Video text information plays an important role in semanticbased video analysis, indexing, and retrieval. Text embedded in the image or video contains very useful information like the name of the person, title, location and sometimes brief description of the image. Many algorithms have been proposed to detect and localize the text information present in video images. In this paper, we proposed a methodology to enhance the quality of the image and then detect and localize text regions from low quality video images. Experimental results show the proposed method achieves improved precision rate and recall rate.

No abstract

Soil compaction is one of the major geo technical engineering applications in infrastructure development of the nation. Large volumes of soil are used in the construction of flyovers, earth dams, and railways. There is a need to understand comprehensively in a unified and coherent manner. Thus the knowledge of compaction behavior and its characteristics of fine grained soils at different compaction energies assume great importance from they viewpoint of practical significant. In the present work, compaction parameters such as (MDD) (max) and optimum moisture content (OMC) care determined at various compaction energies by conducting the laboratory compaction tests. In the field, the compaction of soils usually involves using different compaction energies. A limited experimental investigation has been taken up in the present study. The cardinal aim of the present study is to focus on effect of compaction energy on the behavior and compaction characteristics and unconfined compressive strength (qu) of soils.

Deep learning is a rising territory of machine learning (ML) inquires about. It includes different shrouded layers of fake neural systems. Deep learning (DL) is a part of machine learning dependent on an arrangement of calculations that endeavor to show abnormal state reflections in information. It is utilized by Google in its voice and picture acknowledgment calculations, by Netflix and Amazon to choose what you need to watch or purchase straightaway, and by specialists at MIT to anticipate what’s to come. Profound Learning is utilized in different fields for accomplishing various levels of deliberation like sound, content; pictures highlight extraction and so forth. The Deep learning philosophy applies nonlinear changes and model reflections of abnormal state in extensive databases. With Deep learning capacity to make forecasts and groupings taking the upside of huge information, it can be a creative answer for issues and issues that have been never thought to be understood in such a simple way. Then again, it makes numerous difficulties on the researchers who are endeavoring to convey such another methodology. The accompanying audit sequentially shows how and in what real applications profound realizing calculations have been used. We have completed a broad writing audit and reviewed the utilization of profound learning methods on different fields.