Quote examiner: verifying quoted images using web-based text similarity

Over the last few years, there has been a rapid growth in digital data. Images with quotes are spreading virally through online social media platforms. Misquotes found online often spread like a forest fire through social media, which highlights the lack of responsibility of the web users when circulating poorly cited quotes. Thus, it is important to authenticate the content contained in the images being circulated online. So, there is a need to retrieve the information within such textual images to verify quotes before its usage in order to differentiate a fake or misquote from an authentic one. Optical Character Recognition (OCR) is used in this paper, for converting textual images into readable text format, but none of the OCR tools are perfect in extracting information from the images accurately. In this paper, a method of post-processing on the retrieved text to improve the accuracy of the detected text from images has been proposed. Google Cloud Vision has been used for recognizing text from images. It has also been observed that using post-processing on the extracted text improved the accuracy of text recognition by 3.5% approximately. A web-based text similarity approach (URLs and domain name) has been used to examine the authenticity of the content of the quoted images. Approximately, 96.26% accuracy has been achieved in classifying quoted images as verified or misquoted. Also, a ground truth dataset of authentic site names has been created. In this research, images with quotes by famous celebrities and global leaders have been used. A comparative analysis has been performed to show the effectiveness of our proposed algorithm.

     

Comparison of 2D simultaneous multi-slice and 3D GRASE readout schemes for pseudo-continuous arterial spin labeling of cerebral perfusion at 3 T

Objective

In this perfusion magnetic resonance imaging study, the performances of different pseudo-continuous arterial spin labeling (PCASL) sequences were compared: two-dimensional (2D) single-shot readout with simultaneous multislice (SMS), 2D single-shot echo-planar imaging (EPI) and multishot three-dimensional (3D) gradient and spin echo (GRASE) sequences combined with a background-suppression (BS) module.

Materials and methods

Whole-brain PCASL images were acquired from seven healthy volunteers. The performance of each protocol was evaluated by extracting regional cerebral blood flow (rCBF) measures using an inline morphometric segmentation prototype. Image data postprocessing and subsequent statistical analyses enabled comparisons at the regional and sub-regional levels.

Results

The main findings were as follows: (i) Mean global CBF obtained across methods was were highly correlated, and these correlations were significantly higher among the same readout sequences. (ii) Temporal signal-to-noise ratio and gray-matter-to-white-matter CBF ratio were found to be equivalent for all 2D variants but lower than those of 3D-GRASE.

Discussion

Our study demonstrates that the accelerated SMS readout can provide increased acquisition efficiency and/or a higher temporal resolution than conventional 2D and 3D readout sequences. Among all of the methods, 3D-GRASE showed the lowest variability in CBF measurements and thus highest robustness against noise.

     

2-Aminobenzothiazole as an efficient corrosion inhibitor of AA6061-T6 in 0.5 M HCl medium: electrochemical,surface morphological,and theoretical study

Journal of Applied Electrochemistry - The inhibitive action of 2-aminobenzothiazole (ABT) on the corrosion of AA6061-T6 was evaluated in 0.5 M HCl by electrochemical techniques. The...     

An analysis for AlGaN/GaN modulation doped field effect transistor using accurate velocity-field dependence for high power microwave frequency applications

An analytical model of Al_0.15Ga_0.85N/GaN modulation doped field effect transistor (MODFET), which uses an accurate velocity field relationship and incorporates the dominant effect of piezoelectric polarization induced charge at the AlGaN/GaN interface is presented. The effect of traps has also been taken into account. The calculated DC characteristics are in excellent agreement with the measured data. The model is extended to predict the microwave performance of the device. High current levels (>500 mA/mm), large transconductance (160.83 mS/mm) and a high cutoff frequency (9.6 GHz) have been achieved analytically and are in close agreement with the experimental data.     

Synthesis of TiO<Subscript>2</Subscript> Nanoparticles from Ilmenite Through the Mechanism of Vapor-Phase Reaction Process by Thermal Plasma Technology

Synthesis of nanoparticles of TiO₂ was carried out by non-transferred arc thermal plasma reactor using ilmenite as the precursor material. The powder ilmenite was vaporized at high temperature in plasma flame and converted to a gaseous state of ions in the metastable phase. On cooling, chamber condensation process takes place on recombination of ions for the formation of nanoparticles. The top-to-bottom approach induces the disintegration of complex ilmenite phases into simpler compounds of iron oxide and titanium dioxide phases. The vapor-phase reaction mechanism was carried out in thermal plasma zone for the synthesis of nanoparticles from ilmenite compound in a plasma reactor. The easy separation of iron particles from TiO₂ was taken place in the plasma chamber with deposition of light TiO₂ particles at the top of the cooling chamber and iron particles at the bottom. The dissociation and combination process of mechanism and synthesis are studied briefly in this article. The product TiO₂ nanoparticle shows the purity with a major phase of rutile content. TiO₂ nanoparticles produced in vapor-phase reaction process shows more photo-induced capacity.