Based on the features of fashion industry, we propose a novel visual method for analysis of fashion related multimedia information in the virtual space. The preferred factors with the highest attention rate in clothes selection are colour of skin, style and colour of clothes. Thus, whether the preferred factors satisfy the personalized demand of clients plays an greatly important role in proposed recommendation system.easy to users

Unmanned aerial vehicle (UAV) detection is gaining more attention in fields like public safety due to the extensive usage of UAVs in commercial and industrial applications. Consequently, UAV object identification algorithms are likewise evolving quickly. Notwithstanding, the diminutive dimensions of drones, intricate airspace backdrops, and fluctuating lighting circumstances continue to provide noteworthy obstacles for this field of study. This research suggests a small-scale UAV identification technique based on the improved YOLOv8 in response to the aforementioned issues. The main goal is to improve surveillance capabilities by using real-time video to detect and follow drones. Furthermore, the SMTP protocol present within it alerts when any drone is captured from the live streaming videos, and the buzzer will sound a warning signal.

The aim of our project is to develop a robot to detect human being trapped inside the collapsed building using suitable sensors. It helps the rescue team during natural calamities like earthquakes. The robot is designed and it can be controlled using customized IP address. Ultra-Wide Band (UWB) radar is used to detect the human beings even behind the walls. Arduino UNO is used to process the signal from the radar and other sensors. Wi-Fi module with inbuild camera which is used for the communication with the rescue team and the robot.The main purpose is to detect alive human beings is done. To design, build, and test a robot that moves autonomously. To find out the alive human being as soon as possible so that the person’s life can be saved. To design and implement alive human detection robot based on IoT. Keywords: Human Detection, Mobile Control, Arduino UNO etc.,

In forensic science, it is seen that hand-drawn face sketches are still very limited and time consuming when it comes to using them with the latest technologies used for recognition and identification of criminals. In this paper, we present a standalone application which would allow users to create composites face sketch of the suspect without the help of forensic artists using drag and drop feature in the application and can automatically match the drawn composite face sketch with the police database much faster and efficiently using deep learning and cloud infrastructure. Keywords: Forensic Face Sketch, Face Sketch Construction, Face Recognition, Criminal Identification, Deep Learning, Machine Locking, Two Step Verification.