Darpan Anand - Academia.edu (original) (raw)

Papers by Darpan Anand

2021 International Conference on Computational Performance Evaluation (ComPE)

The current era is the not only depends on Industry 4.0 but extends the technical development up ... more The current era is the not only depends on Industry 4.0 but extends the technical development up to Industry 5.0. These developments are beyond the central client-server based system and depends on the multi-server based system using distributed services. These systems are inter-connected through multi-server architecture, using distributed computing to incorporate the services deployed on various different servers. For these services and architecture the authentication which is a process to prove genuine user’s legitimate identity, is very crucial. Due to various threats and attacks, the strong and non-vulnerable process of authentication is required. This manuscript targets to give the solution for multi-server architecture based authentication. The proposed authentication mechanism is targeting the e-governance system as a case study to give the integration and unified view to the existing scattered system to server the country. The existing e-governance system is working on three layers communication system. The proposed system is able to prove the genuine user’s legitimate identity for multi-server architecture based system. Further, the proposed system is developed to work for distributed storage utility and secure due to not depends on the central verification table. Further, the proposed authentication mechanism has the utility to share a secrete key for secure communication among all the layers. It means the proposed system has capabilities for integration, unified view to existing system, session key management among all the communication layers, not depends on central verification table, and having distributed storage utility. The proposed mechanism of authentication is tested for various known security attack to attain the security goals.

2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021

2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021

Computers, Materials & Continua, 2022

Software-defined networking is one of the progressive and prominent innovations in Information an... more Software-defined networking is one of the progressive and prominent innovations in Information and Communications Technology. It mitigates the issues that our conventional network was experiencing. However, traffic data generated by various applications is increasing day by day. In addition, as an organization's digital transformation is accelerated, the amount of information to be processed inside the organization has increased explosively. It might be possible that a Software-Defined Network becomes a bottleneck and unavailable. Various models have been proposed in the literature to balance the load. However, most of the works consider only limited parameters and do not consider controller and transmission media loads. These loads also contribute to decreasing the performance of Software-Defined Networks. This work illustrates how a software-defined network can tackle the load at its software layer and give excellent results to distribute the load. We proposed a deep learning-dependent convolutional neural networkbased load balancing technique to handle a software-defined network load. The simulation results show that the proposed model requires fewer resources as compared to existing machine learning-based load balancing techniques.

Advanced Healthcare Systems, 2022

Security and Privacy of Electronic Healthcare Records: Concepts, paradigms and solutions, 2019

This chapter discusses concepts and various research-oriented IAM techniques for growing connecte... more This chapter discusses concepts and various research-oriented IAM techniques for growing connected healthcare system. Identity and access management (IAM) in a computer system includes a security framework, tools, and technologies to control access to critical information resources to legitimate users in the right context. IAM is even more challenging for healthcare organization as they are responsible for the protection of users identities and valuable medical records. Health care organizations are more prone to attacks than financial institutions. Data breaches in e-healthcare can lead to identifying theft, billing, and insurance frauds. To prevent such breaches IAM for health care must be even more secure and scalable to meet current challenges. IAM cannot be explained without learning the concept of identification.

Asian Journal of Research in Computer Science, 2021

Cocoa industry of Ghana employs above a million people across Ghana areas of cocoa-growing, and i... more Cocoa industry of Ghana employs above a million people across Ghana areas of cocoa-growing, and it is the principal source of revenue for above 6 million people. The government of Ghana spends an important amount of money yearly on cocoa procurements in addition to farm inputs. However, the business of cocoa stays to meet many obstacles in testing and procurement, leading to lower annual yields. The study seeks to examine the issues of Ghana's cocoa purchasing process and develop IoT based automatic cocoa quality testing system. The method of the study will be descriptive design with quantitative method to pinpoint the procurement process and quality assurance process of cocoa in Ghana. The quantitative results will be used to develop IoT based automatic cocoa quality testing system to address cocoa testing issue. The study will analyze the impact of the proposed system for procurement process on the cocoa quality testing and procurement process in Ghana.

