Volume 10 | Issue 6 | June-2022

 Abstract

In online shopping, People would like to know how they look in a particular dress they tend to buy. To bring closer between in-store (offline) and online shopping and provide a realistic shopping experience to the consumers, a system is required to predict how people look in a particular garment that they tend to buy. Traditional approaches to make such a system were dealing with computer graphics where a 3D avatar of the person is created and various clothes are visualized on him/her. The usage of such approaches limits practical applications due to high computation and hardware requirements. This Project aims to build a fitting system such that, it visualizes people wearing new clothes without any 3D information, only using Images, in the same pose as they are standing in. This Project is composed of two modules one for changing the shape of cloth given in the input according to the personality and another module to attach this cloth onto the individual body. Using Efficient CNN based networks, which learns to predict the parameters for changing shape via spatial transformation is used in the first module. The shape changed cloth is passed on to the next module which is based on U-net architecture that predicts the mask where to attach the cloth, using this information the cloth is attached onto the body for generating final output images. The system is able to generate natural and rich images without much loss.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

VIRTUAL CLOTH FITTING IN 2D USING DEEP LEARING

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

As advanced face synthesis and manipulation methods are made available, new types of fake face representations are being created which have raised significant concerns for their use in day-to-day life. Hence, it is crucial to identify the digitally altered facial images. A new method to identify the manipulated human faces and locate the region of manipulation is done using U-net Architecture. This manipulated image, created by altering the original image, along with the mask of alteration is used to train the model. Image padding, rectified linear activation, max pooling, up convolution are performed and thus output mask is obtained. The accuracy and dice score are calculated. Thus the area of manipulation done on the human face is found by using U-net.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Facial manipulation, U-net, area of manipulation, multi-class classification

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In Cryptography, plain text is converted to encrypted text before it is sent, and it is converted to plain text after communication on the other side. Steganography is a method of hiding secret data, by embedding it into an audio, video, image, or text file. One technique is to hide data in bits that represent the same color pixels repeated in a row in an image file. By applying the encrypted data to this redundant data in some inconspicuous way, the result will be an image file that appears identical to the original image but that has "noise" patterns of regular, unencrypted data. In this project it proposes to encrypt the IoT networks data by Cryptography method and hide the encrypted message inside an image file using Steganography method as well increases the number of bits that can be saved within a pixel of an image. We are going to incorporate the usage of Convolutional neural networks in traditional steganography method to drastically increase the payload that can be transmitted through an image. Thus, in this project the Convolutional networks algorithm will be developed and trained in such a way to increase the payload of the data to be encrypted as well as safely decrypted to view the original message.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Steganography, Cloud storage, Fractal Net

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The process of land registration in any country is known to be a multistep process, since it entails the engagement of all stakeholders who will have a direct or indirect stake in the registration. The currently used land record title storage system raises major issues about data fraud, the security of highly sensitive data, and the risk of system failure due to natural disasters, such as the server used for data storage going down. Compared to the current approaches and procedures for land title management and data storage, blockchain is a cutting-edge technology and database that has the ability to completely address the problems that plague current systems. The basic and most important aspect of blockchain technology is that it is a decentralised network in which all data supplied by a single node are confirmed by all other available nodes, and only after a consensus is made can then the shared data be saved to the blockchain.There are various platforms being used for the creation of reliable, decentralised, transparent, immutable, and secure blockchain-based land registration and management systems. Smart contracts based on the Ethereum blockchain are gaining traction among these systems. Being a public blockchain platform, it allows anyone to participate in the blockchain ecosystem .

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

LAND REGISTRATION USING BLOCK CHAIN METHOD

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

A wireless mesh network (WMN) is a mesh network created through the connection of wireless access point (WAP) nodes installed at each network user's locale. The networking infrastructure is decentralized and simplified because each node need only transmit as far as the next node. WMNs may or may not be connected to the internet. Wireless mesh networks, which can also be a form of wireless ad hoc network (WANET), are often used for the following: connecting internet of things (IoT) devices, such as sensors, security systems, smart appliances and monitoring systems; building networks in developing communities that lack internet wiring infrastructure; and providing consistent wireless access to hospitals, educational campuses and warehouses. Wi-Fi and networking in temporary locations, such as construction Network Security Can be defined as measures taken to protect data during their transmission along the media. Whereas securing the internet means taking measures to protect data during their transmission over a collection of Interconnected networks. Network security is the most important issue in the vast field of wireless networks. In order to improve network security, there are number of products that are available in the market that use packet filtering. For a network administrator, packet filtering is an effective tool for security purposes but he/she has to have an in depth knowledge of the capability of this tool. Our firewall software contains a set of protocol for which the filters will be applied. We have devised a packet filtering firewall called Net app for Microsoft windows operating systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Sensing with MQTT Mesh Network

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

DATA-DRIVEN DECISION SUPPORT FOR OPTIMIZING CYBER FORENSIC INVESTIGATIONS

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Animal Recognition, Repellent, Artificial Intelligence, Edge Computing, Animal Detection, Deep Learning, DCNN

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CONSUMER TO CONSUMER PRODUCT TRADING WITH STRATEGIC CONSUMER BEHAVIOUR USING PRIVATE BLOCK CHAIN TECHNIQUE

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Non-Continuous Spacious, resource monitoring, scheduling

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

BRAIN TUMOR DIAGONATION USING MACHINE LEARNING

  License

Creative Commons Attribution 4.0 and The Open Definition