Comparative study of building recognition rates in urban environments using vector quantization and deep learning
International Journal of Development Research
Comparative study of building recognition rates in urban environments using vector quantization and deep learning
Received 17th September, 2022 Received in revised form 20th September, 2022 Accepted 29th October, 2022 Published online 30th November, 2022
Copyright © 2022, Eduardo Silva Vasconcelos et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Building recognition is essential for a variety of applications such as automatic target detection, 3D city reconstruction, digital navigation, etc. This work aims to comparatively analyze the recognition rates of building images, using the Vector Quantization technique for image compression using the Linde-Buzo-Gray algorithm, with the results obtained by the Deep Learning method. Fourty classes have been analyzed including 10, 20, and 30 images per class, separately, in the RGB color scale, varying the number of centroids in 16, 32, 64, 128, and 256 for the vector quantization technique, and also varying the percentage of the number of images for training in 40%, 50%, and 60%, with their respective percentages of the number of images for recognition, in both methods. To verify the differences, ANOVA was performed, with Tukey's post-hoc at 5% significance. High recognition rates could be obtained from both methods. In the inferential analysis of the results obtained by Vector Quantization, significant recognition rates were found from 32 centroids. No significant difference has been found, by comparing the results obtained from the application of both techniques.
