Greyscale based learning in BPNN for image restoration problem

A new method of back propagation learning with respect to the problem of image restoration which is named as greyscale based learning in back propagation neural networks ( BPNN) is investigated. It is observed that by using this method the value of mean square error ( MSE) decreases significantly. In addition,this method also gives good visual results when it is applied in image restoration problem. This method is also useful to tackle the inherited drawback of falling into local minima by reducing its effect on overall system by bifurcating the learning locally different for different grey scale values. The performance of this algorithm has been studied in detail with different combinations of weights. In short,this algorithm provides much better results especially when compared with the simple back propagation algorithm with any further enhancements and without going for hybrid solutions.

Film-Screen Radiographic Artefacts: A Paradigm Shift in Classification

Objective: To propose a new method of classifying film-screen radiographic artefacts. Methodology: A prospective study was carried out at the Radiology Department of a University Teaching Hospital in Nigeria between June, 2011 and June 2013. Radiographs were assessed with the aid of a viewing box for artefacts which were arranged according to prior classifications by other researchers. They were subsequently grouped according to pre-arranged format into the new classification. Result: The following groups were observed: packaging (dark), procedure (greyscale), patient (greyscale), pre-processor (dark), processor (greyscale) and post-processor (greyscale). Conclusion: Classification of artefacts based on appearance and stage of introduction into film is easier to understand and remember.

A Novel Progressive Secret Image Sharing Method with Better Robustness

Secret image sharing (SIS) can be utilized to protect a secret image during transmit in the public channels. However, classic SIS schemes, e.g., visual secret sharing (VSS) and polynomial-based scheme, are not suitable for progressive encryption of greyscale images in noisy environment, since they will result in different problems, such as lossy recovery, pixel expansion, complex computation, "All-or-Nothing"and robustness. In this paper, a novel progressive secret sharing (PSS)method based on the linear congruence equation, namely LCPSS, is proposed to solve these problems. LCPSS is simple designed and easy to realize, but naturally has many great properties, e.g., (k, n) threshold,progressive recovery, lossless recovery, lack of robustness and simple computation.

Potential for energy conservation:A portable desktop paper reusing system for office waste paper

Renewable paper reusing plays a significant role in the sustainable environment under the background of the shortage in forest resources and the pollution from the paper industry.The conventional reusing stream of waste office paper appears to have low reusing rates while consuming massive amounts of energy in intermediate steps.In this study,we developed a novel portable renewable desktop paper reusing system based on font area detection and greyscale sensor.The proposed system consists of two main parts,namely,a greyscale sensor and font area detection model and a polishing mechanism.Acting as an ink mark detector for waste desktop paper,the greyscale sensor and font area detection model can detect the font in the waste desktop paper using an adaptive dynamic compensation schematic.The polishing mechanism will grind the font area of the wasted desktop paper,and this paper reusing processing is non-chemical,energy saving and environmentally friendly.The proposed system is demonstrated through simulations and experimental results,which show that the proposed renewable desktop paper reusing system is portable and is effective for reusing waste office paper in the office.An accuracy of 99.78%is demonstrated in the greyscale sensor and font area detection model,and the average reuse rate of one piece of paper is 2.52 times,verifying that the proposed portable system is effective and practical in renewable desktop paper reusing applications.