in R.Mosaic plot in R.
Mosaic plot in R.
 

Recently uploaded

Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)jennyeacort
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degreeyuu sss
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Colleen Farrelly
 
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAmazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAbdelrhman abooda
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档208367051
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 

Recently uploaded (20)

Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024
 
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAmazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 

Conference Paper:IMAGE PROCESSING AND OBJECT DETECTION APPLICATION: INSURANCE CASE - ABOUT CLAIMS AND UNDERWRITING

  • 1. IMAGE PROCESSING AND OBJECT DETECTION APPLICATION: INSURANCE CASE - ABOUT CLAIMS AND UNDERWRITING Dr. Volkan OBAN1 1Asst. Prof., Istinye University, İstanbul TÜRKİYE Abstract In this study, some image processing and object detection techniques are handled for claims processing and underwriting. Image detection and recognition provides different perspectives in the insurance industry, especially in the demand process, as well as in traditional practices. Insurers endeavor and concentrate on determining whether the claims are valid or not. The use of image detection techniques allows realistic assessment of images of damaged objects loaded and their claims by policyholders. Keywords: Artificial Intelligence, Computer Vision, Image Processing, Object Detection, Deep Learning, Insurance, Tensorflow, Keras, Imageai,Yolo 1. Introduction: The insurance data contains various types of information in the form of continuous or discrete numbers, short texts, huge paragraphs, and, of course, images. Multitudes of claims, customer inquiries and masses of data make the insurance industry an ideal address for artificial intelligence and cognitive technologies. Artificial intelligence is already deeply embedded in insurance processes. A 2017 study reports that the insurance industry has invested $124 million in AI, compared to an average of $70 million invested by other industries. According to McKinsey’s Insurance 2030 Report, with the new wave of deep learning techniques, such as convolutional neural networks, AI can truly mimic the perception, reasoning, learning, and problem solving of the human mind. AI will help the insurance sector shift from its current state of “detect and repair” to “predict and prevent.” While AI has made great strides within the insurance industry, one promising element of a robust AI strategy must be further explored: computer vision technologies. Implementing computer vision technology that enables visual insurance claims has emerged as a solution that can transform the entire claims process. Computer vision guides customers through the process of capturing visuals while recognizing objects within those images, classifying the images, and routing the enquiries to the to the right agents or adjusters for immediate analysis and incident assessment By embedding AI within claims processes, insurers can easily access and extract the relevant data and reduce processing times. AI can also identify patterns in masses of data and help detect fraudulent claims during the process. Using machine learning
  • 2. capabilities, AI can automatically calculate past damages and predict the costs from historical data, aiding in the determination of premiums. McKinsey predicts that as insurers and their ecosystem become more adept at using AI technologies to enhance decision making and operations, lower costs, and optimize the customer experience, the pace of adoption will further accelerate. While AI has made great strides within the insurance industry, one promising element of a robust AI strategy must be further explored: computer vision technologies. Computer vision is a field that works on enabling computers to see, identify, and process images/videos like a human being. It is like imparting human intelligence and instincts to a computer. It may sound promising; however, in reality, it is quite difficult to enable computers to recognize images of different objects. It is not a new field, but it has caught more attention and become more precise only after the advent of deep learning in the last decade. [InsurAnalytics] Computer vision is based strongly on artificial intelligence, as the computer must gain high-level understanding from digital images. Some application of computer vision in the insurance industry.  IMAGE SIMILARITY  FACIAL RECOGNITION  OBJECT DETECTION AND RECOGNITION  MOTION ESTIMATION  DAMAGE DETECTION ……, etc. Positive Acquisitions of Image Processing Technologies to Insurance Sector:  The use of facial and image recognition technologies, as well as images stamped with geo- location and time, enables insurance companies to reduce their risk of fraud.  