Book ChapterDOI
Sketch-Based Images Database Retrieval
Stanislaw Matusiak,Mohamed Daoudi,Thierry Blu,Olivier Avaro +3 more
- pp 185-191
Reads0
Chats0
TLDR
An application allowing content-based retrieval that can thus be considered as an MPEG-7 example application and may be called "sketch-based database retrieval" since the user interacts with the database by means of sketches.Abstract:
This paper describes an application allowing content-based retrieval that can thus be considered as an MPEG-7 example application. The application may be called "sketch-based database retrieval" since the user interacts with the database by means of sketches. The user draws its request with a pencil: the request image is then a binary image that comprises a contour on a uniform bottom.read more
Citations
More filters
Journal ArticleDOI
A performance evaluation of gradient field HOG descriptor for sketch based image retrieval
Rui Hu,John Collomosse +1 more
TL;DR: Gradient Field HOG is described; an adapted form of the HOG descriptor suitable for Sketch Based Image Retrieval (SBIR) and incorporated into a Bag of Visual Words retrieval framework, and shown to consistently outperform retrieval versus SIFT, multi-resolution HOG, Self Similarity, Shape Context and Structure Tensor.
Journal ArticleDOI
Retrieval by shape similarity with perceptual distance and effective indexing
TL;DR: This paper proposes retrieval by shape similarity using local descriptors and effective indexing, and presents a comparative analysis of different indexing structures, for shape retrieval.
Sketch-Based Image Matching Using Angular Partitioning
TL;DR: In this article, a hand-drawn rough black and white sketch is compared with an existing data base of full color images (art works and photographs) to create ambient intelligence in terms of the evaluation of nonprecise, easy to input sketched information.
Journal ArticleDOI
Technical Section: An evaluation of descriptors for large-scale image retrieval from sketched feature lines
TL;DR: This work addresses the problem of fast, large scale sketch-based image retrieval, searching in a database of over one million images, and proposes two different approaches for which it is objectively evaluated that they significantly outperform existing approaches.
Journal ArticleDOI
Sketch-based image matching Using Angular partitioning
TL;DR: This work presents a novel method for image similarity measure, where a hand-drawn rough black and white sketch is compared with an existing data base of full color images (art works and photographs) to create ambient intelligence in terms of the evaluation of nonprecise, easy to input sketched information.
References
More filters
Journal ArticleDOI
A theory of multiscale, curvature-based shape representation for planar curves
F. Mokhtarian,Alan K. Mackworth +1 more
TL;DR: A shape representation technique suitable for tasks that call for recognition of a noisy curve of arbitrary shape at an arbitrary scale or orientation is presented and several evolution and arc length evolution properties of planar curves are discussed.
Journal ArticleDOI
Visual image retrieval by elastic matching of user sketches
A. Del Bimbo,Pietro Pala +1 more
TL;DR: A technique which is based on elastic matching of sketched templates over the shapes in the images to evaluate similarity ranks and is integrated with arrangements to provide scale invariance and take into account spatial relationships between objects in multi-object queries.
Book ChapterDOI
Query by Visual Example - Content based Image Retrieval
Kyoji Hirata,Toshikazu Kato +1 more
Journal ArticleDOI
Silhouette-based isolated object recognition through curvature scale space
TL;DR: A complete, fast and practical isolated object recognition system has been developed which is very robust with respect to scale, position and orientation changes of the objects as well as noise and local deformations of shape (due to perspective projection, segmentation errors and non-rigid material used in some objects).
Geometric methods for analysis of ridges in n-dimensional images
TL;DR: The goals of this dissertation are to produce an algorithm for segmenting an image in the way that a front-end vision system does, using the local geometry induced by the intensity values of the image, to create multiscale representations of the objects that allow exploration of the details of the images via an interactive computer system, and to provide a formal geometric foundation for multiscales image analysis.