4 research outputs found
A Real Time System for Hand Gesture Recognition
No full textIn this paper we explore the various aspects of hand gesture recognition in real time using neural networks. Hand gesture can be a vital way for the user to interact with any system. In this system we capture a hand gesture from the user and then perform the action related to it. This provides us with an alternative to mouse and keyboard to control a system. Hand gesture recognition can be helpful in various fields and areas where interacting with the system without touch is important. Hand gesture recognition is incorporated along with image processing and to add additional accuracy we are using neural network. This combination of image processing and neural network in real time forms a really powerful tool, forming the base of our project
A Survey of Object Classification and Detection Techniques in Assistance Systems for the Visually Impaired
No full textThe number of visually impaired individuals in the world is estimated to be 1 billion, as per WHO reports. Through a thorough examination of existing assistive technology and research, this paper provides a survey of object classification and detection techniques that are used in assistive technology by visually impaired individuals. We discuss the methodology’s drawbacks, s and functionalities of these techniques, and observe how sufficient they are in meeting the needs and requirements of the targeted users, and how they can be improved. As a result of this study, we identify areas with room for improvement in object detection in the assistive technology domain
PyCPL: The ESO Common Pipeline Library in Python v1.0
No full textPyCPL provides full access to ESO's Common Pipeline Library ( CPL) for
astronomical data reduction within a Python environment. Not only does it offer
a Python interface to the robust CPL library, but it also lets users and
developers fully utilise the rest of the scientific Python ecosystem. We have
written a C++ layer to CPL and with pybind11 (a third-party library) created a
Pythonic API to CPL. Since CPL has been around for so long, it has been
thoroughly tested and understood. In 2003 it was developed in C due to its
efficiency and speed of execution. With the community however moving away from
C/C++ programming and embracing Python for data processing tasks, there is a
need to provide access to the CPL utilities within a Python environment. With
the latest version being released users can now install PyCPL to run existing
CPL recipes (written in C) and access the results from Python. It also provides
the ability to create new recipes in Python using the functionality provided by
CPL.Comment: This paper was for a poster presented in ADASS XXXIII. poster number
P92
