An Indian facial database highlighting the Spectacle Problems

Name: An Indian facial database highlighting the Spectacle Problems
Creator: lazarus mayaluri
License: https://creativecommons.org/licenses/by/4.0/

Citation Author(s):: Lazarus Mayaluri (National Institute of Technology Rourkela)

Supratim Gupta (National Institute of Technology Rourkela)

Nidhi Panda (National Institute of Technology Rourkela)
Submitted by:: lazarus mayaluri
Last updated:: Thu, 07/30/2020 - 11:26
DOI:: 10.21227/ay8v-kj06
Data Format:: ZIP (binary jpg txt and bmp files)
Links:: Google Drive Link

7775 views

Categories:

Keywords:

Secondary reflection.

ACCESS DATASET CITE

Abstract

Occlusion, glare and secondary reflections formed due to and on the spectacles - results in poor detection, localization, and recognition of eye/face features. We term all the problems related to the usage of spectacles as The spectacle problem. Though several studies on the spectacle detection and removal have been reported in the literature, the study focusing on spectacle problem removal is very limited. One of the main reasons being, the nonavailability of a facial image database highlighting the spectacle problems. Therefore, we created an Indian facial image database consisting of corresponding facial images with and without spectacle problems. The release of database Version 1 contains a total of 271 images. However, the release of database Version 2 contains a total of 1,23,213 images from 58subjects.

Instructions:

Instructions are mentioned in the uploaded document.

Metadata nomenclature format (Version 1): "NUM_G_S_I_O"

where NUM = Subject ID Number: 000-270

G = Gender: Female='0', Male='1'

S = Spectacles: With out spectacles='0', With spectacles='1'

I = Illumination problem: No illumination problem='0', With illumnation problem='1'

O = Occlusion: No occlusion='0', With occlusion='1'

Metadata nomenclature format (Version 2): "SXX_G_I_S_NUM_A"

where SXX = Subject ID Number: S01-S58

G = Gender: Female='0', Male='1'

I = Illumination level: High illumination='H', Medium illumination='M', Low illumination='L'

S = Spectacles: With out spectacles='0', With spectacles='1'

NUM = Image Number: 001-201

A = Session: Session 0='0', Session 1='1'

Paper citation: "http://hdl.handle.net/2080/2992".

M. Z. Lazarus, S. Gupta and N. Panda, “An Indian facial database highlighting the Spectacle Problems,” in 2018 IEEE International Conference on Innovative Technologies in Engineering 2018 (ICITE OU), April 2018.

Can be downloaded from the following Google drive link:

https://drive.google.com/drive/folders/1yEI07d9ALKJd9yQzPekHeSGpoR2KRslS?usp=sharing

lazarus mayaluri Sun, 03/08/2020 - 05:47 Permalink

When shall we get the dataset?

Namrata Londhe Sun, 08/11/2019 - 12:39 Permalink