Visual Saliency: From Pixel-Level to Object-Level Analysis
Autor Jianming Zhang, Filip Malmberg, Stan Sclaroffen Limba Engleză Paperback – 2 feb 2019
In this book, the authors present methods for both traditional and emerging saliency computation tasks, ranging from classical low-level tasks like pixel-level saliency detection to object-level tasks such as subitizing and salient object detection. For low-level tasks, the authors focus on pixel-level image processing approaches based on efficient distance transform. For object-level tasks, the authors propose data-driven methods using deep convolutional neural networks. The book includes both empirical and theoretical studies, together with implementation details of the proposed methods. Below are the key features fordifferent types of readers.
For computer vision and image processing practitioners:
This book provides up-to-date supplementary reading material for course topics like connectivity based image processing, deep learning for image processing;
Some easy-to-implement algorithms for course projects with data provided (as links in the book);
Hands-on programming exercises in digital topology and deep learning.
For computer vision and image processing practitioners:
- Efficient algorithms based on image distance transforms for two pixel-level saliency tasks;
- Promising deep learning techniques for two novel object-level saliency tasks;
- Deep neural network model pre-training with synthetic data;
- Thorough deep model analysis including useful visualization techniques and generalization tests;
- Fully reproducible with code, models and datasets available.
- Summary of theoretic findings and analysis of Boolean map distance;
- Theoretic algorithmic analysis;
- Applications in salient object detection and eye fixation prediction.
This book provides up-to-date supplementary reading material for course topics like connectivity based image processing, deep learning for image processing;
Some easy-to-implement algorithms for course projects with data provided (as links in the book);
Hands-on programming exercises in digital topology and deep learning.
Preț: 300.95 lei
Preț vechi: 376.18 lei
-20% Nou
Puncte Express: 451
Preț estimativ în valută:
57.59€ • 59.76$ • 48.14£
57.59€ • 59.76$ • 48.14£
Carte tipărită la comandă
Livrare economică 12-18 martie
Preluare comenzi: 021 569.72.76
Specificații
ISBN-13: 9783030048303
ISBN-10: 3030048306
Pagini: 120
Ilustrații: VII, 138 p. 47 illus., 44 illus. in color.
Dimensiuni: 155 x 235 mm
Greutate: 0.23 kg
Ediția:1st ed. 2019
Editura: Springer International Publishing
Colecția Springer
Locul publicării:Cham, Switzerland
ISBN-10: 3030048306
Pagini: 120
Ilustrații: VII, 138 p. 47 illus., 44 illus. in color.
Dimensiuni: 155 x 235 mm
Greutate: 0.23 kg
Ediția:1st ed. 2019
Editura: Springer International Publishing
Colecția Springer
Locul publicării:Cham, Switzerland
Cuprins
1 Overview.- 2 Boolean Map Saliency: A Surprisingly Simple Method.- 3 A Distance Transform Perspective.- 4 Efficient Distance Transform for Salient Region Detection.- 5 Salient Object Subitizing.- 6 Unconstrained Salient Object Detection.- 7 Conclusion and Future Work.
Caracteristici
This book includes efficient algorithms based on image distance transforms for two pixel-level saliency tasks as well as applications in salient object detection and eye fixation prediction. Also included are hands-on programming exercises in digital topology and deep learning.