Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

Facial recognition using dynamic image processing

Citation

Abstract

In this paper, we are prompting to detect a particular object (human face) from multiple objects (crowd) where multiple objects are present. We will try to recognize that particular object by using two pattern recognition algorithms, Eigenfaces, Hidden Markov model. Basically the reason to use more than one algorithm or process however that’s mention is because more accuracy hence therefore with one process the results however never become absolute and perfect, therefore filtering away the results from one algorithm and make it more efficient the second algorithm may come handy. An identified way that has been most famous is using particular algorithm or process and having a full-formed Data set.

Description

Cataloged from PDF version of thesis report.
Includes bibliographical references (page 43-44).
This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2017.

Publisher Link

Type

Thesis