Rasem Alashkar, Mohamed ElSabbahy, Ahmad Sabha, Momen Abdelghany, B. Tlili, Jinane Mounsef
{"title":"AI-Vision Towards an Improved Social Inclusion","authors":"Rasem Alashkar, Mohamed ElSabbahy, Ahmad Sabha, Momen Abdelghany, B. Tlili, Jinane Mounsef","doi":"10.1109/AI4G50087.2020.9311049","DOIUrl":null,"url":null,"abstract":"The promise of Artificial Intelligence (AI)-based technologies is immense, and benefits range from efficiency profits to unprecedented improvements of quality of life in a social exclusive world, where discrimination and marginalization pose significant difficulties for building inclusive cities and providing equal access to opportunities for disabled persons. The challenges faced by visually impaired individuals in today's world are too many to count. While many tools have been introduced to help address these problems, these tools remain very costly to afford. The proposed smart glasses AI-Vision, which aim to provide the needed support in daily routine tasks utilizes machine learning algorithms in two applications of great interest. A facial expression/age/gender recognition for meetings, and a color recognition for outfit sorting are integrated in the device's framework. The generated feedback sound can be heard by the user through the bone conduction technology while avoiding disturbance of surrounding noise. The proposed AI-Vision reduces substantially the cost of a similar product while keeping an efficient recognition accuracy.","PeriodicalId":286271,"journal":{"name":"2020 IEEE / ITU International Conference on Artificial Intelligence for Good (AI4G)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE / ITU International Conference on Artificial Intelligence for Good (AI4G)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AI4G50087.2020.9311049","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
The promise of Artificial Intelligence (AI)-based technologies is immense, and benefits range from efficiency profits to unprecedented improvements of quality of life in a social exclusive world, where discrimination and marginalization pose significant difficulties for building inclusive cities and providing equal access to opportunities for disabled persons. The challenges faced by visually impaired individuals in today's world are too many to count. While many tools have been introduced to help address these problems, these tools remain very costly to afford. The proposed smart glasses AI-Vision, which aim to provide the needed support in daily routine tasks utilizes machine learning algorithms in two applications of great interest. A facial expression/age/gender recognition for meetings, and a color recognition for outfit sorting are integrated in the device's framework. The generated feedback sound can be heard by the user through the bone conduction technology while avoiding disturbance of surrounding noise. The proposed AI-Vision reduces substantially the cost of a similar product while keeping an efficient recognition accuracy.