Data segmentation for geometric feature extraction from lidar point clouds

To achieve human face identification, this paper adopts the method of geometric feature extraction and the enlargement of image interpolation on the basis of the completion of face detection. First of all, the input digital image will be normalized to reduce the complexity of the image, and then the feature of human face will be extract. With the feature information extracted, we can construct the feature vector and assign different weights to different feature vector. Weight is interpreted as the EXP obtained after a large amount of training experience is gained. Finally, to get the similarity of picture, the bilinear interpolation method is adopted on the basis of the nearest interpolation. Thus, we will get the results of face identification according to the similarity quality. Through the development and implementation of practical programming, this paper proves the feasibility of such method.

Download Full-text

Geometric Feature Extraction by a Multimarked Point Process

IEEE Transactions on Pattern Analysis and Machine Intelligence ◽

10.1109/tpami.2009.152 ◽

2010 ◽

Vol 32 (9) ◽

pp. 1597-1609 ◽

Cited By ~ 53

Author(s):

Florent Lafarge ◽

Georgy Gimel'farb ◽

Xavier Descombes

Keyword(s):

Feature Extraction ◽

Point Process ◽

Geometric Feature ◽

Geometric Feature Extraction

Download Full-text

A novel geometric feature extraction method for ear recognition

Expert Systems with Applications ◽

10.1016/j.eswa.2016.08.035 ◽

2016 ◽

Vol 65 ◽

pp. 127-135 ◽

Cited By ~ 27

Author(s):

Ibrahim Omara ◽

Feng Li ◽

Hongzhi Zhang ◽

Wangmeng Zuo

Keyword(s):

Feature Extraction ◽

Extraction Method ◽

Geometric Feature ◽

Feature Extraction Method ◽

Ear Recognition ◽

Geometric Feature Extraction

Download Full-text

DGANet: A Dilated Graph Attention-Based Network for Local Feature Extraction on 3D Point Clouds

Remote Sensing ◽

10.3390/rs13173484 ◽

2021 ◽

Vol 13 (17) ◽

pp. 3484

Author(s):

Jie Wan ◽

Zhong Xie ◽

Yongyang Xu ◽

Ziyin Zeng ◽

Ding Yuan ◽

...

Keyword(s):

Feature Extraction ◽

Long Range ◽

Point Clouds ◽

Feature Representation ◽

Learning Ability ◽

Geometric Feature ◽

Cloud Data ◽

Fine Grained ◽

3D Point Clouds ◽

Benchmark Datasets

Feature extraction on point clouds is an essential task when analyzing and processing point clouds of 3D scenes. However, there still remains a challenge to adequately exploit local fine-grained features on point cloud data due to its irregular and unordered structure in a 3D space. To alleviate this problem, a Dilated Graph Attention-based Network (DGANet) with a certain feature for learning ability is proposed. Specifically, we first build a local dilated graph-like region for each input point to establish the long-range spatial correlation towards its corresponding neighbors, which allows the proposed network to access a wider range of geometric information of local points with their long-range dependencies. Moreover, by integrating the dilated graph attention module (DGAM) implemented by a novel offset–attention mechanism, the proposed network promises to highlight the differing ability of each edge of the constructed local graph to uniquely learn the discrepancy feature of geometric attributes between the connected point pairs. Finally, all the learned edge attention features are further aggregated, allowing the most significant geometric feature representation of local regions by the graph–attention pooling to fully extract local detailed features for each point. The validation experiments using two challenging benchmark datasets demonstrate the effectiveness and powerful generation ability of our proposed DGANet in both 3D object classification and segmentation tasks.

Download Full-text