Super resolution and recognition of long range captured multi‐frame iris images

Abstract

In this study, a framework to super resolve and recognise the long range captured iris polar images is proposed. The proposed framework consists of best frame selection algorithm, modified diamond search algorithm, Gaussian process regression (GPR) based and enhanced iterated back projection (EIBP)-based super-resolution approach, fuzzy entropy-based feature selector and neural network (NN) classifier. The framework uses linear kernel co-variance function in local patch-based GPR and EIBP algorithms and it super resolves the iris images depending on the contents of the patches, without an external dataset. NN classifier classifies the iris images by using features extracted using discrete cosine transform domain based noreference image quality assessment model, Gray level co-occurrence matrix, Hu seven moments and statistical features. The framework is tested using CASIA long range iris database by comparing and analysing the peak signal-to-noise ratio, structural similarity index matrix and visual information fidelity in pixel domain of proposed algorithms with Yang and Nguyen framework. The results demonstrate that the proposed framework is well suited for recognition of iris images captured at a long distance.

A Survey of Super-Resolution in Iris Biometrics With Evaluation of Dictionary-Learning

“…The CASIA Long Range database has also been used in a number of studies [35], [36]. Deshpande and Patavardhan [35] employed Gaussian Process Regression (GPR) and Enhanced Iterated Back Projection (EIBP) to super-resolve iris images. The best frame was selected as reference for alignment purposes by using the Discrete Cosine Transform.…”

“…The GPR is a time consuming process, therefore patches with less amount of information (measured by their variance of intensity) are processed with the faster EIBP algorithm. Performance was evaluated in [35] by downsampling iris images, and then super-resolving them. The authors reported several image fidelity measures in the pixel domain between original high-quality images and reconstructed images.…”

Super-resolution for Selfie Biometrics: Introduction and Application to Face and Iris

“…Other studies have proposed to incorporate quality measures [57,59,63,35], so more weight is given to frames with higher quality [28]. Recent reconstruction-based studies have proposed the use of Gaussian Process Regression (GPR), Enhanced Iterated Back Projection (EIBP) [17], and Total Variation regularization algorithms [16] to super-resolve polar frames.…”

Iris super‐resolution using CNNs: is photo‐realism important to iris recognition?

“…In [18], Nguyen et al introduce a signal-level fusion to integrate quality scores to the reconstructionbased SR process performing a quality weighted SR for a LR video sequence of a less constrained iris at a distance or on the move obtaining good results. However, in this case, as in [19] that perform the best frame selection, many LR images are required to reconstruct the HR image which is one of the disadvantages of this kind of reconstruction-based methods.…”