Dynamic Texture Recognition Using Volume Local Binary Count Patterns With an Application to 2D Face Spoofing Detection

Zhao, Xiangmo; Lin, Yaping; Heikkilä, Janne

doi:10.1109/tmm.2017.2750415

Cited by 98 publications

(67 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More specifically, our best result of recognition rate on this scheme is 95.69% (see Table 2), nearly same DDLBP with MJMI [33] (95.8%), the highest rate of recognition on this scheme using SVM classifier. With 92.87% using 1-NN, our descriptor outperforms DNGP [5] and CVLBC [21] over 2% and 1% respectively in the meanwhile it is not better than other LBP-based methods. This may be because DT sequences in DynTex++ dataset, which includes sub-videos split from the original DynTex dataset, comprise lack of directional trajectories (see Fig.…”

Section: Resultsmentioning

confidence: 86%

See 1 more Smart Citation

Directional Beams of Dense Trajectories for Dynamic Texture Recognition

Nguyen

Nguyễn

Bouchara

et al. 2018

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

Abstract. An effective framework for dynamic texture recognition is introduced by exploiting local features and chaotic motions along beams of dense trajectories in which their motion points are encoded by using a new operator, named LVP f ull -TOP, based on local vector patterns (LVP) in full-direction on three orthogonal planes. Furthermore, we also exploit motion information from dense trajectories to boost the discriminative power of the proposed descriptor. Experiments on various benchmarks validate the interest of our approach.

show abstract

Section: Resultsmentioning

confidence: 86%

“…An another variant, called LBP-TOP [13], has been also presented to overcome the curse of dimensionality of VLBP by addressing LBP on three orthogonal planes. Various extensions based on two above works have been then proposed to advance the discriminative power: CVLBC [21], CVLBP [15], CLSP-TOP [14], HLBP [16].…”

Section: Related Workmentioning

confidence: 99%

Directional Beams of Dense Trajectories for Dynamic Texture Recognition

Nguyen

Nguyễn

Bouchara

et al. 2018

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

show abstract

“…9-class: In this scheme, MMDP D M with rate of 98.90% is the best performance compared to other MDP descriptors. In the meanwhile, accuracies of MMDP D M C and MMDP D M/C are 98.35% and 98.70%, slightly lower rates of 99.20%, 99.35%, and 99.60% which are reported by CVLBC [63], FD-MAP [14], and DNGP [15] respectively. However, CVLBC and FD-MAP is not better than ours on other scenarios (except 8-class) of UCLA dataset, while DNGP has a complex representation.…”

Section: Recognition On Ucla Datasetmentioning

confidence: 82%

Momental directional patterns for dynamic texture recognition

Nguyen

Bouchara

Nguyen

2020

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Understanding the chaotic motions of dynamic textures (DTs) is a challenging problem of video representation for different tasks in computer vision. This paper presents a new approach for an efficient DT representation by addressing the following novel concepts. First, a model of moment volumes is introduced as an effective pre-processing technique for enriching the robust and discriminative information of dynamic voxels with low computational cost. Second, two important extensions of Local Derivative Pattern operator are proposed to improve its performance in capturing directional features. Third, we present a new framework, called Momental Directional Patterns, taking into account the advantages of filtering and local-feature-based approaches to form effective DT descriptors. Furthermore, motivated 1 by convolutional neural networks, the proposed framework is boosted by utilizing more global features extracted from max-pooling videos to improve the discrimination power of the descriptors. Our proposal is verified on benchmark datasets, i.e., UCLA, DynTex, and DynTex++, for DT classification issue. The experimental results substantiate the interest of our method.

show abstract

“…In contrast, as Table 3 shows, for the KTH-TIPS-2a database, Table 4. For consistency, we set parameter pair (L, s) for the Brodatz database as (15,3) and for the KTH-TIPS-2a database as (13,2), which correspond to the best classification performance in Tables 2 Table 4, we notice that the classification accuracy of two datasets keeps growing with the increase of K. Although K with a value larger than 128 may correspond to higher classification accuracy, for computational efficiency, we set K as 128 for all experiments unless mentioned otherwise.…”

Section: Patch and Block Sizesmentioning

confidence: 99%

“…Texture can be broadly defined as a type of visual features that characterize the surface of an object or a material. Distinctive and robust representation of texture is the key for various multimedia applications such as image representation [1], texture retrieval [2], face recognition [3], image quality assessment [4,5], image/texture segmentation [6], dynamic texture/scene recognition [7,3], texture/color style transfer [8], and seismic interpretation [9]. Texture descriptors [10,11,12,13,14,15,16], which are robust against rotations and translations of images, are able to provide discriminative features.…”

Section: Introductionmentioning

confidence: 99%