Face recognition in low-quality images using adaptive sparse representations

• Published in: Image and vision computing Vol. 85; pp. 46 - 58
• Main Authors: Heinsohn, Daniel, Villalobos, Esteban, Prieto, Loreto, Mery, Domingo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.05.2019
• Subjects: Deep learning; Face recognition; Low-quality images; Low-resolution; Sparse representations; Superresolution; Deep learning; Low-quality images; Sparse representations; Face recognition; Superresolution; Low-resolution
• ISSN: 0262-8856; 1872-8138
• DOI: 10.1016/j.imavis.2019.02.012

Although unconstrained face recognition has been widely studied over the recent years, state-of-the-art algorithms still result in an unsatisfactory performance for low-quality images. In this paper, we make two contributions to this field: the first one is the release of a new dataset called ‘AR-LQ’ that can be used in conjunction with the well-known ‘AR’ dataset to evaluate face recognition algorithms on blurred and low-resolution face images. The proposed dataset contains five new blurred faces (at five different levels, from low to severe blurriness) and five new low-resolution images (at five different levels, from 66 × 48 to 7 × 5 pixels) for each of the hundred subjects of the ‘AR’ dataset. The new blurred images were acquired by using a DLSR camera with manual focus that takes an out-of-focus photograph of a monitor that displays a sharp face image. In the same way, the low-resolution images were acquired from the monitor by a DLSR at different distances. Thus, an attempt is made to acquire low-quality images that have been degraded by a real degradation process. Our second contribution is an extension of a known face recognition technique based on sparse representations (ASR) that takes into account low-resolution face images. The proposed method, called blur-ASR or bASR, was designed to recognize faces using dictionaries with different levels of blurriness. These were obtained by digitally blurring the training images, and a sharpness metric for matching blurriness between the query image and the dictionaries. These two main adjustments made the algorithm more robust with respect to low-quality images. In our experiments, bASR consistently outperforms other state-of-the-art methods including hand-crafted features, sparse representations, and seven well-known deep learning face recognition techniques with and without super resolution techniques. On average, bASR obtained 88.8% of accuracy, whereas the rest obtained less than 78.4%. •New method based on sparse representations for face recognition in low-quality images.•Release of AR-LQ, a dataset with blurred images (AR-blur) and low-resolution images (AR-LR) acquired using a realistic method with a DLSR camera.•Experiments on blurred images.•Experiments on low-resolution images.•Discussion of the results in greater detail.