Bangla Natural Language Image to Text (BNLIT) (doi:10.7910/DVN/DZZ1ZB)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Document Description

Citation

Title:

Bangla Natural Language Image to Text (BNLIT)

Identification Number:

doi:10.7910/DVN/DZZ1ZB

Distributor:

Harvard Dataverse

Date of Distribution:

2019-08-20

Version:

1

Bibliographic Citation:

Jishan, Md. Asifuzzaman; Mahmud, Khan Raqib; Azad, Abul Kalam Al, 2019, "Bangla Natural Language Image to Text (BNLIT)", https://doi.org/10.7910/DVN/DZZ1ZB, Harvard Dataverse, V1

Study Description

Citation

Title:

Bangla Natural Language Image to Text (BNLIT)

Identification Number:

doi:10.7910/DVN/DZZ1ZB

Authoring Entity:

Jishan, Md. Asifuzzaman (University of Liberal Arts Bangladesh)

Mahmud, Khan Raqib (University of Liberal Arts Bangladesh)

Azad, Abul Kalam Al (University of Liberal Arts Bangladesh)

Distributor:

Harvard Dataverse

Access Authority:

Jishan, Md. Asifuzzaman

Depositor:

Jishan, Md. Asifuzzaman

Date of Deposit:

2019-08-20

Holdings Information:

https://doi.org/10.7910/DVN/DZZ1ZB

Study Scope

Keywords:

Computer and Information Science, Bengali Natural Language Descriptors, Image to Text Generation

Abstract:

We represented a new Bangla dataset with a Hybrid Recurrent Neural Network model which generated Bangla natural language description of images. This dataset achieved by a large number of images with classification and containing natural language process of images. We conducted experiments on our self-made Bangla Natural Language Image to Text (BNLIT) dataset. Our dataset contained 8,743 images. We made this dataset using Bangladesh perspective images. We used one annotation for each image. In our repository, we added two types of pre-processed data which is 224 × 224 and 500 × 375 respectively alongside annotations of full dataset. We also added CNN features file of whole dataset in our repository which is features.pkl.

Methodology and Processing

Sources Statement

Data Access

Notes:

<a href="http://creativecommons.org/publicdomain/zero/1.0">CC0 1.0</a>

Other Study Description Materials

Other Study-Related Materials

Label:

Annotation-Bangla Natural Language Image to Text (BNLIT)-Full Dataset

Notes:

text/plain; charset=UTF-8

Other Study-Related Materials

Label:

Bangla Natural Language Image to Text (BNLIT)-Preprocessing and Resizing Dataset-resized-224_224.rar

Notes:

application/x-rar-compressed

Other Study-Related Materials

Label:

Bangla Natural Language Image to Text (BNLIT)-Preprocessing and Resizing Dataset-resized-500_375.rar

Notes:

application/x-rar-compressed

Other Study-Related Materials

Label:

features.pkl

Notes:

application/octet-stream

Other Study-Related Materials

Label:

Test-Annotation-Bangla Natural Language Image to Text (BNLIT).txt

Notes:

text/plain

Other Study-Related Materials

Label:

Train-Annotation-Bangla Natural Language Image to Text (BNLIT).txt

Notes:

text/plain