An Automated Ear Localization Technique Based on Modified Hausdorff Distance

Sarangi, Partha Pratim; Panda, Madhumita; Mishra, Bhabani Shankar Prasad; Dehuri, Satchidananda

doi:10.1007/978-981-10-2107-7_21

Cited by 17 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of these weaknesses, HD becomes unusable in most practical scenarios that involve corrupted and incomplete data. To deal with these undesirable conditions, plus situations of rotations and translations that the classical HD ignores, scholars have attempted to modify the measure [35][36][37][38][39][40][41][42][43][44][45]. Our analysis on these methods realized that the issues of extreme noise and outlier conditions have been inadequately discussed.…”

Section: Motivations and Aimsmentioning

confidence: 99%

Hausdorff Distance with Outliers and Noise Resilience Capabilities

Maiseli

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

For years, the Hausdorff distance (HD) has been an indispensable tool to address computer vision and pattern recognition problems. Compared with other metrics, HD incorporates critical details of objects (position and shapes) to output reasonable distances between pairs of point sets. Despite its capabilities, HD is highly sensitive to outliers and noisy data. From previous studies, we discovered that the issues have been inadequately addressed. In the present work, a technique is proposed to empower HD under undesirable conditions of data. The technique uses diffusion-like stopping kernels that investigate regions of data and trim-off outliers and noise. We, additionally, have analyzed our formulation to show why it works. Extensive experimental results demonstrate the efficacy of our approach relative to previous methods.

show abstract

Section: Motivations and Aimsmentioning

confidence: 99%

Hausdorff Distance with Outliers and Noise Resilience Capabilities

Maiseli

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

show abstract

“…. , b m }, then the Hausdorff distance between sets A and B is as follow [36]- [38]. In this paper, • is the Euclidean distance between set A and set B.…”

Section: B Narrow Down the Search Range Of Closest Contour Pointmentioning

confidence: 99%

Gravity Aided Positioning Based on Real-Time ICCP With Optimized Matching Sequence Length

Liu

Lin

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The existing real-time iterative closest contour point (ICCP) algorithm uses fixed matching sequence length, which is set according to human experience and cannot obtain the best positioning accuracy on all tracks. This paper proposes a real-time ICCP algorithm with the optimized matching sequence length (OMSL-ICCP) based on the analysis of the shortcomings of the existing real-time ICCP. The optimal matching sequence length of OMSL-ICCP under the current measured gravity anomaly sequence is obtained by the golden section search. The Hausdorff distance is utilized to obtain the search range of the closest contour point, which can effectively shrink the search range of the closest contour point. And the gravitation field algorithm is applied to further improve the positioning accuracy. In simulation tests with different gravity sensor measurement noises, different INS positioning errors and different gravity map resolutions, the difference of positioning performance between the existing real-time ICCP and the OMSL-ICCP is compared. Under the same test conditions, the simulation results show that the positioning accuracy of OMSL-ICCP is higher than the positioning accuracy obtained by the existing real-time ICCP algorithm with the optimal sequence length.INDEX TERMS Gravity aided positioning, real-time ICCP, golden section search, gravitation field algorithm, Hausdorff distance.

show abstract

“…In this section, we summarize the different aspects of relevant published studies. Most automatic 2D ear detection approaches depend on the mutual morphological properties of the ear, for instance, the characteristic edges [12], model matching [13], and learning algorithms [14].…”

Section: Automatic 2d Ear Detectionmentioning

confidence: 99%

“…Several modeling matching-based detection methods have been published, e.g., shape-based localization [23], and a modified Hausdorff distance-based ear localization method [13].…”

Section: Automatic 2d Ear Detectionmentioning

confidence: 99%

Local and Holistic Feature Fusion for Occlusion-Robust 3D Ear Recognition

Zhu

Zhang

2018

Symmetry

View full text Add to dashboard Cite

Occlusion over ear surfaces results in performance degradation of ear registration and recognition systems. In this paper, we propose an occlusion-resistant three-dimensional (3D) ear recognition system consisting of four primary components: (1) an ear detection component, (2) a local feature extraction and matching component, (3) a holistic matching component, and (4) a decision-level fusion algorithm. The ear detection component is implemented based on faster region-based convolutional neural networks. In the local feature extraction and matching component, a symmetric space-centered 3D shape descriptor based on the surface patch histogram of indexed shapes (SPHIS) is used to generate a set of keypoints and a feature vector for each keypoint. Then, a two-step noncooperative game theory (NGT)-based method is proposed. The proposed symmetric game-based method is effectively applied to determine a set of keypoints that satisfy the rigid constraints from initial keypoint correspondences. In the holistic matching component, a proposed variant of breed surface voxelization is used to calculate the holistic registration error. Finally, the decision-level fusion algorithm is applied to generate the final match scores. Evaluation results from experiments conducted show that the proposed method produces competitive results for partial occlusion on a dataset consisting of natural and random occlusion.

show abstract

An Automated Ear Localization Technique Based on Modified Hausdorff Distance

Cited by 17 publications

References 14 publications

Hausdorff Distance with Outliers and Noise Resilience Capabilities

Hausdorff Distance with Outliers and Noise Resilience Capabilities

Gravity Aided Positioning Based on Real-Time ICCP With Optimized Matching Sequence Length

Local and Holistic Feature Fusion for Occlusion-Robust 3D Ear Recognition

Contact Info

Product

Resources

About