Asian Journal of Research in Computer Science, 2021

A collection of interconnected devices that deal with communication protocols that are common to ... more A collection of interconnected devices that deal with communication protocols that are common to share resources provided by nodes of a network over digital interconnections is a computer network. The process of determining the most efficient route from a source to a given target is called routing. Cisco's Enriched Internal Routing Gateway Protocol for IPv6 and the IETF's OSPFv3 (First Version 3 of Open Shortest Path) are two of the most frequently studied IPv6 routing protocols among researchers (EIGRPv6). As a result of the popularity of EIGRPv6 and OSPFv3, it is necessary to undertake a thorough contrast of the two protocols once working inside a minor enterprise network on IPv6. Thus, the study analysed the performance comparison of OSPFV3 and EIGRP with IPv6 networks with regards to convergence time, end-to-end delay, and packet loss. Packet Tracer 6.2.2 was used to compare the performance of routing protocols of different kinds. In the simulation, Cisco routers, switch...

Blockchain for 5G-Enabled IoT, 2020

Proceedings of International Conference on Big Data, Machine Learning and their Applications, 2020

Diabetes is a metabolic chronic disease that due to the lack of insulin makes a serious problem w... more Diabetes is a metabolic chronic disease that due to the lack of insulin makes a serious problem with the transfer of blood all over the body. Nowadays, this epidemic has been expanding steadily everywhere throughout the world. Furthermore, negligence can lead to visual deficiency, amputations, cardiovascular breakdown, heart failure, and stroke. Diabetes generally occurs in two types (diabetes Type-1, diabetes Type-2) through the body, diabetes Type-2 shows the acute condition in the patient's body. The present study reviews the existing research studies and their methods for predicting diabetes using machine learning techniques, these methods use previously stored patient information to predict the next steps or the next events. During this research that using machine learning methods in addition to high speed and accuracy in the prediction of diabetes, it can improve the efficiency and importance of this process. Keywords Diabetes risk prediction • Diabetes Type-2 • Ensemble methods •

Turkish Journal of Computer and Mathematics Education (TURCOMAT), 2021

This research paper explores the concept of eAuction, an increasingly form of online procurement.... more This research paper explores the concept of eAuction, an increasingly form of online procurement. There is fixed delivery policy.This is a fully dynamic system which can be easily operated by the users.This research paper explores all the increasing form of online procurement. Online e auction system is gaining popularity day by day because of its ease of making online bidding and selling or buying. Users can freely go the website and register there and it’s ready for selling or buying their product. The main thing that is needed to be there is trust among the users, so that they can easily register and take part in the process without having any doubt regarding security. The aim of any online system are related with two points that are Customer satisfaction and Business purpose. Therefore, to meet these requirements there must be need of making enhancements in the online auction system. This paper will explore the all forms of online procurement that we can make to improve the curr...

The sentimental analysis is phenomenon of exploring, analyzing and organizing human feelings. It ... more The sentimental analysis is phenomenon of exploring, analyzing and organizing human feelings. It is a process of extracting feelings of human faro pictures. It involves the separation of image into various characters such as face, background, etc. It uses lips and eye shape for extracting human feelings. It uses numerous of applications such as Pycharm Numpy ,Open CV, Python,etc. Its main objective is to find out the moods of human such as happy , sad ,etc. This report generates the emotional state of human being as well as different emotion of human in different situation.

Automated techniques minimize the complexity, saving time and efforts in the object classificatio... more Automated techniques minimize the complexity, saving time and efforts in the object classification and their analysis. Sloan Digital Sky Survey (SDSS) is one of the spectroscopic surveys releasing large data sets. Astronomers are looking for some automated techniques so that they can analyze these massive data sets which are now publicly available. We use Feed Forward Back Propagation (FFBP) Neural Network for automatic classification. Classification of stars is performed on the basis of two parameters that are temperature and color. 1500 SDSS spectra are classified into 4 spectral types, and around 2359 SDSS spectra are classified into 7 spectral types ranging from A to K and O to M type stars by using color and temperature, respectively.

Mathematical Problems in Engineering, 2021

The advanced technology Internet of Things (IoT) visualizes a worldwide, that is, internally conn... more The advanced technology Internet of Things (IoT) visualizes a worldwide, that is, internally connected, networks of smart physical entities. IoT is a promising technology used in several applications including disaster management. In disaster management, the role of IoT is so important and ubiquitous and could be life-saving. This article describes the role of IoT in disaster management. More precisely, it presents IoT-based disaster management for different kind of disasters with a comparison between some solutions that are available in the market. It shows an implementation of some examples of the application of IoT such as early-warning system for fire detection and earthquake and represents some approaches talking about the application, IoT architecture, and focusing of the study on different disasters. This study could be a good guide to stakeholder about the use of IoT technology to secure their smart cities’ infrastructure and to manage disaster and reduce risks.

