Real-time accurate eye center localization for low-resolution grayscale images

Ahmed, Noha Younis

doi:10.1007/s11554-020-00955-2

Cited by 15 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because the method [ 18 ] increased the training data through the GAN and used two heterogeneous CNN models to detect fine location of pupils. It can be seen that the performance of the Bin method [ 27 ] or Ahmed method [ 28 ] is similar to that of the proposed method at

, but the accuracy is lower than the proposed method by 2.4–3.7% at

.…”

Section: Methodsmentioning

confidence: 88%

“…To demonstrate the superior pupil tracking performance of the proposed method, we conducted comparative experiments using the state-of-the-art methods mentioned in Section 2 . For evaluation with a wider range of studies, we first compared the performance with three major approaches such as traditional machine learning methods with hand-crafted features [ 12 , 13 , 14 ], cascading method with hand-crafted features [ 15 ], GAN-based method [ 17 ], CNN-based method [ 18 ], CNN with regression framework [ 27 ], and specular reflection method [ 28 ]. All results of the comparison methods are based on the accuracy from the corresponding papers.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Energy Efficient Pupil Tracking Based on Rule Distillation of Cascade Regression Forest

Kim

Jeong

2020

Sensors

View full text Add to dashboard Cite

As the demand for human-friendly computing increases, research on pupil tracking to facilitate human–machine interactions (HCIs) is being actively conducted. Several successful pupil tracking approaches have been developed using images and a deep neural network (DNN). However, common DNN-based methods not only require tremendous computing power and energy consumption for learning and prediction; they also have a demerit in that an interpretation is impossible because a black-box model with an unknown prediction process is applied. In this study, we propose a lightweight pupil tracking algorithm for on-device machine learning (ML) using a fast and accurate cascade deep regression forest (RF) instead of a DNN. Pupil estimation is applied in a coarse-to-fine manner in a layer-by-layer RF structure, and each RF is simplified using the proposed rule distillation algorithm for removing unimportant rules constituting the RF. The goal of the proposed algorithm is to produce a more transparent and adoptable model for application to on-device ML systems, while maintaining a precise pupil tracking performance. Our proposed method experimentally achieves an outstanding speed, a reduction in the number of parameters, and a better pupil tracking performance compared to several other state-of-the-art methods using only a CPU.

show abstract

, but the accuracy is lower than the proposed method by 2.4–3.7% at

.…”

Section: Methodsmentioning

confidence: 88%

Section: Methodsmentioning

confidence: 99%

Energy Efficient Pupil Tracking Based on Rule Distillation of Cascade Regression Forest

Kim

Jeong

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Table 5 shows the accuracy, recall, precision, and F1score of the obtained results in the testing phase. The comparison between the proposed DBNN and [12,20,21,24] using the applied BioID dataset is shown in Fig. 15.…”

Section: Resultsmentioning

confidence: 99%

“…Table 1 lists some of the intelligent techniques used for eye localization [18][19][20][21][22][23][24]. The authors used a Weighted Binarization Cascaded Convolutional Network (WBCCN) to localize the eye image with a minimum detection error rate of 0.66.…”

Section: Related Workmentioning

confidence: 99%

“…Choi et al [20] proposed an eye pupil localization approach using the BioID dataset, and they utilized a GAN network to generate the eye images with an average accuracy of 93.30%. Furthermore, Ahmed [21] presented an algorithm to detect the Center of the Eye (CoE) using the Eye Region of Interest (ERoI) based on BioID, and the accuracy achieved was 91.68%.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Eye Detection-Based Deep Belief Neural Networks and Speeded-Up Robust Feature Algorithm

Tarek¹,

Shohieb²,

Elhady³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

The ability to detect and localize the human eye is critical for use in security applications and human identification and verification systems. This is because eye recognition algorithms have multiple challenges, such as multi-pose variations, ocular parts, and illumination. Moreover, the modern security applications fail to detect facial expressions from eye images. In this paper, a Speeded-Up Roust Feature (SURF) Algorithm was utilized to localize the face images of the enrolled subjects. We highlighted on eye and pupil parts to be detected based on SURF, Hough Circle Transform (HCT), and Local Binary Pattern (LBP). Afterward, Deep Belief Neural Networks (DBNN) were used to classify the input features results from the SURF algorithm. We further determined the correctly and wrongly classified subjects using a confusion matrix with two class labels to classify people whose eye images are correctly detected. We apply Stochastic Gradient Descent (SGD) optimizer to address the overfitting problem, and the hyper-parameters are fine-tuned based on the applied DBNN. The accuracy of the proposed system is determined based on SURF, LBP, and DBNN classifier achieved 95.54% for the ORL dataset, 94.07% for the BioID, and 96.20% for the CASIA-V5 dataset. The proposed approach is more reliable and more advanced when compared with state-of-the-art algorithms.

show abstract

Attention-Aware Recognition of Activities of Daily Living Based on Eye Gaze Tracking

Madhusanka

Ramadass

Rajagopal

et al. 2022

Internet of Things for Human-Centered Design

View full text Add to dashboard Cite

Real-time accurate eye center localization for low-resolution grayscale images

Cited by 15 publications

References 44 publications

Energy Efficient Pupil Tracking Based on Rule Distillation of Cascade Regression Forest

Energy Efficient Pupil Tracking Based on Rule Distillation of Cascade Regression Forest

Eye Detection-Based Deep Belief Neural Networks and Speeded-Up Robust Feature Algorithm

Attention-Aware Recognition of Activities of Daily Living Based on Eye Gaze Tracking

Contact Info

Product

Resources

About