Automatic image capturing

Simple item page
dc.contributor.authorSojitra, Ishita
dc.date.accessioned2025-05-01T16:10:54Z
dc.date.available2025-05-01T16:10:54Z
dc.date.issued2023
dc.descriptionThe difficult and multidisciplinary process of automatically creating accurate and logical textual descriptions for photographs is known as automatic image captioning. Modern Neural Networks excel in tasks like Computer Vision and Natural Language Processing, but their memory and compute appetite hinder deployment on resource-limited edge devices. Researchers have developed pruning and quantization algorithms to compress networks without compromising efficacy. The process typically involves two main steps: Image understanding and Caption generation. This work presents an unconventional end-to-end compression pipeline for a CNN (Convolutional neural network)-LSTM (Long short-term memory)-based Image captioning model, achieving a 73.1 percentage reduction in model size, 71.3 percentage reduction in inference time, and 7.7 percentage increase in BLEU(bilingual evaluation understudy) score compared to uncompressed models. By comparing generated captions with reference captions created by humans, evaluation metrics like BLEU (bilingual evaluation understudy) and METEOR (metric for evaluation of translation with explicit ordering) are used to evaluate the quality of generated captions. The purpose of Automatic image processing is to extract useful information from photos, making analysis, interpretation, and manipulation faster, precise, and effective in various fields, using computational algorithms.
dc.identifier.doihttps://doi.org/10.7939/r3-8xqr-m878
dc.language.isoen
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subjectimage understanding
dc.subjectcaption generation
dc.subjectcomputer vision
dc.subjectnatural language processing
dc.subjectdeep learning
dc.subjectCNN
dc.subjectrecurrent neural networks
dc.subjectlong short-term memory
dc.subjectevaluation metrics
dc.titleAutomatic image capturing
dc.typehttp://purl.org/coar/resource_type/c_1843
ual.jupiterAccesshttp://terms.library.ualberta.ca/public

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
2023_MScIT_Sojitra.pdf
Size:
6.31 MB
Format:
Adobe Portable Document Format
Download

Collections

Master of Science in Information Technology Project Reports (Concordia University of Edmonton)