In today’s robotics and machine translation tasks are performing the main role in hand gestures. ... more In today’s robotics and machine translation tasks are performing the main role in hand gestures. Gesture or detection implementation will help humans in several means. Gesture recognition systems are used in various fields such as DNN, ML and NNs etc. The applications of this research are sign language translation, music creation and Robot remote controlling, etc. In this research work proposed HGR methods are using feature extraction and optimized MSVM classification. This process gives the applications of edge detection, interference, filters, SIFT-ALO algorithm and binary during image pre-processing, in which these approaches add to better extraction and selection. In proposed work, implemented an optimized MSVM method are two classes such as training and testing. Optimized M-SVM is performed on the ASL gesture dataset along with existing SURF and SIFT techniques. This research work is used for the simulation tool (MATLAB) and calculated performance metrics like processing time, ...

2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), 2021

Internet of Things (IoT) has been used in many different applications such as agriculture, smart ... more Internet of Things (IoT) has been used in many different applications such as agriculture, smart cities, health care, and many more. It is a building block for many smart technologies and any device that is connected to the internet has the ability to become an IoT device. IoT plays a very crucial role in controlling the spread of virus in case of any pandemic. A pandemic is an infectious virus that spreads to more than one continent and is a major threat to not only people’s lives but also to the livelihood and economy of a country. IoT plays an important role in all the phases of a pandemic. Different IoT devices such as drones, smart watches, robots, applications prove to be helpful in controlling the spread and also keeping the track of existing spread of the virus. This paper discusses the use of IoT in monitoring the spread of the pandemic and the role of various IoT devices and technologies in early detection, quarantine phase and after recovery from a pandemic.

2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 2018

With the advances in 3D technology, digital photogrammetry and computer vision, solving the corre... more With the advances in 3D technology, digital photogrammetry and computer vision, solving the correspondence problem accurately and efficiently has gained popularity. Locating the position of corresponding pixel in target image for given pixel in reference image is referred as Correspondence problem in stereo-image matching. A number of stereo image matching approaches are available at present, but there has been trade-off between density of match, speed and accuracy. Techniques that are capable of producing dense disparity maps are prone to higher computational complexity thereby, requires longer time, however techniques that are fast are not capable of producing dense disparity maps. On the basis of density of disparity maps generated, we can broadly classify image matching methods as area-based image matching or feature-based image matching.[1] An alternative approach has been proposed in this paper in order to match pixels accurately using a mathematical approach referred as Polynomial Fitting which requires identification of minimum of 6 control points in the locality or neighborhood. If the number of control points for a given region or locality is less than 6, than window size increases automatically to accommodate more control points. Window continues to grow in size until number of control points in the region becomes 6 or exceeds 6. When the number of control points are greater than 6, all possible combination of 6 points are used to calculate and the combination that gives least Sum of Squared Error is used for further calculation. A statistical algorithm referred as Random Sample Consensus is applied in order to select 6 control points for calculation. The algorithm randomly selects any 6 pair of control points for calculation. We can divide this algorithm into two segments-1)Determination of control points 2) Determination of match points. The percentage of accurately matched pixels in stereo pairs was found to be 93.48% in one of the test data set, which was very high compared to standard Normalized Cross Correlation based approach (77.89%).

2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS), 2021

Facial expressions are not only the natural form of human emotions display but also a key nonverb... more Facial expressions are not only the natural form of human emotions display but also a key nonverbal type of communication. Face detection and emotion classification is an area which is widely used and has been at the center of the on-going research now. The rapid development in this area has allowed to use the technology in applications such as living assistance, real time monitoring of health, surveillance systems, authentication, access control and many more. As most of the focus for emotion detection lies around mouth and eyes, extracting and categorizing the gestures is very important. Neural networks and machine learning has demonstratedits use in obtaining good results in emotion recognition and classification. This paper discusses a combined model for facial key point detection and facial expression detection model.

