Patil P.H.,SPPU |
Thepade S.D.,SPPU |
Maurya M.,SVKMs Mukesh Patel School of Technology Management and Engineering
International Journal of Applied Engineering Research | Year: 2015
A video is made up of frames. Generally video processing applications demand to process each video frame one by one, but processing each frame consumes lot of time; video content summarization helps in improvising the processing speed such applications. Key frames in video are considered for content summarization. Key frame is a frame in which there is a major change as compared to the previous video frames. Hence key frame extraction becomes very important in Video Content Summarization. In applications needing content summarization, like data storage, retrieval and surveillance, key frames extraction plays a vital role. In this paper, novel key frames extraction method is proposed with Thepade's Sine Error Vector Rotation (TSEVR), Thepade's Hartley Error Vector Rotation (TH1EVR) and Thepade's Slant Error Vector Rotation (TS1EVR) with ten different codebook sizes and assorted similarity measures. Experimentation done with help of the test bed of videos has shown that higher codebook sizes give better completeness in key frame extraction for video summarization. Experimental results are discussed for video content summarization with five assorted similarity measures like Euclidean Distance, Canberra Distance, Square-Chord Distance, Mean Square Error, Sorensen Distance with proposed TSEVR, TH1EVR and TS1EVR. Overall Euclidean distance gives better Keyframe extraction. The Thepade's Sine Error Vector rotation based keyframe extraction gives better performance with Euclidean Distance at codebook size 1024 among the considered variations in the paper. © Research India Publications.
Kekre H.B.,SVKMs Mukesh Patel School of Technology Management and Engineering |
Sarode T.K.,Narsee Monjee Institute of Management and Higher Studies |
Gharge S.M.,Narsee Monjee Institute of Management and Higher Studies
ICWET 2010 - International Conference and Workshop on Emerging Trends in Technology 2010, Conference Proceedings | Year: 2010
Segmenting a mammographic images into homogeneous texture regions representing disparate tissue types is often a useful preprocessing step in the computer-assisted detection of breast cancer. That is why we proposed new algorithm to detect cancer in mammogram breast cancer images. In this paper we proposed segmentation using vector quantization technique. Here we used Kekre's Fast Codebook Generation algorithm (KFCG) for segmentation of mammographic images. Initially a codebook of size 128 was generated for mammographic images. These code vectors were further clustered in 8 clusters using same KFCG algorithm. Eight segmented images were obtained for each code vector. These 8 images were displayed as a result. This approach does not leads to over segmentation or under segmentation, as is the case for watershed segmentation and entropy segmentation using Gray Level Co-occurrence Matrix. Results of these algorithms are shown for comparison. Copyright 2010 ACM.
Surve B.C.,SVKMs Mukesh Patel School of Technology Management and Engineering
Proceedings of the 2014 Conference on IT in Business, Industry and Government: An International Conference by CSI on Big Data, CSIBIG 2014 | Year: 2014
Renewable energy is the answer to energy crises which can bring rays of hopes for a country which is bless by nature with abundant natural resources. Solar energy is one of them. There is a need of accurate, reliable and easily accessible solar GIS. This paper works on sitting algorithm for Solar power generation; also explore Spatio-Temporal data modeling and method to develop web based application for Solar Power plant siting in India using GIS. Application incorporate Open Geo suit with Postgres Spatial database as back-end and Jave as front-end as well as Web Map services from Google Map. © 2014 IEEE.
Patil R.,SVKMs Mukesh Patel School of Technology Management and Engineering
Communications in Computer and Information Science | Year: 2011
Automated guided vehicle selection, a key concern in manufacturing environment is a complex, difficult task and requires extensive technical knowledge with systematic analysis. It is invaluable to justify the selected equipment before actual implementation of the same. This paper presents a logical procedure to select automated guided vehicle in manufacturing environment for a given application. The procedure is based on preference selection index (PSI) method. An automated guided vehicle selection index is proposed that evaluates and ranks automated guided vehicle for the given application. An example is included to illustrate the approach. © 2011 Springer-Verlag.
Maurya M.,SVKMs Mukesh Patel School of Technology Management and Engineering |
Proceedings of the 2012 World Congress on Information and Communication Technologies, WICT 2012 | Year: 2012
This paper discusses various MapReduce applications like pi, wordcount, grep, Terasort. We have shown experimental results of these applications on a Hadoop cluster. In this paper, performance of above application has been shown with respect to execution time and number of nodes. We find that as the number of nodes increases the execution time decreases. This paper is basically a research study of above MapReduce applications. © 2012 IEEE.