Techniques for Generation of Random Fields for Image Segmentation

Rambabu Pemula

ISBN 10: 6203199850 / ISBN 13: 9786203199857

Published by LAP LAMBERT Academic Publishing Dez 2020, 2020

About this Item

This item is printed on demand - Print on Demand Titel. Neuware -The book consists of image processing in particular related to image segmentation. The book depicts four issues. These issues related to segmentation of low contrast images, removal of shadow in the images, reduction of high dimensional images, and computational complexity of segmentation techniques. To address these issues, the author proposed OT-FO, GRF-B, GORF-LLE-ML, and H-ML technique. The results demonstrated that the H-ML approach obtained an accurate segmentation outcome on low contrast, shadow, high dimensional images, and different kinds of noises with reduced computational time. In the study of the performance of the proposed methods, the author has conducted experiments using benchmark databases like Berkely dataset (BSD500), Semantic dataset and author own dataset, etc., and has made a study of mean, standard deviation, Jaccard index, correlation, dice coefficient, segmentation accuracy, and time complexityVDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 152 pp. Englisch.

Seller Inventory # 9786203199857

Bibliographic Details

• Title: Techniques for Generation of Random Fields for Image Segmentation
• Publisher: LAP LAMBERT Academic Publishing Dez 2020
• Publication Date: 2020
• Language: English
• ISBN 10: 6203199850
• ISBN 13: 9786203199857
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 220W x 150H x 10D millimeters 220 millimeters width by 150 millimeters height by 10 millimeters depth
• Weight: 244 grams

About this title

Synopsis

The book consists of image processing in particular related to image segmentation. The book depicts four issues. These issues related to segmentation of low contrast images, removal of shadow in the images, reduction of high dimensional images, and computational complexity of segmentation techniques. To address these issues, the author proposed OT-FO, GRF-B, GORF-LLE-ML, and H-ML technique. The results demonstrated that the H-ML approach obtained an accurate segmentation outcome on low contrast, shadow, high dimensional images, and different kinds of noises with reduced computational time. In the study of the performance of the proposed methods, the author has conducted experiments using benchmark databases like Berkely dataset (BSD500), Semantic dataset and author own dataset, etc., and has made a study of mean, standard deviation, Jaccard index, correlation, dice coefficient, segmentation accuracy, and time complexity