Normal view MARC view ISBD view

Generating Captions for Underwater Images Using Deep Learning Models

By:

Tanay Gangey. Hardik Gourisaria. Akhilarka Jayanthi. Rama Dev P. Shylaja S S

Material type:

TextLanguage: English Publication details: 2019Subject(s):

Deep Learning, Convolutional Neural Networks, Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Units, Image Captioning

DDC classification:

CPCS19-1854

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Collection	Call number	URL	Status	Barcode
Institutional repository	Central Library Central Library	Central Library	CPCS19-1854 (Browse shelf(Opens below))	Link to resource	Available	IR1854

Image captioning is a small yet important domain lying under the vast subject of Scene Understanding. Our work focusses on the generation of annotations for Underwater images in natural language. A new underwater image dataset, namely PESEmphasis5k, has been created and captioned. Our model using different variations of CNNs, LSTMs, and GRUs, when trained on our new dataset, generates captions with good accuracy. Alongside this, we introduce Parameter Wise Tally Checker as a new evaluation metrics for analyzing and evaluating models and demonstrate its usage on our captioning model.

There are no comments on this title.

to post a comment.