Convolutional neural network with joint stepwise character/word modeling based system for scene text recognition

Multimedia Tools and Applications - Text recognition in the wild is a challenging task in the field of computer vision and machine learning. Existing optical character recognition engines cannot...     

Spray-Coating of Superhydrophobic Coatings for Advanced Applications

Superhydrophobic coatings are widely applicable, e.g., as self-cleaning surfaces or water–oil separation membranes, yet their wider usage is impeded due to costs of fabrication, size, or substrate limitation. Spray-coating is a versatile coating procedures and might offer a good solution for the fabrication of these superhydrophobic coatings, due to the fact that coatings can be fabricated on various materials in a simple, fast, and inexpensive manner. Most procedures rely on hybrid coatings of hydrophobized nanoparticles and a polymeric matrix, which have several drawbacks including the easy loss of nanoparticles and difficult waste handling. Here, the fabrication of the superhydrophobic material, called Fluoropor, for the first time, by spray-coating on various substrates including metals, tissues, concrete, and glass is presented. It is fabricated by spray-coating a mixture of a highly fluorinated monomer blended with porogens followed by photopolymerization. The superhydrophobicity of the material relies on the porous structure on the micro-/nanoscale across the bulk material and does not require any nanoparticles. Excellent self-cleaning ability of these coatings, resistance against thermal and abrasive impact, and their application as oil–water separation membranes are shown. This versatile applicability is highly promising for real-world application as self-cleaning coatings or oil–water separating membranes.     

Mean-Shift segmentation and PDE-based nonlinear diffusion: toward a common variational framework for foreground/background document image segmentation

The presence of noise in images of degraded documents limits the direct application of segmentation approaches and can lead to the presence of a number of different artifacts in the final segmented image. A possible solution is the integration of a pre-filtering step which may improve the segmentation quality through the reduction of such noise. This study demonstrated that combining the Mean-Shift clustering algorithm and the tensor-driven diffusion process into a joint iterative framework produced promising results. For instance, this framework generates segmented images with reduced edge and background artifacts when compared to results obtained after applying each method separately. This improvement is explained by the mutual interaction of global and local information, introduced, respectively, by the Mean-Shift and the anisotropic diffusion. Another point of note is that the anisotropic diffusion process smoothed images while preserving edge continuities. The convergence of this framework was defined automatically under a stopping criterion not previously defined when the diffusion process was applied alone. To obtain a fast convergence, the common framework utilizes the speedup algorithm of the Fukunaga and Hostetler Mean-Shift formulation already proposed by Lebourgeois et al. (International Conference on Document Analysis and Recognition (ICDAR), pp 52–56, 2013). This new variant of the Mean-Shift algorithm produced similar results to the original one, but ran faster due to the application of the integral volume. The first application of this framework was document ink bleed-through removal where noise is stemmed from the interference of the verso side on the recto side, thus perturbing the legibility of the original text. Other categories of images could also be subjected to the proposed framework application.     

A new PDE-based approach for singularity-preserving regularization: application to degraded characters restoration

The massive digitization of heritage documents has raised new prospects for research like degraded document image restoration. Degradations harm the legibility of the digitized documents and limit their processing. As a solution, we propose to tackle the problem of degraded text characters with PDE (partial differential equation)-based approaches. Existing PDE approaches do not preserve singularities and edge continuities while smoothing. Hence, we propose a new anisotropic diffusion by adding new constraints to the Weickert coherence-enhancing diffusion filter in order to control the diffusion process and to eliminate the inherent corner rounding. A qualitative improvement in the singularity preservation is thus achieved. Experiments conducted on degraded document images illustrate the effectiveness of the proposed method compared with other anisotropic diffusion approaches. We illustrate the performance with the study of the optical recognition accuracy rates.     

Secretagogue and bacteriostatic active fractions derived from a peptic hydro‐ lysate of alfalfa RuBisCO small purified subunit

For the first time a purification process for small RuBisCO (ribulose‐1,5‐bisphosphate carboxylase/oxygenase) subunit (SRS) was developed from an industrial by‐product of alfalfa, taking advantage of its solubility at low pH. Only one protein strip (14 kDa) was clearly detected in the sodium dodecyl sulfate polyacrylamide gel electrophoresis (SDS‐PAGE) profile of the supernatant at pH 2. The recovery of SRS was 48% by this method, with a purity estimated as 98% by densitometry and reverse phase high‐performance liquid chromatography (RP‐HPLC). Moreover, most polyphenolic compounds were discarded, as confirmed by spectrophotometry and RP‐HPLC. SRS hydrolysis was performed for 20 h at 37 °C using pepsin in ammonia/formic acid buffer at pH 3. The hydrolysate was fractionated on a Sephadex G25 column equilibrated with ethanolamine/HCl buffer. Biological activities were found in two fractions. The first fraction showed slight bacteriostatic properties against two pathogenic bacteria, Salmonella arizonae and Shigella sonnei. The second fraction, tested by radioimmunoassay (RIA), presented a secretagogue activity comparable to that of gastrin. Copyright © 2006 Society of Chemical Industry     

Handling noise in textual image resolution enhancement using online and offline learned dictionaries

International Journal on Document Analysis and Recognition (IJDAR) - The resolution enhancement of textual images poses a significant challenge mainly in the presence of noise. The inherent...     

Ab Initio Insight into the Interaction of Metal-Decorated Fluorinated Carbon Fullerenes with Anti-COVID Drugs

We theoretically investigated the adsorption of two common anti-COVID drugs, favipiravir and chloroquine, on fluorinated C₆₀ fullerene, decorated with metal ions Cr³⁺, Fe²⁺, Fe³⁺, Ni²⁺. We focused on the effect of fluoridation on the interaction of fullerene with metal ions and drugs in an aqueous solution. We considered three model systems, C₆₀, C₆₀F₂ and C₆₀F₄₈, and represented pristine, low-fluorinated and high-fluorinated fullerenes, respectively. Adsorption energies, deformation of fullerene and drug molecules, frontier molecular orbitals and vibrational spectra were investigated in detail. We found that different drugs and different ions interacted differently with fluorinated fullerenes. Cr³⁺ and Fe²⁺ ions lead to the defluorination of low-fluorinated fullerenes. Favipiravir also leads to their defluorination with the formation of HF molecules. Therefore, fluorinated fullerenes are not suitable for the delivery of favipiravir and similar drugs molecules. In contrast, we found that fluorine enhances the adsorption of Ni²⁺ and Fe³⁺ ions on fullerene and their activity to chloroquine. Ni²⁺-decorated fluorinated fullerenes were found to be stable and suitable carriers for the loading of chloroquine. Clear shifts of infrared, ultraviolet and visible spectra can provide control over the loading of chloroquine on Ni²⁺-doped fluorinated fullerenes.     

A survey on interference management techniques in femtocell self-organizing networks

The femtocell concept is an emerging technology for deploying the next generation of the wireless networks, aiming at indoor coverage enhancement, increasing capacity, and offloading the overlay macrocell traffic. Nevertheless, one of the most critical issues in femtocells is the potential interference between nearby femtocells and from femtocells to macrocells or to mobile handsets, thus mitigating the overall system capacity.In this paper, we have discussed mechanisms which can be deployed to lessen the interference and increase the user capacity. Therefore, we provide a survey on the different interference and resource management techniques in Self-Organizing Network according to specifics classification criteria. These techniques derive from the following approaches: power control, proper cell planning, frequency reuse, OFDMA, self-configuration and self-optimization, conventional TDD, etc. These techniques can be applied separately and can be used as hybrid. A qualitative comparison among the different approaches and techniques is provided at the end of this paper.