Published on Sun Sep 22 2013

Generic Image Classification Approaches Excel on Face Recognition

Fumin Shen, Chunhua Shen

The standard image classification pipeline outperforms all state-of-the-art face recognition methods. The choice of dictionary learning methods may not be important. Learning multiple dictionaries using different low-level image features often improve the final classification accuracy.

0
0
0
Abstract

The main finding of this work is that the standard image classification pipeline, which consists of dictionary learning, feature encoding, spatial pyramid pooling and linear classification, outperforms all state-of-the-art face recognition methods on the tested benchmark datasets (we have tested on AR, Extended Yale B, the challenging FERET, and LFW-a datasets). This surprising and prominent result suggests that those advances in generic image classification can be directly applied to improve face recognition systems. In other words, face recognition may not need to be viewed as a separate object classification problem. While recently a large body of residual based face recognition methods focus on developing complex dictionary learning algorithms, in this work we show that a dictionary of randomly extracted patches (even from non-face images) can achieve very promising results using the image classification pipeline. That means, the choice of dictionary learning methods may not be important. Instead, we find that learning multiple dictionaries using different low-level image features often improve the final classification accuracy. Our proposed face recognition approach offers the best reported results on the widely-used face recognition benchmark datasets. In particular, on the challenging FERET and LFW-a datasets, we improve the best reported accuracies in the literature by about 20% and 30% respectively.

Mon Apr 14 2014
Neural Networks
PCANet: A Simple Deep Learning Baseline for Image Classification?
In this work, we propose a very simple deep learning network for image classification. It comprises only the very basic data processing components: PCA, binary hashing, and block-wise histograms. This architecture is thus named as a PCA network (PCANet) and can be designed and learned extremely easily and efficiently.
0
0
0
Tue Jan 10 2017
Computer Vision
Efficient Image Set Classification using Linear Regression based Image Reconstruction
We propose a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high-dimensional space to avoid the computationally expensive training step. Images of the test set are then reconstructed using the regression models.
0
0
0
Mon Jul 10 2017
Computer Vision
Synthesis-based Robust Low Resolution Face Recognition
Recognition of low resolution face images is a challenging problem. We propose a dictionary learning approach for classifying the low-resolution probe image. It is shown that our method is efficient and can perform significantly better than many competitive face recognition algorithms.
0
0
0
Thu Dec 13 2018
Computer Vision
Deep Face Image Retrieval: a Comparative Study with Dictionary Learning
Facial image retrieval is a challenging task since faces have many similar areas. With the advent of deep learning, deep networks are often applied to extract powerful features. This paper investigates the application of different deep learning models for face image retrieval.
0
0
0
Mon Sep 12 2011
Machine Learning
A Probabilistic Framework for Discriminative Dictionary Learning
In this paper, we address the problem of discriminative dictionary learning. We show that DDL can be solved by a sequence of updates that make use of well-known sparse coding and dictionary learning algorithms from the literature.
0
0
0
Wed Jul 08 2015
Computer Vision
DCTNet : A Simple Learning-free Approach for Face Recognition
PCANet was proposed as a lightweight deep learning network. It mainlyverages Principal Component Analysis (PCA) to learn multistage filter banks. DCTNet is free from learning as 2D DCT bases can be computed in advance.
0
0
0