Open Access
Sketch and Match: Scene Montage Using a Huge Image Collection
TLDR
This work presents a sketch-based approach to find matching source images for seamless image composition, by leveraging a large amount of image corpus collected from the Internet.Abstract:
We present a sketch-based approach to find matching source images for seamless image composition, by leveraging a large amount of image corpus collected from the Internet. Given a target image where the user draws a rough sketch to indicate the desired object fill-in, our system automatically searches a large image database, and returns a sparse set of matching images. These matching images contain salient regions semantically similar to the usersupplied sketch. Once the user has selected the preferred source region, it will be seamlessly pasted onto the target image where the sketch is drawn.read more
Citations
More filters
Book ChapterDOI
2D Figure Pattern Mining
TL;DR: A technique that enables the applications to automatically present users with the list of figures considered to have any meaning and retrieve the desired figures from the database using it as the key is proposed.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.
Journal ArticleDOI
A performance evaluation of local descriptors
TL;DR: It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Proceedings ArticleDOI
Video Google: a text retrieval approach to object matching in videos
TL;DR: An approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video, represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion.
Journal ArticleDOI
Content-based image retrieval at the end of the early years
TL;DR: The working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap are discussed, as well as aspects of system engineering: databases, system architecture, and evaluation.