OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning

The explosion of the Internet provides us with a tremendous resource of images shared online. It also confronts vision researchers the problem of finding effective methods to navigate the vast amount of visual information. Semantic image understanding plays a vital role towards solving this problem....

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of computer vision Ročník 88; číslo 2; s. 147 - 168
Hlavní autori: Li, Li-Jia, Fei-Fei, Li
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Boston Springer US 01.06.2010
Springer
Springer Nature B.V
Predmet:
Algorithms
Artificial Intelligence
Categories
Computer Imaging
Computer Science
Datasets
Human
Image Processing and Computer Vision
Internet
Learning
Monte Carlo method
Object recognition
On-line systems
Pattern Recognition
Pattern Recognition and Graphics
Vision
Graphical model
Internet vision
Image retrieval
Object recognition
Annotation
Dataset collection
Incremental learning
Non-parametric model
Semi-supervised learning
Polysemy
Classification
Object localization
Markov Chain Monte Carlo sampling
Topic model
Generative model
ISSN:0920-5691, 1573-1405
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The explosion of the Internet provides us with a tremendous resource of images shared online. It also confronts vision researchers the problem of finding effective methods to navigate the vast amount of visual information. Semantic image understanding plays a vital role towards solving this problem. One important task in image understanding is object recognition, in particular, generic object categorization. Critical to this problem are the issues of learning and dataset. Abundant data helps to train a robust recognition system, while a good object classifier can help to collect a large amount of images. This paper presents a novel object recognition algorithm that performs automatic dataset collecting and incremental model learning simultaneously. The goal of this work is to use the tremendous resources of the web to learn robust object category models for detecting and searching for objects in real-world cluttered scenes. Humans contiguously update the knowledge of objects when new examples are observed. Our framework emulates this human learning process by iteratively accumulating model knowledge and image examples. We adapt a non-parametric latent topic model and propose an incremental learning framework. Our algorithm is capable of automatically collecting much larger object category datasets for 22 randomly selected classes from the Caltech 101 dataset. Furthermore, our system offers not only more images in each object category but also a robust object category model and meaningful image annotation. Our experiments show that OPTIMOL is capable of collecting image datasets that are superior to the well known manually collected object datasets Caltech 101 and LabelMe.
Bibliografia:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-009-0265-6