Eye landmarks detection via weakly supervised learning

Huang, Bin; Chen, Renwen; Zhou, Qinghua; Wang, Xu

doi:10.1016/j.patcog.2019.107076

Cited by 20 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, for further neighbourhoods (such as N (5,10) , N (10,30) ), information available in these neighbours is not as uniform, determining a larger number of iterations to convergence, but with faster overall segmentation times (please refer to Table 9 for value). In the N (30,45) case, we can see a fast segmentation time along with small number of iterations to convergence, which is explained by the sparsity of label propagations from these neighbours. Similar computational performance patterns can be observed for the Synthetic and Berkeley datasets (Tables 7 and 8).…”

Section: Methodsmentioning

confidence: 99%

“…GrowCut 493.67 6.00 BBG-5 (2,5) 249.42 7.11 BBG-5 (5,10) 302.75 5.65 BBG-5 (10,30) 371.33 5.96 BBG-5 (30,45) 303.00 6.27 Table 8. Results for Berkeley dataset (average computational complexity metrics).…”

Section: Methods Iteration Count Segmentation Time (Seconds)mentioning

confidence: 99%

“…GrowCut 515.68 6.12 BBG-5 (2,5) 611.34 8.64 BBG-5 (5,10) 765.47 7.04 BBG-5 (10,30) 731.98 7.27 BBG-5 (30,45) 614.77 7.35…”

Section: Methods Iteration Count Segmentation Time (Seconds)mentioning

confidence: 99%

“…GrowCut 684.70 6.69 BBG-5 (2,5) 388.15 7.74 BBG-5 (5,10) 485.40 6.18 BBG-5 (10,30) 471.45 6.15 BBG-5 (30,45) 381.45 6.31 In this experiment we investigated the presence of a butterfly effect by assessing whether by changing the initial conditions of the system (i.e., the neighbourhood) we can determine a change in image segmentation properties. In other words, we were interested in whether the small change in neighbourhood system can propagate to the high-level output semantics.…”

Section: Methods Iteration Count Segmentation Time (Seconds)mentioning

confidence: 99%

“…While GrowCut has been extended in various directions, its classical version is still being successfully applied to image segmentation tasks, especially in the medical field, either as the main segmentation method [ 27 , 28 ] or as part of a larger pipeline [ 26 , 29 , 30 ]. This is the case since, as a segmentation algorithm, GrowCut provides several desireable qualities such as interactivity, small fine-tuning overhead, and relatively clear segmentation semantics.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

See 4 more Smart Citations

Butterfly Effect in Chaotic Image Segmentation

Marginean

Andreica

Dioşan

et al. 2020

Entropy

View full text Add to dashboard Cite

The exploitation of the important features exhibited by the complex systems found in the surrounding natural and artificial space will improve computational model performance. Therefore, the purpose of the current paper is to use cellular automata as a tool simulating complexity, able to bring forth an interesting global behaviour based only on simple, local interactions. We show that, in the context of image segmentation, a butterfly effect arises when we perturb the neighbourhood system of a cellular automaton. Specifically, we enhance a classical GrowCut cellular automaton with chaotic features, which are also able to improve its performance (e.g., a Dice coefficient of 71% in case of 2D images). This enhanced GrowCut flavor (referred to as Band-Based GrowCut) uses an extended, stochastic neighbourhood, in which randomly-selected remote neighbours reinforce the standard local ones. We demonstrate the presence of the butterfly effect and an increase in segmentation performance by numerical experiments performed on synthetic and natural images. Thus, our results suggest that, by having small changes in the initial conditions of the performed task, we can induce major changes in the final outcome of the segmentation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methods Iteration Count Segmentation Time (Seconds)mentioning

confidence: 99%

“…GrowCut 515.68 6.12 BBG-5 (2,5) 611.34 8.64 BBG-5 (5,10) 765.47 7.04 BBG-5 (10,30) 731.98 7.27 BBG-5 (30,45) 614.77 7.35…”

Section: Methods Iteration Count Segmentation Time (Seconds)mentioning

confidence: 99%

Section: Methods Iteration Count Segmentation Time (Seconds)mentioning

confidence: 99%

Section: Theoretical Backgroundmentioning

confidence: 99%

See 3 more Smart Citations

Butterfly Effect in Chaotic Image Segmentation

Marginean

Andreica

Dioşan

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

Deep Belief Neural Networks for Eye Localization Based Speeded up Robust Features and Local Binary Pattern

Shams

Hassanien

Tang

2022

Lecture Notes in Operations Research

View full text Add to dashboard Cite

Classification of Eye Tracking Data in Visual Information Processing Tasks Using Convolutional Neural Networks and Feature Engineering

et al. 2021

View full text Add to dashboard Cite

Eye tracking technology has been adopted in numerous studies in the field of human-computer interaction (HCI) to understand visual and display-based information processing as well as the underlying cognitive processes employed by users when navigating a computer interface. Analyzing eye tracking data can also help identify interaction patterns with regard to salient regions of an information display. Deep learning technology is increasingly being used in the analysis of eye tracking data by allowing for the classification of large amounts of eye tracking results. In this paper, eye tracking data and convolutional neural networks (CNNs) were used to perform a classification task to predict three types of information presentation methods. As a first step, a number of data preprocessing and feature engineering approaches were applied to eye tracking data collected through a controlled visual information processing experiment. The resulting data were used as input for the comparison of four CNN models with different architectures. In this experiment, two CNN models were effective in classifying the information presentations with overall accuracy greater than 80%.

show abstract

Eye landmarks detection via weakly supervised learning

Cited by 20 publications

References 18 publications

Butterfly Effect in Chaotic Image Segmentation

Butterfly Effect in Chaotic Image Segmentation

Deep Belief Neural Networks for Eye Localization Based Speeded up Robust Features and Local Binary Pattern

Classification of Eye Tracking Data in Visual Information Processing Tasks Using Convolutional Neural Networks and Feature Engineering

Contact Info

Product

Resources

About