Lossless Compression of Polar Iris Image Data

Horvath, Kurt; Stögner, Herbert; Uhl, Andreas; Weinhandel, Georg

doi:10.1007/978-3-642-21257-4_41

Cited by 22 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• JPEG XR FuturixImager6 applied this most current ISO still image coding standard based on the Microsoft H.D. format [25]. Table 6 shows the C.R.…”

Section: Setting and Compression Methodsmentioning

confidence: 99%

Storage Space Reduction of Biometric Iris Databases by Successive Images Differences and Quadtree Decomposition

Hashim,

Jassim,

Hashim

2023

MMEP

View full text Add to dashboard Cite

In recent years, the rise of biometric applications, particularly those centered around iris-based systems, has been significant. High data volumes inherent in these applications and the potential vulnerability of network links necessitate data compression in certain instances. The advantage of lossless compression methods is twofold: they maintain recognition performance without degradation while necessitating fewer computations for differentiation compared to their lossy counterparts. This study proposes a novel approach for lossless/lossy compression of iris biometric sample data across various public iris databases. Initially, the differences between successive images within each class are calculated, leveraging the strong correlation of images within each class. Subsequently, these differences are compressed using quadtree decomposition. This methodology was tested on six renowned iris databases: CASIA V1, CASIA V3, MMU1, MMU2, and UBIRIS Iris, all of which contain 8-bit grayscale images. The results indicate that the proposed strategy offers superior compression performance across different iris databases in comparison to existing methods. Notably, the results suggest that this method can be effectively integrated into an iris biometric recognition system, providing efficient iris image compression, especially when applied in its lossless form.

show abstract

“…• JPEG XR FuturixImager6 applied this most current ISO still image coding standard based on the Microsoft H.D. format [25]. Table 6 shows the C.R.…”

Section: Setting and Compression Methodsmentioning

confidence: 99%

Storage Space Reduction of Biometric Iris Databases by Successive Images Differences and Quadtree Decomposition

Hashim,

Jassim,

Hashim

2023

MMEP

View full text Add to dashboard Cite

show abstract

“…Ives et al [ 6 ] investigated the effects of image compression on recognition system performance using a commercial version of the Daugman “iris2pi” algorithm along with JPEG-2000 compression, and linked that to image quality. Korvath et al [ 7 ] evaluated the impact of dedicated lossless image codecs (lossless JPEG, JPEG-LS, PNG, and GIF), lossless variants of lossy codecs (JPEG2000, JPEG XR, and SPIHT), and some general purpose file compression schemes on the iris images. Bergmüller et al [ 8 ] studied the impact of using pre-compressed data in iris segmentation and evaluated the relation between iris segmentation performance and general image quality metrics.…”

Section: Related Workmentioning

confidence: 99%

Iris Image Compression Using Deep Convolutional Neural Networks

Jalilian

Hofbauer

Uhl

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Compression is a way of encoding digital data so that it takes up less storage and requires less network bandwidth to be transmitted, which is currently an imperative need for iris recognition systems due to the large amounts of data involved, while deep neural networks trained as image auto-encoders have recently emerged a promising direction for advancing the state-of-the-art in image compression, yet the generalizability of these schemes to preserve the unique biometric traits has been questioned when utilized in the corresponding recognition systems. For the first time, we thoroughly investigate the compression effectiveness of DSSLIC, a deep-learning-based image compression model specifically well suited for iris data compression, along with an additional deep-learning based lossy image compression technique. In particular, we relate Full-Reference image quality as measured in terms of Multi-scale Structural Similarity Index (MS-SSIM) and Local Feature Based Visual Security (LFBVS), as well as No-Reference images quality as measured in terms of the Blind Reference-less Image Spatial Quality Evaluator (BRISQUE), to the recognition scores as obtained by a set of concrete recognition systems. We further compare the DSSLIC model performance against several state-of-the-art (non-learning-based) lossy image compression techniques including: the ISO standard JPEG2000, JPEG, H.265 derivate BPG, HEVC, VCC, and AV1 to figure out the most suited compression algorithm which can be used for this purpose. The experimental results show superior compression and promising recognition performance of the model over all other techniques on different iris databases.

show abstract