2021 International Conference on Computational Performance Evaluation (ComPE)

The current era is the not only depends on Industry 4.0 but extends the technical development up ... more The current era is the not only depends on Industry 4.0 but extends the technical development up to Industry 5.0. These developments are beyond the central client-server based system and depends on the multi-server based system using distributed services. These systems are inter-connected through multi-server architecture, using distributed computing to incorporate the services deployed on various different servers. For these services and architecture the authentication which is a process to prove genuine user’s legitimate identity, is very crucial. Due to various threats and attacks, the strong and non-vulnerable process of authentication is required. This manuscript targets to give the solution for multi-server architecture based authentication. The proposed authentication mechanism is targeting the e-governance system as a case study to give the integration and unified view to the existing scattered system to server the country. The existing e-governance system is working on three layers communication system. The proposed system is able to prove the genuine user’s legitimate identity for multi-server architecture based system. Further, the proposed system is developed to work for distributed storage utility and secure due to not depends on the central verification table. Further, the proposed authentication mechanism has the utility to share a secrete key for secure communication among all the layers. It means the proposed system has capabilities for integration, unified view to existing system, session key management among all the communication layers, not depends on central verification table, and having distributed storage utility. The proposed mechanism of authentication is tested for various known security attack to attain the security goals.

2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021

2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021

Computers, Materials & Continua, 2022

Software-defined networking is one of the progressive and prominent innovations in Information an... more Software-defined networking is one of the progressive and prominent innovations in Information and Communications Technology. It mitigates the issues that our conventional network was experiencing. However, traffic data generated by various applications is increasing day by day. In addition, as an organization's digital transformation is accelerated, the amount of information to be processed inside the organization has increased explosively. It might be possible that a Software-Defined Network becomes a bottleneck and unavailable. Various models have been proposed in the literature to balance the load. However, most of the works consider only limited parameters and do not consider controller and transmission media loads. These loads also contribute to decreasing the performance of Software-Defined Networks. This work illustrates how a software-defined network can tackle the load at its software layer and give excellent results to distribute the load. We proposed a deep learning-dependent convolutional neural networkbased load balancing technique to handle a software-defined network load. The simulation results show that the proposed model requires fewer resources as compared to existing machine learning-based load balancing techniques.

Advanced Healthcare Systems, 2022

Security and Privacy of Electronic Healthcare Records: Concepts, paradigms and solutions, 2019

This chapter discusses concepts and various research-oriented IAM techniques for growing connecte... more This chapter discusses concepts and various research-oriented IAM techniques for growing connected healthcare system. Identity and access management (IAM) in a computer system includes a security framework, tools, and technologies to control access to critical information resources to legitimate users in the right context. IAM is even more challenging for healthcare organization as they are responsible for the protection of users identities and valuable medical records. Health care organizations are more prone to attacks than financial institutions. Data breaches in e-healthcare can lead to identifying theft, billing, and insurance frauds. To prevent such breaches IAM for health care must be even more secure and scalable to meet current challenges. IAM cannot be explained without learning the concept of identification.

Asian Journal of Research in Computer Science, 2021

Cocoa industry of Ghana employs above a million people across Ghana areas of cocoa-growing, and i... more Cocoa industry of Ghana employs above a million people across Ghana areas of cocoa-growing, and it is the principal source of revenue for above 6 million people. The government of Ghana spends an important amount of money yearly on cocoa procurements in addition to farm inputs. However, the business of cocoa stays to meet many obstacles in testing and procurement, leading to lower annual yields. The study seeks to examine the issues of Ghana's cocoa purchasing process and develop IoT based automatic cocoa quality testing system. The method of the study will be descriptive design with quantitative method to pinpoint the procurement process and quality assurance process of cocoa in Ghana. The quantitative results will be used to develop IoT based automatic cocoa quality testing system to address cocoa testing issue. The study will analyze the impact of the proposed system for procurement process on the cocoa quality testing and procurement process in Ghana.

