Local deep feature learning framework for 3D shape

Bu, Shuhui; Han, Pengcheng; Liu, Zhenbao; Han, Junwei; Lin, Hongwei

doi:10.1016/j.cag.2014.09.007

Cited by 22 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: ) Performance Of Deep Learning Methods On 3d Data Descriptormentioning

confidence: 99%

“…GPU implementation was used in the extension of [154] by Bu et al in [155] which adopted a GPU based implementation for symmetry detection and correspondence tasks in which the proposed method showed improved performance. Inspired by the success of Heat kernel Signature (HKS) in obtaining low-level descriptors, Xie et al [155] utilized the HKS as a low-level descriptor at different scales and used auto-encoder to discriminate features from the HKS for 3D shape retrieval task. In [156], Han et al learn the discriminative features of 3D shapes from a Mesh Convolutional Restricted Boltzmann Machines(MCRBMs) in which Local Function Energy Distribution (LFED) was used to preserved the structure of the local features which leads to successful learning of the local and global features of 3D shapes.…”

Section: ) Performance Of Deep Learning Methods On 3d Data Descriptormentioning

confidence: 99%

See 1 more Smart Citation

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

et al. 2020

View full text Add to dashboard Cite

Deep learning approach has been used extensively in image analysis tasks. However, implementing the methods in 3D data is a bit complex because most of the previously designed deep learning architectures used 1D or 2D as input. In this work, the performance of deep learning methods on different 3D data representations has been reviewed. Based on the categorization of the different 3D data representations proposed in this paper, the importance of choosing a suitable 3D data representation which depends on simplicity, usability, and efficiency has been highlighted. Furthermore, the origin and contents of the major 3D datasets were discussed in detail. Due to growing interest in 3D object retrieval and classification tasks, the performance of different 3D object retrieval and classification on ModelNet40 dataset were compared. According to the findings in this work, multi views methods surpass voxel-based methods and with increased layers and enough data augmentation the performance can still be increased. Therefore, it can be concluded that deep learning together with a suitable 3D data representation gives an effective approach for improving the performance of 3D shape analysis. Finally, some possible directions for future researches were suggested.

show abstract

Section: ) Performance Of Deep Learning Methods On 3d Data Descriptormentioning

confidence: 99%

Section: ) Performance Of Deep Learning Methods On 3d Data Descriptormentioning

confidence: 99%

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Over the past several years, to overcome the disadvantages of those features, some methods [24]- [26]tend to simulate human vision mechanism. In recent researches, deep learning based methods [27]- [30] have become a hot topic in computer vision and have made great achievements. After the AlexNet [31] won the ILSVRC-2012 competition, CNNs [32] enhance the feature extraction performance of various computer vision tasks (object detection and tracking [32], [33], image classification [31], [32], and finegrained categorization [8]).…”

Section: B Deep-learning Based Detection Methodsmentioning

confidence: 99%

Object Detection in Aerial Images Using Feature Fusion Deep Networks

et al. 2019

Self Cite

View full text Add to dashboard Cite

Object detection acts as an essential part in a wide range of measurement systems in traffic management, urban planning, defense, agriculture, and so on. Convolutional Neural Networks-based researches reach a great improvement on detection tasks in natural scene images enjoying from the strong ability of feature representations. However, because of the high density, the small size of objects, and the intricate background, the current methods achieve relatively low precision in aerial images. The intention of this work is to obtain better detection performance in aerial images by designing a novel deep neural network framework called Feature Fusion Deep Networks (FFDN). The novel architecture combines a designed structural learning layer based on a graphical model. As a result, the network not only provides powerful hierarchical representation but also strengthens the spatial relationship between the high-density objects. We demonstrate the great improvement of the proposed FFDN on the UAV123 data set and another novel challenging data set called UAVDT benchmark. The objects which appear with small size, partial occlusion and out of view, as well as in the dark background can be detected accurately. INDEX TERMS Convolutional neural networks (CNNs), aerial images, feature fusion deep networks (FFDN), object detection.

show abstract

“…The most important that are worth mentioning include central symmetric LBP [16,19], improved local binary pattern (ILBP) [20], multi-scale block LBP [21,22], or Weber local descriptor (WLD) [23]. In addition, many papers describing linkages of local descriptors with different filters, like Gabor wavelets, have been published [6,24,25,26,27].The extensive research on application of local descriptors in pattern recognition is still ongoing, as evidenced by numerous new studies in this field, e.g., [28,29,30,31,32,33,34,35,36,37,38,39,40,41,42].Particularly, noteworthy is the recent trend of combining deep learning with local descriptors, see, for instance, [43,44,45]. Comprehensive survey study can be found in [7,46].…”

Section: Fig 1 Visualization Of the Concept Of The Lbpmentioning

confidence: 99%

An application of chain code-based local descriptor and its extension to face recognition

Karczmarek

Kiersztyn

Pedrycz

et al. 2017

Pattern Recognition

View full text Add to dashboard Cite

Local descriptors are widely used technique of feature extraction to obtain information about both local and global properties of an object. Here, we discuss an application of the Chain Code-Based Local Descriptor to face recognition by focusing on various datasets and considering different variants of this description method. We augment the generic form of the descriptor by adding a possibility of grouping pixels into blocks, i.e., effectively describing larger neighborhoods. The results of experiments show the efficiency of the approach. We demonstratethat the obtained results are comparable or even better than those delivered by other important algorithms in the class of methods based on the Bag-of-Visual-Words paradigm.

show abstract

Local deep feature learning framework for 3D shape

Cited by 22 publications

References 50 publications

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

Object Detection in Aerial Images Using Feature Fusion Deep Networks

An application of chain code-based local descriptor and its extension to face recognition

Contact Info

Product

Resources

About