Reinforced Palmprint Reconstruction Attacks in Biometric Systems

Biometric signals can be acquired with different sensors and recognized in secure identity management systems. However, it is vulnerable to various attacks that compromise the security management in many applications, such as industrial IoT. In a real-world scenario, the target template stored in the database of a biometric system can possibly be leaked, and then used to reconstruct a fake image to fool the biometric system. As such, many reconstruction attacks have been proposed, yet unsatisfactory naturalness, poor visual quality or incompleteness remains as major limitations. Thus, two reinforced palmprint reconstruction attacks are proposed. Any palmprint image, which can be easily obtained, is used as the initial image, and the region of interest is iteratively modified with deep reinforcement strategies to reduce the matching distance. In the first attack, Modification Constraint within Neighborhood (MCwN) limits the modification extent and suppresses the reckless modification. In the second attack, Batch Member Selection (BMS) selects the significant pixels (SPs) to compose the batch, which are simultaneously modified to a slighter extent to reduce the matching number and the visual-quality degradation. The two reinforced attacks can satisfy all the requirements, which cannot be simultaneously satisfied by the existing attacks. The thorough experiments demonstrate that the two attacks have a highly successful attack rate for palmprint systems based on the most state-of-the-art coding-based methods.

Adaptive Sparse Domain Selection for Weather Radar Superresolution

Accurate and high-resolution weather radar data reflecting detailed structure information of radar echo plays an important role in analysis and forecast of extreme weather. Typically, this is done using interpolation schemes, which only use several neighboring data values for computational approximation to get the estimated, resulting the loss of intense echo information. Focus on this limitation, a superresolution reconstruction algorithm of weather radar data based on adaptive sparse domain selection (ASDS) is proposed in this article. First, the ASDS algorithm gets a compact dictionary by learning the precollected data of model weather radar echo patches. Second, the most relevant subdictionaries are adaptively select for each low-resolution echo patches during the spare coding. Third, two adaptive regularization terms are introduced to further improve the reconstruction effect of the edge and intense echo information of the radar echo. Experimental results show that the ASDS algorithm substantially outperforms interpolation methods for ×2 and ×4 reconstruction in terms of both visual quality and quantitative evaluation metrics.

Denoising and Dehazing an Image in a Cascaded Pattern for Continuous Casting

Automatic vision systems have been widely used in the continuous casting of the steel industry, which improve efficiency and reduce labor. At present, high temperatures with evaporating fog cause images to be noisy and hazy, impeding the usage of advanced machine learning algorithms in this task. Instead of considering denoising and dehazing separately like previous papers, we established that by taking advantage of deep learning in a modeling complex formulation, our proposed algorithm, called Cascaded Denoising and Dehazing Net (CDDNet) reduces noise and hazy in a cascading pattern. Experimental results on both synthesized images and a pragmatic video from a continuous casting factory demonstrate our method’s superior performance in various metrics. Compared with existing methods, CDDNet achieved a 50% improvement in terms of peak signal-to-noise ratio on the validation dataset, and a nearly 5% improvement on a dataset that has never seen before. Besides, our model generalizes so well that processing a video from an operating continuous casting factory with CDDNet resulted in high visual quality.

Fuzzy Proximity based Robust Data Hiding Scheme with Interval Threshold

In 2020, Ashraf et al. proposed an interval type-2 fuzzy logic based block similarity calculation using color proximity relations of neighboring pixels in a steganographic scheme. Their method works well for detecting similarity, but it has drawbacks in terms of visual quality, imperceptibility, security, and robustness. Using Mamdani fuzzy logic to identify color proximity at the block level, as well as a shared secret key and post-processing system, this paper attempts to develop a robust data hiding scheme with similarity measure to ensure good visual quality, robustness, imperceptibility, and enhance the security. Further, the block color proximity is graded using an interval threshold. Accordingly, data embedding is processed in the sequence generated by the shared secret keys. In order to increase the quality and accuracy of the recovered secret message, the tampering coincidence problem is solved through a post-processing approach. The experimental analysis, steganalysis and comparisons clearly illustrate the effectiveness of the proposed scheme in terms of visual quality, structural similarity, recoverability and robustness.

