Blur Insensitive Texture Classification Using Local Phase Quantization

By Ville Ojansivu, Janne Heikkilä. International Conference on Image and Signal Processing, 2008

1,074 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/dfe16796b869265e05b3d4cee17e28764164176c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Training deep networks for facial expression recognition with crowd-sourced label distribution (2016, background): “Early works rely on hand-crafted features such as Gabor Wavelets [34], Local Binary Patterns on Three Orthogonal Planes (LBP-TOP) [35], Pyramid Histogram of Oriented Gradients (PHOG) [20] and Local Quantized Patterns (LPQ) [5].”
Past, Present, and Future of Face Recognition: A Review (2020, methodology): “Ahonen et al. [91] (2008) used the newly introduced operator: local phase quantization (LPQ) [92] in recognition of blurred faces to solve the facial recognition issue under blurring situations.”
COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios (2020, neutral): “Proposed by Ojansivu and Heikkilä [54], LPQ was originally proposed aiming to provide a good texture description for noised images, affected by blur.”
A Micro-GA Embedded PSO Feature Selection Approach to Intelligent Facial Emotion Recognition (2017, background): “On the contrary, a larger window sometimes is not able to extract sufﬁcient discriminative information, therefore decreasing the performances for sharp images [16].”
Structured AutoEncoders for Subspace Clustering (2018, background): “• LPQ: We first divide each image into multiple nonoverlapping blocks and then extract the LPQ feature from each patch.”
Face liveness detection with component dependent descriptor (2013, methodology): “Meanwhile, different texture operators, including Local Phase Quantization (LPQ) [17], concatenated histogram of LBPs ( LBP u 2 8 , 1 , LBP u 2 8 , 2 , LBP u 2 16 , 2 ) and the one with block division [16] and Histogram of Gradient (HOG) [8] are performed for the H-Face images with all scales.”
BSIF: Binarized statistical image features (2012, methodology): “The baseline for the experiments is formed by Local Binary Patterns (LBP) [9], BIF-column (BIFc) [5], and Local Phase Quantization (LPQ) [10] methods.”
Handcrafted vs. non-handcrafted features for computer vision classification (2017, methodology): “[39] V. Ojansivu, J. Heikkila, Blur insensitive texture classification using local phase quantization, ICISP2008, pp. 236–243.”
Texture Feature Extraction Methods: A Survey (2019, methodology): “Moreover, Ojansivu and Heikkila [92] proposed a new descriptor for texture classification that is robust to image blurring.”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “…a pair of thresholds and a split coding scheme which allows for encoding pixel similarity; the Local Phase Quantization (LPQ) by Ojansivu et al. [164, 165] quantizing the Fourier transform phase in local neighborhoods which is, by design, tolerant to most common types of image blurs; the…”
Face Presentation Attack with Latex Masks in Multispectral Videos (2017, methodology): “This result accentuates the need for developing an accurate face Features VIS NIR Thermal HOG [6] 36.9 45.7 29.6 ULBP [15] 40.2 49.5 28.2 BSIF [11] 32.5 46.7 25.0 LPQ [16] 43.7 45.”
Local binary features for texture classification: Taxonomy and experimental study (2017, methodology): “We use the original source code if it is publicly available, and for the remainder we have developed our own implementation.”
AFIF4: Deep Gender Classification based on AdaBoost-based Fusion of Isolated Facial Features and Foggy Faces (2017, background): “They reported that local salient patterns (LSP) [13] and histogram of oriented gradients (HOG) [14] achieve the best accuracy using holistic visual features, while local phase quantization (LPQ) [15] with SVM attains the best accuracy using local visual features.”
Automatic Analysis of Facial Actions: A Survey (2019, methodology): “The LPQ descriptor [127] uses local phase information extracted using 2D short-term Fourier transform (STFT)”
Deep learning for decentralized parking lot occupancy detection (2017, methodology): “The authors specifically used LBP, LPQ features and their variations (Ojala et al., 2002; Ojansivu & Heikkilä, 2008; Rahtu et al., 2012) as input of the SVM. In325 their experiment, they show that there is no absolute best among those textural features for this task.”
PKLot - A robust dataset for parking lot classification (2015, background): “The Local Phase Quantization (LPQ) (Ojansivu & Heikkilä, 2008) is based on the blur invariance property of the Fourier phase spectrum.”
Face Spoofing Detection Using Colour Texture Analysis (2016, background): “3) Local Phase Quantization (LPQ): The LPQ descriptor [52] was proposed to deal with the blurred images.”
Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark (2011, background): “Our method for facial expression recognition is based on the local binary pattern (LBP) class of descriptors.”