Computer vision’s ability to validate claims in real-time enables expedited claim settlements  Computer vision improves KPIs across the board, which translates into significant cost reductions in contact centre from improved FCR and AHT, reduced adjuster time in the field, and less customer churn.  With a faster AHT and increased FCR, insurance companies can validate and process claims faster than ever without the need for staff augmentation.  The visual upload process is fast, interactive, and eliminates the need to wait for a field adjustor or live agent to approve the claim. When claims are processed faster, customers are happier. [TechSee] and [Andrew Mort] Fraudulent claims It has been commonly observed that many people tend to file fraudulent claims. For instance, people filing health insurance claims multiple times and across multiple insurance companies. Similar is the scenario for motor insurance – frauds are increasing at an alarming rate. As per a report by economic times, “a combination of poor due diligence in writing policies by insurance companies and the organizational efficiencies of criminals in identifying those who are on deathbed and in enlisting doctors to produce fake certificates led to frauds which are estimated
  • 3. to have cost over Rs 10,000 crore annually to the industry.” These frauds directly affect the profitability of the industry. In order to make up for the fraudulent claims, companies tend to raise premiums, meaning innocent customers must pay higher amounts of premiums. THREE WAYS COMPUTER VISION IS CHANGING P&C INSURANCE [Capco] Computer vision, a field of artificial intelligence (AI), has developed rapidly over the last ten years, with the end goal of a computer learning to see as a human would. The application of computer vision has the potential to transform the property and casualty insurance (P&C) industry, by helping individuals and insurance companies throughout virtually all the stages of the underwriting and claims life cycles. Read on as we examine three scenarios that highlight how computer vision can enhance safety, accuracy and efficiency throughout the insurance process. 2. IMAGE SIMILARITY Image Similarity compares two images and returns a value that tells you how visually similar they are. Here is used hashing algorithms by Python. (hashlib module- import hashlib). The lower the the score, the more contextually similar the two images are with a score of ‘0’ being identical.
  • 4. 3. FACIAL RECOGNITION Recognize and manipulate faces from Python. Built using dlib’s state-of-the-art face recognition. Built with deep learning. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark. Face Detection: Face detection is a computer vision technology that helps to locate/visualize human faces in digital images. Face detection has gained a lot of importance especially in fields like photography, security, and marketing. 4.OBJECT DETECTION AND RECOGNITION Object detection is the craft of detecting instances of a certain class, like animals, humans and many more in an image or video Object Detection (Tensorflow models in Python) makes it easy to detect objects by using pretrained object detection models
  • 5. number of person(insan sayısı) : 13 number of car(arac sayısı) : 8 number of truck(kamyon sayısı) : 2 number of bus(otobüs sayısı) : 1 number of backpack(sırt çantası sayısı) : 1 Is there any ambulance at the scene of the accident? ambulance : 82.00276494026184 police van: 15.833474695682526 minibus: 1.516808196902275 Garbage truck: 0.15010888455435634 fire engine : 0.11310353875160217 moving van: 0.08072283817455173 trolleybus : 0.07773929974064231 snowplow : 0.04561058012768626 tow truck : 0.037757077370770276 crane : 0.024561924510635436
  • 6. number of person(insan sayısı) : 20 number of car(arac sayısı) : 12 number of truck(kamyon sayısı) : 1 number of bus(otobüs sayısı) : 0 number of traffic lights(trafik lambasısayısı) : 2 Are there any traffic sign and lights? number of person(insan sayısı) : 1 number of car(arac sayısı) : 4 number of truck(kamyon sayısı) 2 number of traffic lights(trafik lambası sayısı) 3
  • 7. number of pedestrian(yaya sayısı) : 6 number of person(insan sayısı) : 12 number of car(arac sayısı) : 4 number of truck(kamyon sayısı) 1 number of traffic lights(trafik lambası sayısı) 0
  • 8. Car Speed Detection 5.Conclusion: Claims processing is a key touch point in the customer life cycle, and insurers have only a short opportunity to wow or disappoint their policyholders. With much at stake, insurers must adopt innovative tools and technologies in order to transform the claims function. Implementing computer vision technology that enables visual insurance claims has emerged as a solution that can transform the entire claims process. Computer vision guides customers through the process of capturing visuals while recognizing objects within the images, classifying the images. Artificial intelligence (computer vision, image processing …) techniques have been studied for the current situation in the industry.