Aman Swaraj, Harshita Sahni, Archit Agarwal, Neeraj Kumar Pandey and Supriya Shukla, College of Engineering- Roorkee, India

Indian Culture exceeds beyond the mere definition of ‘simply how people live’ as it scientifically operates according to specific, detailed knowledge of the eventual aim of life and the means to attain it. Over the years, a lot of work has been done on object recognition and scene recognition but Event Recognition is still one of the fields wherein lies a huge potential for lots of research work and so with this paper, we put forward our best step to preserve the culture of India. More than 150 images of near about 20 cultural events are collected. Results are derived from support vector machine classifier using features extracted by a pre-trained convolutional neural network- Alex Net. In most visual recognition tasks, it strongly suggested that features obtained from deep learning with convolutional nets should be the chief candidate. Our proposed framework has classified images with a comparable accuracy of 77.72 %.

Indian cultural events recognition, Convolutional neural network, Local Binary Patterns, Support Vector Machine.