Rights accessRestricted access - confidentiality agreement
This master's thesis provides an analysis on the generation of synthetic datasets as a pertinent substitute for missing large training sets in learning algorithms. Furthermore, it endeavours to enhance feature detection in learning to count problems by application of Deep Learning (DL) algorithms.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder. If you wish to make any use of the work not provided for in the law, please contact: firstname.lastname@example.org