Visual quality of Banjir Kanal Timur riverbank as a public open space in the city (Case study: Banjir Kanal Timur Jakarta)

The availability of public open spaces in urban areas is very urgent at this time, especially considering the need for public open spaces that can be used by urban communities, both as social areas and sports recreation. The existing condition along the canal edge requires improving the visual quality so that it can be used as a public open space. The purpose of this study is to evaluate the riverbank, as well as increasing the visual appeal to form public open spaces without reducing the ecological quality of the land and waters of the canal. The analysis method uses scenic beauty estimation, semantic, differential to assess the visual quality at 10 capture points of the coastal riverbank landscape and those with a value less than - 20 have a low or poor visual quality value. In general, the riverbank has a moderate visual quality value because it has not been used properly. The final result of this research activity is as a reference for improving the visual quality of Banjir Kanal Timur, thus creating a Public Open Space according to standart, safe, comfortable regulation for social interaction, sports recreation, education and concern for the ecological and hydrological aspects of the city.

Novel 2-D histogram based Soft thresholding for Brain Tumor Detection and Image Compression

The objective of image compression is to extract meaningful clusters in a given image. Significant groups are possible with absolute threshold values. 1-D histogram-based multilevel thresholding is computationally complex and reconstructed image visual quality comparatively low because of equal distribution of energy over the entire histogram plan. So, 2-D histogram-based multilevel thresholding is proposed in this paper by maximizing the Renyi entropy with a novel hybrid Genetic Algorithm, Particle Swarm Optimization and Symbiotic Organisms Search (hGAPSO-SOS), and the obtained results are compared with state of the art optimization techniques. Recent study reveals that PSNR fails in measuring the visual quality because of mismatch with the objective mean opinion scores (MOS). So, we incorporate a weighted PSNR (WPSNR) and visual PSNR (VPSNR). Experimental results examined on Magnetic Resonance images of brain, and results with 2-D histogram reveal that hGAPSO-SOS method can be efficiently and accurately used in multilevel thresholding problem.

Visual Perceptual Quality Assessment Based on Blind Machine Learning Techniques

This paper presents the construction of a new objective method for estimation of visual perceiving quality. The proposal provides an assessment of image quality without the need for a reference image or a specific distortion assumption. Two main processes have been used to build our models: The first one uses deep learning with a convolutional neural network process, without any preprocessing. The second objective visual quality is computed by pooling several image features extracted from different concepts: the natural scene statistic in the spatial domain, the gradient magnitude, the Laplacian of Gaussian, as well as the spectral and spatial entropies. The features extracted from the image file are used as the input of machine learning techniques to build the models that are used to estimate the visual quality level of any image. For the machine learning training phase, two main processes are proposed: The first proposed process consists of a direct learning using all the selected features in only one training phase, named direct learning blind visual quality assessment DLBQA. The second process is an indirect learning and consists of two training phases, named indirect learning blind visual quality assessment ILBQA. This second process includes an additional phase of construction of intermediary metrics used for the construction of the prediction model. The produced models are evaluated on many benchmarks image databases as TID2013, LIVE, and LIVE in the wild image quality challenge. The experimental results demonstrate that the proposed models produce the best visual perception quality prediction, compared to the state-of-the-art models. The proposed models have been implemented on an FPGA platform to demonstrate the feasibility of integrating the proposed solution on an image sensor.

