scholarly journals CNN-Based Pupil Center Detection for Wearable Gaze Estimation System

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Warapon Chinsatit ◽  
Takeshi Saitoh
Keyword(s):  
Medical Diagnosis ◽  
Good Accuracy ◽  
Detection Method ◽  
Input Image ◽  
Classification Model ◽  
Gaze Estimation ◽  
The Gaze ◽  
Pupil Center ◽  
Center Position ◽  
Estimation System

This paper presents a convolutional neural network- (CNN-) based pupil center detection method for a wearable gaze estimation system using infrared eye images. Potentially, the pupil center position of a user’s eye can be used in various applications, such as human-computer interaction, medical diagnosis, and psychological studies. However, users tend to blink frequently; thus, estimating gaze direction is difficult. The proposed method uses two CNN models. The first CNN model is used to classify the eye state and the second is used to estimate the pupil center position. The classification model filters images with closed eyes and terminates the gaze estimation process when the input image shows a closed eye. In addition, this paper presents a process to create an eye image dataset using a wearable camera. This dataset, which was used to evaluate the proposed method, has approximately 20,000 images and a wide variation of eye states. We evaluated the proposed method from various perspectives. The result shows that the proposed method obtained good accuracy and has the potential for application in wearable device-based gaze estimation.

scholarly journals A New Gaze Estimation Method Based on Homography Transformation Derived from Geometric Relationship

2020 ◽  
Vol 10 (24) ◽  
pp. 9079
Author(s):  
Kaiqing Luo ◽  
Xuan Jia ◽  
Hua Xiao ◽  
Dongmei Liu ◽  
Li Peng ◽  
...  
Keyword(s):  
Estimation Method ◽  
Gaze Estimation ◽  
Estimation Model ◽  
Experimental Accuracy ◽  
Unknown Parameters ◽  
The Gaze ◽  
Marquardt Algorithm ◽  
Mapping Equation ◽  
Estimation System ◽  
Homography Transformation

In recent years, the gaze estimation system, as a new type of human-computer interaction technology, has received extensive attention. The gaze estimation model is one of the main research contents of the system. The quality of the model will directly affect the accuracy of the entire gaze estimation system. To achieve higher accuracy even with simple devices, this paper proposes an improved mapping equation model based on homography transformation. In the process of experiment, the model mainly uses the “Zhang Zhengyou calibration method” to obtain the internal and external parameters of the camera to correct the distortion of the camera, and uses the LM(Levenberg-Marquardt) algorithm to solve the unknown parameters contained in the mapping equation. After all the parameters of the equation are determined, the gaze point is calculated. Different comparative experiments are designed to verify the experimental accuracy and fitting effect of this mapping equation. The results show that the method can achieve high experimental accuracy, and the basic accuracy is kept within 0.6∘. The overall trend shows that the mapping method based on homography transformation has higher experimental accuracy, better fitting effect and stronger stability.

scholarly journals POnline: An Online Pupil Annotation Tool Employing Crowd-sourcing and Engagement Mechanisms

2019 ◽  
Vol 6 ◽  
pp. 176-191
Author(s):  
David Gil de Gómez Pérez ◽  
Roman Bednarik
Keyword(s):  
State Of The Art ◽  
Gaze Estimation ◽  
Annotation Tool ◽  
Crowd Sourcing ◽  
Data Set ◽  
Gaze Tracking ◽  
Estimation Algorithms ◽  
The Gaze ◽  
Pupil Center ◽  
Pupil Detection

Pupil center and pupil contour are two of the most important features in the eye-image used for video-based eye-tracking. Well annotated databases are needed in order to allow benchmarking of the available- and new pupil detection and gaze estimation algorithms. Unfortunately, creation of such a data set is costly and requires a lot of efforts, including manual work of the annotators. In addition, reliability of manual annotations is hard to establish with a low number of annotators. In order to facilitate progress of the gaze tracking algorithm research, we created an online pupil annotation tool that engages many users to interact through gamification and allows utilization of the crowd power to create reliable annotations \cite{artstein2005bias}. We describe the tool and the mechanisms employed, and report results on the annotation of a publicly available data set. Finally, we demonstrate an example utilization of the new high-quality annotation on a comparison of two state-of-the-art pupil center algorithms.

