Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment

Recently in Malaysia, digital out-of-home (DOOH) advertising is getting common. It is a marketing tool to promote the branding of a product or service in the high population flow area. The existing DOOH advertising in Malaysia only broadcast the advertisement in a continuous and random manner withou...

全面介紹

Saved in:
書目詳細資料
主要作者: Loo, Eng Keong
格式: Thesis
出版: 2021
主題:
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my-mmu-ep.11423
record_format uketd_dc
spelling my-mmu-ep.114232023-05-22T07:31:49Z Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment 2021-01 Loo, Eng Keong TA1501-1820 Applied optics. Photonics Recently in Malaysia, digital out-of-home (DOOH) advertising is getting common. It is a marketing tool to promote the branding of a product or service in the high population flow area. The existing DOOH advertising in Malaysia only broadcast the advertisement in a continuous and random manner without considering the presence of the audience. This causes the audience most likely to perceive some irrelevant advertisements. The recent advances of facial analysis unlock the potential of the DOOH media towards the targeted advertising manner. Therefore, the DOOH media is able to deliver a customised advertisement based on the facial attributes of the audience. However, the DOOH media is commonly operating in an uncontrolled environment. In such an environment, facial analysis faces two main challenges which are blurry faces and misaligned faces. These challenges are noises that increase the difficulty in feature extraction. In this thesis, meFusion, a handcrafted feature extraction method for gender estimation is proposed to handle the aforementioned challenges without going through the pre-processing stage. Bypassing the preprocessing stage is able to reduce the workload of DOOH media. A series of experiments that simulate the challenges are conducted. The experiments result show meFusion has the highest tolerance towards the noises, while compared with the existing handcrafted feature extraction method. A designed gender estimation framework that incorporates meFusion to realise the targeted advertising on DOOH media. A series of experiments that compare the designed framework with a pre-trained model from cloud services such as Google Cloud’s Vision API and Microsoft Azure Face. At the same time, a newly collected Malaysian face dataset in an uncontrolled environment, named Malaysian Ethnics Facial Database 2 (MEFD2), which consist of 2975 persons with a total of 13498 images, is applied in the experiments. 2021-01 Thesis http://shdl.mmu.edu.my/11423/ http://erep.mmu.edu.my/ masters Multimedia University Faculty of Engineering and Technology (FET) EREP ID: 9901
institution Multimedia University
collection MMU Institutional Repository
topic TA1501-1820 Applied optics
Photonics
spellingShingle TA1501-1820 Applied optics
Photonics
Loo, Eng Keong
Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment
description Recently in Malaysia, digital out-of-home (DOOH) advertising is getting common. It is a marketing tool to promote the branding of a product or service in the high population flow area. The existing DOOH advertising in Malaysia only broadcast the advertisement in a continuous and random manner without considering the presence of the audience. This causes the audience most likely to perceive some irrelevant advertisements. The recent advances of facial analysis unlock the potential of the DOOH media towards the targeted advertising manner. Therefore, the DOOH media is able to deliver a customised advertisement based on the facial attributes of the audience. However, the DOOH media is commonly operating in an uncontrolled environment. In such an environment, facial analysis faces two main challenges which are blurry faces and misaligned faces. These challenges are noises that increase the difficulty in feature extraction. In this thesis, meFusion, a handcrafted feature extraction method for gender estimation is proposed to handle the aforementioned challenges without going through the pre-processing stage. Bypassing the preprocessing stage is able to reduce the workload of DOOH media. A series of experiments that simulate the challenges are conducted. The experiments result show meFusion has the highest tolerance towards the noises, while compared with the existing handcrafted feature extraction method. A designed gender estimation framework that incorporates meFusion to realise the targeted advertising on DOOH media. A series of experiments that compare the designed framework with a pre-trained model from cloud services such as Google Cloud’s Vision API and Microsoft Azure Face. At the same time, a newly collected Malaysian face dataset in an uncontrolled environment, named Malaysian Ethnics Facial Database 2 (MEFD2), which consist of 2975 persons with a total of 13498 images, is applied in the experiments.
format Thesis
qualification_level Master's degree
author Loo, Eng Keong
author_facet Loo, Eng Keong
author_sort Loo, Eng Keong
title Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment
title_short Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment
title_full Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment
title_fullStr Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment
title_full_unstemmed Gender Analysis Using Simplified Local Binary Pattern Features Under Uncontrolled Environment
title_sort gender analysis using simplified local binary pattern features under uncontrolled environment
granting_institution Multimedia University
granting_department Faculty of Engineering and Technology (FET)
publishDate 2021
_version_ 1776101405056040960