Animate Object Detection Using Deep Learning

  • Aishwarya Patil

Abstract

Nowadays, with the increasing use of biometric data, it is expected that systems can give successful results against difficult situations and work robustly. Especially, in face recognition systems, variables such as direction of light, facial expression and reflection are making difficult to identify. Thus, in recent Years, Convolutional Neural Network (CNN) models, which are deep learning models as an alternative to traditional feature extraction and artificial neural network methods, have begun to be developed. When analyzing human . activities using data mining or machine learning techniques, it can be useful to infer properties such as the gender or age of the people involved. Many algorithms have been implemented on different static and non-static conditions. Static conditions include static and uniform background, identical poses, similar illumination, neutral frontal face Non static conditions include position, partial occlusion and facial hair, which makes recognition process a complex problem. The main stages for face recognition include face detection, feature representation and classifications. In this work we present a glimpse of face detection techniques, methods used, their performance and their limitations and proposed a new technique for Face Detection based on Viola and Jones algorithm and principal component analysis.
Published
2018-04-23
How to Cite
PATIL, Aishwarya. Animate Object Detection Using Deep Learning. International Journal Of Emerging Technology and Computer Science, [S.l.], v. 3, n. 2, p. 124-129, apr. 2018. ISSN 2455-9954. Available at: <https://aspirepublishers.com/index.php/ijetcs/article/view/192>. Date accessed: 31 may 2020.