# Face recognition via compact second order image gradient orientations

arXiv: https://arxiv.org/abs/2201.09246 · HTML: https://mlsanity.com/paper/2201.09246/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 58 references that are in the map.
- First posted on arXiv 23 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models](https://mlsanity.com/paper/2007.00328/) (2020)
- [A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition](https://mlsanity.com/paper/1606.02894/) (2016)
- [Nuclear Norm based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes](https://mlsanity.com/paper/1405.1207/) (2014)
- [Multi-focus Image Fusion using dictionary learning and Low-Rank Representation](https://mlsanity.com/paper/1804.08355/) (2018)
- [Occluded Face Recognition Using Low-rank Regression with Generalized Gradient Direction](https://mlsanity.com/paper/1906.02429/) (2019)
- [Robust and Low-Rank Representation for Fast Face Identification with Occlusions](https://mlsanity.com/paper/1605.02266/) (2016)
- [Defect detection for patterned fabric images based on GHOG and low-rank decomposition](https://mlsanity.com/paper/1702.05555/) (2017)

## Built on by (most cited first, 1 of 1)

- [Hybrid second-order gradient histogram based global low-rank sparse regression for robust face recognition](https://mlsanity.com/paper/2511.05893/) (2025)

## Abstract (arXiv)

Conventional subspace learning approaches based on image gradient orientations only employ the first-order gradient information. However, recent researches on human vision system (HVS) uncover that the neural image is a landscape or a surface whose geometric properties can be captured through the second order gradient information. The second order image gradient orientations (SOIGO) can mitigate the adverse effect of noises in face images. To reduce the redundancy of SOIGO, we propose compact SOIGO (CSOIGO) by applying linear complex principal component analysis (PCA) in SOIGO. Combined with collaborative representation based classification (CRC) algorithm, the classification performance of CSOIGO is further enhanced. CSOIGO is evaluated under real-world disguise, synthesized occlusion and mixed variations. Experimental results indicate that the proposed method is superior to its competing approaches with few training samples, and even outperforms some prevailing deep neural network based approaches. The source code of CSOIGO is available at https://github.com/yinhefeng/SOIGO.