Effect of eccentricity of overnight lenses on 2-year axial growth and visual quality

AIM: To explore the effect of eccentricity of overnight orthokeratology (OK) lenses on 2-year eye axial growth and visual quality. METHODS: Based on the degree of eccentricity of OK lenses, patients were divided into three groups: a low degree of eccentricity group (degree of eccentricity ≤0.5 mm), a group of moderate eccentricity (eccentric degree >0.5-1.0 mm) and a group with a high degree of eccentricity (eccentric degree >1-1.5 mm). The degree of eccentricity of the OK lens, spherical equivalent (SE), the uncorrected visual acuity (UCVA) after wearing OK lenses, axial length (AL) before and after wearing OK lenses, total higher-order aberrations (HOA), comas, and spherical aberrations (SA) for 3 mm pupils were analyzed. The difference among the three groups for all parameters was compared using the Kruskal-Wallis H Rank-Sum test. RESULTS: The study retrospectively analyzed 75 cases (139 eyes). In the low eccentricity group (53 eyes), the mean age was 11.4±2.4y, SE was -3.24±1.48 D, and AL was 24.85±1.01 mm. In the moderate eccentricity group (53 eyes), the mean age was 11.4±2.2y, SE was -3.22±1.29 D, and AL was 25.15±0.92 mm. In the high eccentricity group (31 eyes), the mean age was 11.5±1.9y, SE was -3.54±1.43 D, and AL was 24.95±0.84mm. After two years, there was no significant difference in the changes of the axis among the three groups (P=0.089). The HOA, SA, and coma in the high eccentric group were significantly higher than in the middle eccentric group (P<0.05). The HOA, SA, and coma in the high eccentric group were also significantly higher than those in the low eccentric group (P<0.05). CONCLUSION: For OK lenses, it is unnecessary to strictly require the absolute centralization of the lens position. An unnecessary change of the lenses may delay the eye-axis control. However, the balance between axial control and visual quality should be assessed.

Design and Fabrication of a Cost-Effective Optical Notch Filter for Improving Visual Quality

This study presents a multilayer design and fabrication of an optical notch filter for enhancing visual quality. A cost-effective multilayer design of notch filter with low surface roughness and low residual stress is proposed. A 9-layer notch filter composed of SiO2 and Nb2O5 with a central wavelength of 480 nm is prepared by electron beam evaporation combined with ion-assisted deposition. The optical transmittance, residual stress, and surface morphology are measured by a UV/VIS/NIR spectrophotometer, Twyman-Green interferometer and field emission scanning electron microscopy (FE-SEM). The transmittance of the notch filter at the central wavelength is above 15%, and the average transmittance of the transmission band is about 80%. The residual stress of the notch filter is −0.235 GPa, and the root mean square surface roughness is 1.85 nm. For improving the visual quality, a good image contrast can be obtained by observing the microscopic image using the proposed notch filter.

Comparative Investigation of Daylight Glare Probability (DGP) Comfort Classes in Clear Sky Condition

Glare is considered one of the most important variables to reach visual comfort and visual quality. It represents one of the fundamental barriers for an effective use of daylighting in buildings. One of the best performing and robust glare prediction models, relative to other available metrics, is a Daylight Glare Probability (DGP). Based on a validated and precise methodology (RADIANCE) the aim of this work is to compare the DGP model (original cut-off values) with new cut-off values that differ according to the time of day (morning, noon and afternoon). Both cut-off values were compared at more than 300 simulated conditions of daylighting in an interior space. This work offers the originality of studying recently proposed cut-off values in climate luminous with predominant clear sky conditions. Currently, the application of these new cutoff values is reduced to the field of science or simulation professionals. The results showed important differences (64.86%) between the categories proposed by both cut-off values. Nevertheless, these differences do not have a significant impact in glare prediction (< 2.7%), in terms of glare absence (DGP <0.38) and presence (DGP >0.38). This analysis made it possible: (i) to regionally apply the main current corpus criteria regarding glare issues as well as emergent proposals and (ii) to present new experimental data aimed at helping the field and, together with other works, improving the tools used by professionals on a daily basis.