Asian Journal of Research in Computer Science, 2021

A collection of interconnected devices that deal with communication protocols that are common to ... more A collection of interconnected devices that deal with communication protocols that are common to share resources provided by nodes of a network over digital interconnections is a computer network. The process of determining the most efficient route from a source to a given target is called routing. Cisco's Enriched Internal Routing Gateway Protocol for IPv6 and the IETF's OSPFv3 (First Version 3 of Open Shortest Path) are two of the most frequently studied IPv6 routing protocols among researchers (EIGRPv6). As a result of the popularity of EIGRPv6 and OSPFv3, it is necessary to undertake a thorough contrast of the two protocols once working inside a minor enterprise network on IPv6. Thus, the study analysed the performance comparison of OSPFV3 and EIGRP with IPv6 networks with regards to convergence time, end-to-end delay, and packet loss. Packet Tracer 6.2.2 was used to compare the performance of routing protocols of different kinds. In the simulation, Cisco routers, switch...

Blockchain for 5G-Enabled IoT, 2020

Proceedings of International Conference on Big Data, Machine Learning and their Applications, 2020

Diabetes is a metabolic chronic disease that due to the lack of insulin makes a serious problem w... more Diabetes is a metabolic chronic disease that due to the lack of insulin makes a serious problem with the transfer of blood all over the body. Nowadays, this epidemic has been expanding steadily everywhere throughout the world. Furthermore, negligence can lead to visual deficiency, amputations, cardiovascular breakdown, heart failure, and stroke. Diabetes generally occurs in two types (diabetes Type-1, diabetes Type-2) through the body, diabetes Type-2 shows the acute condition in the patient's body. The present study reviews the existing research studies and their methods for predicting diabetes using machine learning techniques, these methods use previously stored patient information to predict the next steps or the next events. During this research that using machine learning methods in addition to high speed and accuracy in the prediction of diabetes, it can improve the efficiency and importance of this process. Keywords Diabetes risk prediction • Diabetes Type-2 • Ensemble methods •

Turkish Journal of Computer and Mathematics Education (TURCOMAT), 2021

This research paper explores the concept of eAuction, an increasingly form of online procurement.... more This research paper explores the concept of eAuction, an increasingly form of online procurement. There is fixed delivery policy.This is a fully dynamic system which can be easily operated by the users.This research paper explores all the increasing form of online procurement. Online e auction system is gaining popularity day by day because of its ease of making online bidding and selling or buying. Users can freely go the website and register there and it’s ready for selling or buying their product. The main thing that is needed to be there is trust among the users, so that they can easily register and take part in the process without having any doubt regarding security. The aim of any online system are related with two points that are Customer satisfaction and Business purpose. Therefore, to meet these requirements there must be need of making enhancements in the online auction system. This paper will explore the all forms of online procurement that we can make to improve the curr...

The sentimental analysis is phenomenon of exploring, analyzing and organizing human feelings. It ... more The sentimental analysis is phenomenon of exploring, analyzing and organizing human feelings. It is a process of extracting feelings of human faro pictures. It involves the separation of image into various characters such as face, background, etc. It uses lips and eye shape for extracting human feelings. It uses numerous of applications such as Pycharm Numpy ,Open CV, Python,etc. Its main objective is to find out the moods of human such as happy , sad ,etc. This report generates the emotional state of human being as well as different emotion of human in different situation.

Automated techniques minimize the complexity, saving time and efforts in the object classificatio... more Automated techniques minimize the complexity, saving time and efforts in the object classification and their analysis. Sloan Digital Sky Survey (SDSS) is one of the spectroscopic surveys releasing large data sets. Astronomers are looking for some automated techniques so that they can analyze these massive data sets which are now publicly available. We use Feed Forward Back Propagation (FFBP) Neural Network for automatic classification. Classification of stars is performed on the basis of two parameters that are temperature and color. 1500 SDSS spectra are classified into 4 spectral types, and around 2359 SDSS spectra are classified into 7 spectral types ranging from A to K and O to M type stars by using color and temperature, respectively.

Mathematical Problems in Engineering, 2021

The advanced technology Internet of Things (IoT) visualizes a worldwide, that is, internally conn... more The advanced technology Internet of Things (IoT) visualizes a worldwide, that is, internally connected, networks of smart physical entities. IoT is a promising technology used in several applications including disaster management. In disaster management, the role of IoT is so important and ubiquitous and could be life-saving. This article describes the role of IoT in disaster management. More precisely, it presents IoT-based disaster management for different kind of disasters with a comparison between some solutions that are available in the market. It shows an implementation of some examples of the application of IoT such as early-warning system for fire detection and earthquake and represents some approaches talking about the application, IoT architecture, and focusing of the study on different disasters. This study could be a good guide to stakeholder about the use of IoT technology to secure their smart cities’ infrastructure and to manage disaster and reduce risks.

