Current Issue : January - March Volume : 2019 Issue Number : 1 Articles : 5 Articles
In this paper, we present a forward collision warning application for smartphones that\nuses license plate recognition and vehicular communication to generate warnings for notifying the\ndrivers of the vehicle behind and the one ahead, of a probable collision when the vehicle behind does\nnot maintain an established safe distance between itself and the vehicle ahead. The application was\ntested in both static and mobile scenarios, from which we confirmed the working of our application,\neven though its performance is affected by the hardware limitations of the smartphones....
We present a very simple approach for the detection of the Perfluorinated Alkylated\nSubstances (PFAs) in water solution. Perfluorooctanesulfonate (PFOS) and Perfluorooctanoate (PFOA)\nare the most extensively investigated perfluoroalkyl and polyfluoroalkyl substances in water because\nhuman exposition can occur through different pathways, even if the dietary intake seems to be their\nmain route of exposure. The developed sensor is based on a specific Molecularly Imprinted Polymer\n(MIP) receptor deposited on a simple D-shaped Plastic Optical Fiber (POF) platform. This novel\nchemical sensor has been characterized using a very simple and low-cost experimental setup based\non an LED and two photodetectors. This optical sensor system is an alternative method to monitor\nthe presence of contaminants with an MIP receptor, instead of a surface plasmon resonance (SPR)\nsensor in D-shaped POFs. For the sake of comparison, the results obtained exploiting the same MIP\nfor PFAs on a classic SPR-POF sensor have been reported. The experimental results have shown\nthat the actual limit of detection of this new configuration was about 0.5 ppb. It is similar to the one\nobtained by the configuration based on an SPR-POF with the same MIP receptor....
A novel image enhancement approach called entropy-based adaptive subhistogram equalization (EASHE) is put forward in this\npaper. The proposed algorithm divides the histogram of input image into four segments based on the entropy value of the\nhistogram, and the dynamic range of each subhistogram is adjusted. A novel algorithm to adjust the probability density function\nof the gray level is proposed, which can adaptively control the degree of image enhancement. Furthermore, the final contrastenhanced\nimage is obtained by equalizing each subhistogram independently. The proposed algorithm is compared with some\nstate-of-the-art HE-based algorithms. The quantitative results for a public image database named CVG-UGR-Database are\nstatistically analyzed. The quantitative and visual assessments show that the proposed algorithm outperforms most of the existing\ncontrast-enhancement algorithms. The proposed method can make the contrast of image more effectively enhanced as well as the\nmean brightness and details well preserved....
Image processing is an important step in every imaging path in the scientific community.\nEspecially in neutron imaging, image processing is very important to correct for image artefacts\nthat arise from low light and high noise statistics. Due to the low global availability of neutron\nsources suitable for imaging, the development of these algorithms is not in the main scope of\nresearch work and once established, algorithms are not revisited for a long time and therefore not\noptimized for high throughput. This work shows the possible speed gain that arises from the usage\nof heterogeneous computing platforms in image processing along the example of an established\nadaptive noise reduction algorithm....
At present, the generative adversarial networks research that generates a high\nconfidence image for a large number of training samples has achieved some\nresults, but the existing research only performs image generation for known\ntraining samples, but does not use the training parameters for image generation\nother than training samples. This paper uses the Tensor Flow deep learning\nframework to build deep convolutional generative adversarial networks to\ncomplete the generation of virtual face images. From the experimental results,\nit can better generate virtual face images similar to real faces, which provides\nnew ideas and methods for the research of generating virtual images....
Loading....