3D object retrieval with stacked local convolutional autoencoder

Leng, Biao; Guo, Shuxu; Zhang, Xiangyang; Zhang, Xiong

doi:10.1016/j.sigpro.2014.09.005

Cited by 83 publications

(39 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method was tested on two benchmark datasets demonstrating that the proposed method was more efficient at three-dimensional shape retrieval than other global features based methods. In another similar work [19], a stacked local convolutional autoencoder was used for…”

Section: Recent Relevant Workmentioning

confidence: 99%

Infant asphyxia detection using autoencoders trained on locally linear embedded-reduced Mel Frequency Cepstrum Coefficient (MFCC) features

Yassin

Zabidi

Ismail

et al. 2018

J. Fundam and Appl Sci.

View full text Add to dashboard Cite

Deep-learning methods are representation, obtained by composing simple but non representation at one level (starting with the raw input) into a representation at a higher, slightly more abstract level. With the composition of enough such transformations, very complex functions can be learned and solved. The objective of this paper is to explore one of the Deep Learning paradigms called autoencoders to perform diagnosis of infant asphyxia.LLE was used to reduce size of feature representation while enhancing them. Two stacked autoencoders were then trained to extract the necessary features for clasification. Extensive tests performed showed that the best classification accuracy.

show abstract

Section: Recent Relevant Workmentioning

confidence: 99%

Infant asphyxia detection using autoencoders trained on locally linear embedded-reduced Mel Frequency Cepstrum Coefficient (MFCC) features

Yassin

Zabidi

Ismail

et al. 2018

J. Fundam and Appl Sci.

View full text Add to dashboard Cite

show abstract

“…The CNN-models are optimized using an error-gradient algorithm [31]. CNNs are widely used in image classification [32] speech-processing tasks [33] and various other applications [34][35][36]. Feature learning through CNNs have several advantages over other deep-architectures.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

Shaheryar¹,

Yin²,

Ramay³

2017

IJCA

View full text Add to dashboard Cite

Mechanical failures in rotating machinery (e.g. wind turbines, generators, motor-derives etc.) may result in catastrophic failures. Different mechanical faults induce characteristic vibrations in the equipment structure. Online vibration monitoring helps mitigate catastrophic failures through early detection and identification of underlying mechanical faults. However, extracting characteristic vibration features that improve fault classification performance and are robust to various noises in the vibration signals is a challenging task. Various statistical and signal processing-based vibrationfeatures have been proposed in the literature. These vibrationfeatures were devised on the basis of prior knowledge about characteristics of vibration signals from different fault types. Recently, automatic feature extraction through unsupervised learning in deep neural architectures has resulted in state of art performance on image and speech recognition tasks. So, Instead of feature-engineering, we, here, hypothesized that feature learning on raw vibration signal possibly will extract vibration-features that can improve fault identification performance of subsequent classifier. To the purpose, we explored Convolutional Neural Network for unsupervised feature learning on vibration signals and Denoising AutoEncoder for extracting vibration features that are robust and invariant to the noises in vibration signals. We proposed a Hybrid deep-model consisting of a Multi-channel Convolutional Neural Network followed by a stack of Denoising Auto-Encoders (MCNN-SDAE) with a single classification layer at the top. We compared the fault identification and classification performance of the proposed model with other models employing tradition statistical and signal processing based vibration-features. We validated the performance of all models on a benchmark vibration data collected from an experimental test-rig specifically designed to study vibration characteristics of bearing related faults.

show abstract

“…Due to various characteristics of 3D objects, diverse descriptors are invented to capture different features [3,8,13,14,22,[30][31][32]57]. We can generally divide these feature descriptors into two groups, which are model-based and view-based representations.…”

Section: Related Workmentioning

confidence: 99%

3D Object retrieval based on viewpoint segmentation

Leng

Guo

et al. 2015

Multimedia Systems

Self Cite

View full text Add to dashboard Cite

© Springer-Verlag Berlin Heidelberg 2015 including computer vision, pattern recognition, and computer-aided design, demonstrating its vitality and importance. The initial attempts of this domain try to retrieve 3D models via textual annotations, which is however, hampered by two aspects. First, annotations may be incomplete and ambiguous due to the provider's language, culture, career habits, and other aspects. Second, the model features are difficult to describe in only a few words in most cases. Therefore, content-based 3D model retrieval becomes a reasonable solution, which concentrates on the model's low-level characteristics.Recently, a great number of algorithms have been proposed in the field of 3D object retrieval [9, 10, 12, 13, 15, 16, 23-28, 33-35, 68]. For the model-based methods, different features of 3D models are presented, including geometric moment [45], surface distribution [42], volumetric-based information [7], shape descriptors (e.g., Zernike moments [20] and Fourier descriptors [58]). However, expensive computation of obtaining the features and unsatisfactory retrieval performance limit their applications. On the contrary, view-based methods overcome these disadvantages, and show their better retrieval performance than model-based ones. There are many existing view-based methods, such as lighting field descriptorLFD) [4], elevation descriptor (ED) [49], adaptive view clustering (AVC) [2], Panorama [44], compact multi-view descriptors (CMVD) [5], and camera constraint-free viewbased method (CCFV) [11]. LFD represents a 3D object using 20 views from the vertexes of a dodecahedron, and the features are Zernike moments and Fourier descriptors extracted from the views [4]. ED describes the altitude information of a 3D object by obtaining six elevations from the front, top, right, rear, bottom and left views [49].Later, AVC, CMVD and CCFV consider the similarities between different views and represent a 3D object by the Abstract In the last decades, extensive efforts have been dedicated to develop better 3D object retrieval methods. View-based methods have attracted a significant amount of attention, not only because of their state-of-the-art performance, but also they merely require some of a 3D object's 2D view images. However, most recent approaches only deal with the images' content difference without the discrepancy of view relative positions. In this paper, we propose a normal method for view segmentation, based on Markov random field (MRF) model, which consider not only the difference between the content of views but also the relative locations. Each view is obtained by projecting at certain viewpoints and angels, therefore, these locations can be applied to depict each view, with content of views. We use the MRF to implement view segmentation and choose the representative views. Finally, we present a framework based on the proposed view segmentation method for 3D object retrieval and the experimental results demonstrate that the proposed method can achieve better retrieval effectiveness t...

show abstract

3D object retrieval with stacked local convolutional autoencoder

Cited by 83 publications

References 52 publications

Infant asphyxia detection using autoencoders trained on locally linear embedded-reduced Mel Frequency Cepstrum Coefficient (MFCC) features

Infant asphyxia detection using autoencoders trained on locally linear embedded-reduced Mel Frequency Cepstrum Coefficient (MFCC) features

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

3D Object retrieval based on viewpoint segmentation

Contact Info

Product

Resources

About