update draft based on WRP comments

contents/articles/2017-01_image_user_auth/index.md

@@ -3,19 +3,21 @@ title: Personalized Image-based User Authentication using Wearable Cameras
 date: Wed Jan 11 2017 11:18:18 GMT+0700 (ICT) 
 author: Pupil Dev Team 
 subtitle: "Ngu Nguyen et al., propose a novel personalized user authentication mechanism that generates an image-based passwords from egocentric videos captured by wearable cameras..."
-featured_img: "../../../../media/images/blog/.jpg"
-featured_img_thumb: "../../../../media/images/blog/.jpg"
+featured_img: "../../../../media/images/blog/user_auth.png"
+featured_img_thumb: "../../../../media/images/blog/user_auth.png"
 ---
 
-<img src="../../../../media/images/blog/.jpg" class='Feature-image' alt="">
+Personal devices are a part of our everyday life that operate and store users private data. Such devices face an array of threats that have become a primary concern for users. The existing authentication mechanism requires users to register and remember one static password for each device at a time. However static passwords are vulnerable to various methods of attacks. 
 
-<div class="small u-padBottom--2">Image Source: [Personalized Image-based User Authentication using Wearable Cameras](https://arxiv.org/pdf/1612.06209.pdf)</div>
+<img src="../../../../media/images/blog/user_auth.png" class='Feature-image' alt="Image-Based Authentication Challenges Generated From Egocentric Videos">
 
-Personal devices are a part of our everyday life that operate and store users private data. Such devices face an array of threats that have become a primary concern for users. The existing authentication mechanism requires users to register and remember one static password for each device at a time. However static passwords are vulnerable to various methods of attacks. 
+<div class="small u-padBottom--2">Image Source: [Personalized Image-based User Authentication using Wearable Cameras](https://arxiv.org/pdf/1612.06209.pdf)</div>
 
 [Ngu Nguyen](http://ambientintelligence.aalto.fi/team.html) et al., propose a novel personalized user authentication mechanism that generates an image-based passwords from egocentric videos captured by wearable cameras. 
 
-One of the process of generating authentication challenges uses the [Pupil headset](https://pupil-labs.com/store/#pupil) to capture egocentric videos and eye fixations to select key frames that are possible to discriminate. The frames are then split into segments and grouped to form fresh and personalized image-based user authentication mechanism. The image-based mechanisms are evaluated to be comparable to static approaches while decreasing security vulnerabilities.
+One of the process of generating authentication challenges uses Pupil Lab's [Pupil headset](https://pupil-labs.com/store/#pupil) to capture egocentric videos and gaze data. [Pupil eye tracker](https://pupil-labs.com/store/#pupil) was used to track eye fixations to reveal user's attention which are demonstrated to be useful in [video summarization](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Xu_Gaze-Enabled_Egocentric_Video_2015_CVPR_paper.pdf) to provide information of wearer's visual behavior.
+
+Whenever eye fixations appear in the timeline, frames that are possible to discriminate are then selected and split into segments and grouped to form fresh and personalized image-based user authentication mechanism. The image-based mechanisms are evaluated to be comparable to static approaches while decreasing security vulnerabilities.
 
 Check out the their full research paper [here](https://arxiv.org/pdf/1612.06209.pdf).