In today’s robotics and machine translation tasks are performing the main role in hand gestures. ... more In today’s robotics and machine translation tasks are performing the main role in hand gestures. Gesture or detection implementation will help humans in several means. Gesture recognition systems are used in various fields such as DNN, ML and NNs etc. The applications of this research are sign language translation, music creation and Robot remote controlling, etc. In this research work proposed HGR methods are using feature extraction and optimized MSVM classification. This process gives the applications of edge detection, interference, filters, SIFT-ALO algorithm and binary during image pre-processing, in which these approaches add to better extraction and selection. In proposed work, implemented an optimized MSVM method are two classes such as training and testing. Optimized M-SVM is performed on the ASL gesture dataset along with existing SURF and SIFT techniques. This research work is used for the simulation tool (MATLAB) and calculated performance metrics like processing time, ...

2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), 2021

Internet of Things (IoT) has been used in many different applications such as agriculture, smart ... more Internet of Things (IoT) has been used in many different applications such as agriculture, smart cities, health care, and many more. It is a building block for many smart technologies and any device that is connected to the internet has the ability to become an IoT device. IoT plays a very crucial role in controlling the spread of virus in case of any pandemic. A pandemic is an infectious virus that spreads to more than one continent and is a major threat to not only people’s lives but also to the livelihood and economy of a country. IoT plays an important role in all the phases of a pandemic. Different IoT devices such as drones, smart watches, robots, applications prove to be helpful in controlling the spread and also keeping the track of existing spread of the virus. This paper discusses the use of IoT in monitoring the spread of the pandemic and the role of various IoT devices and technologies in early detection, quarantine phase and after recovery from a pandemic.

2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 2018

With the advances in 3D technology, digital photogrammetry and computer vision, solving the corre... more With the advances in 3D technology, digital photogrammetry and computer vision, solving the correspondence problem accurately and efficiently has gained popularity. Locating the position of corresponding pixel in target image for given pixel in reference image is referred as Correspondence problem in stereo-image matching. A number of stereo image matching approaches are available at present, but there has been trade-off between density of match, speed and accuracy. Techniques that are capable of producing dense disparity maps are prone to higher computational complexity thereby, requires longer time, however techniques that are fast are not capable of producing dense disparity maps. On the basis of density of disparity maps generated, we can broadly classify image matching methods as area-based image matching or feature-based image matching.[1] An alternative approach has been proposed in this paper in order to match pixels accurately using a mathematical approach referred as Polynomial Fitting which requires identification of minimum of 6 control points in the locality or neighborhood. If the number of control points for a given region or locality is less than 6, than window size increases automatically to accommodate more control points. Window continues to grow in size until number of control points in the region becomes 6 or exceeds 6. When the number of control points are greater than 6, all possible combination of 6 points are used to calculate and the combination that gives least Sum of Squared Error is used for further calculation. A statistical algorithm referred as Random Sample Consensus is applied in order to select 6 control points for calculation. The algorithm randomly selects any 6 pair of control points for calculation. We can divide this algorithm into two segments-1)Determination of control points 2) Determination of match points. The percentage of accurately matched pixels in stereo pairs was found to be 93.48% in one of the test data set, which was very high compared to standard Normalized Cross Correlation based approach (77.89%).

2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS), 2021

Facial expressions are not only the natural form of human emotions display but also a key nonverb... more Facial expressions are not only the natural form of human emotions display but also a key nonverbal type of communication. Face detection and emotion classification is an area which is widely used and has been at the center of the on-going research now. The rapid development in this area has allowed to use the technology in applications such as living assistance, real time monitoring of health, surveillance systems, authentication, access control and many more. As most of the focus for emotion detection lies around mouth and eyes, extracting and categorizing the gestures is very important. Neural networks and machine learning has demonstratedits use in obtaining good results in emotion recognition and classification. This paper discusses a combined model for facial key point detection and facial expression detection model.