Homography-Based Low-Cost Gaze Estimation and its Application to the Usability Assessment of Digital Prototypes of Information Appliances

2013 ◽  
Author(s):  
Satoshi Kanai ◽  
Hiroaki Date
Keyword(s):  
Low Cost ◽  
Test Session ◽  
Gaze Estimation ◽  
Ui Design ◽  
The Gaze ◽  
Usability Assessment ◽  
Simple Event ◽  
Information Appliances ◽  
Estimation System ◽  
Digital Prototype

Recently 3D digital prototypes of information appliances have been proposed for efficient user acceptance tests of user-interface (UI) usability. The purpose of this research is to develop a gaze estimation system based on Homography and to fully integrate it with a 3D digital prototype of the information appliances in order to obtain information more useful for usability assessment. The estimation system consists only of four infrared LEDs and a USB camera and is low-cost. The gaze estimation enables the system not only to record a gaze point on the prototype but to identify the UI objects which the user is looking for in real time during the test session. A gaze-based index was newly introduced to identify the misleading UI objects and to quantify the irrelevance of the UI design. A case study suggested that the integration of the gaze estimation with the 3D digital prototype and the proposed index were useful for automatically identifying which irrelevant UI objects misled the users’ operations which could not yet be captured in previous simple event logging of the user inputs.

scholarly journals CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines

2020 ◽  
Vol 34 (03) ◽  
pp. 2594-2601
Author(s):  
Arjun Akula ◽  
Shuai Wang ◽  
Song-Chun Zhu
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Input Image ◽  
Classification Model ◽  
Learning Models ◽  
Fault Line ◽  
Semantic Level ◽  
Explainable Ai ◽  
Fault Lines ◽  
Classification Category

We present CoCoX (short for Conceptual and Counterfactual Explanations), a model for explaining decisions made by a deep convolutional neural network (CNN). In Cognitive Psychology, the factors (or semantic-level features) that humans zoom in on when they imagine an alternative to a model prediction are often referred to as fault-lines. Motivated by this, our CoCoX model explains decisions made by a CNN using fault-lines. Specifically, given an input image I for which a CNN classification model M predicts class cpred, our fault-line based explanation identifies the minimal semantic-level features (e.g., stripes on zebra, pointed ears of dog), referred to as explainable concepts, that need to be added to or deleted from I in order to alter the classification category of I by M to another specified class calt. We argue that, due to the conceptual and counterfactual nature of fault-lines, our CoCoX explanations are practical and more natural for both expert and non-expert users to understand the internal workings of complex deep learning models. Extensive quantitative and qualitative experiments verify our hypotheses, showing that CoCoX significantly outperforms the state-of-the-art explainable AI models. Our implementation is available at https://github.com/arjunakula/CoCoX

scholarly journals Real-time gaze estimation via pupil center tracking

2018 ◽  
Vol 9 (1) ◽  
pp. 6-18 ◽  
Author(s):  
Dario Cazzato ◽  
Fabio Dominio ◽  
Roberto Manduchi ◽  
Silvia M. Castro
Keyword(s):  
Real Time ◽  
Learning Algorithm ◽  
Natural Environments ◽  
Gaze Estimation ◽  
Head Pose ◽  
Data Set ◽  
Gaze Tracking ◽  
Illumination Changes ◽  
Wide Range ◽  
Estimation System

Abstract Automatic gaze estimation not based on commercial and expensive eye tracking hardware solutions can enable several applications in the fields of human computer interaction (HCI) and human behavior analysis. It is therefore not surprising that several related techniques and methods have been investigated in recent years. However, very few camera-based systems proposed in the literature are both real-time and robust. In this work, we propose a real-time user-calibration-free gaze estimation system that does not need person-dependent calibration, can deal with illumination changes and head pose variations, and can work with a wide range of distances from the camera. Our solution is based on a 3-D appearance-based method that processes the images from a built-in laptop camera. Real-time performance is obtained by combining head pose information with geometrical eye features to train a machine learning algorithm. Our method has been validated on a data set of images of users in natural environments, and shows promising results. The possibility of a real-time implementation, combined with the good quality of gaze tracking, make this system suitable for various HCI applications.

Network Intrusion Detection Method Based on RS-LSSVM

2014 ◽  
Vol 602-605 ◽  
pp. 1634-1637
Author(s):  
Fang Nian Wang ◽  
Shen Shen Wang ◽  
Wan Fang Che ◽  
Yun Bai
Keyword(s):  
Intrusion Detection ◽  
Detection Method ◽  
Attribute Reduction ◽  
Feature Space ◽  
Least Square ◽  
Classification Model ◽  
Network Intrusion Detection ◽  
Support Vector ◽  
Network Intrusion ◽  
Sample Data

An intrusion detection method based on RS-LSSVM is studied in this paper. Firstly, attribute reduction algorithm based on the generalized decision table is proposed to remove the interference features and reduce the dimension of input feature space. Then the classification method based on least square support vector machine (LSSVM) is analyzed. The sample data after dimension reduction is used for LSSVM training, and the LSSVM classification model is obtained, which forms the ability of detecting unknown intrusion. Simulation results show that the proposed method can effectively remove the unnecessary features and improve the performance of network intrusion detection.

Sign in / Sign up

Export Citation Format

Share Document