Image classification for content-based indexing

By Aditya Vailaya, Mário A. T. Figueiredo, Anil K. Jain, HongJiang Zhang. IEEE Transactions on Image Processing, 2001

898 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/142f056a365dccd029c0897fcfa7833aecf2212f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

A survey of content-based image retrieval with high-level semantics (2007, methodology): “[68], using binary Bayesian classifier, high-level concepts of natural scenes are captured from low-level image features.”
Feature Learning for Image Classification Via Multiobjective Genetic Programming (2014, neutral): “D image data directly.”
Scene classification based on single-layer SAE and SVM (2015, background): “For instances, paper (Vailaya et al., 2001) focus on global images features of spatial color and edge distribution.”
A Semantic Typicality Measure for Natural Scene Categorization (2004, neutral): “Early research covers city/landscape- [3], indoor/outdoor- [4] and indoor/outdoor-, city/landscape-, sunset/mountain/forest-classification [5].”
Simultaneous image classification and annotation (2009, neutral): “Much previous work has explored the use of global image features for scene (or event) classification [21, 27, 26, 28, 17], and both discriminative and generative techniques have been applied to this problem.”
ImageCLEF 2014: Overview and Analysis of the Results (2014, methodology): “Particularly, in the training step the conditional probability of an image, being labeled by every class, is calculated using some parametric [40],[6] or nonparametric [34] methods.”
Image retrieval: Ideas, influences, and trends of the new age (2008, neutral): “Concept detection through supervised classification, involving simple concepts such as city, landscape, and sunset is achieved with high accuracy in [Vailaya et al. 2001].”
Content-based image retrieval: approaches and trends of the new age (2005, neutral): “Concept detection through supervised classification, involving simple concepts such as city, landscape, sunset, and forest, have been achieved with high accuracy in [98].”
CLUE: cluster-based retrieval of images by unsupervised learning (2005, background): “Digital Object Identifier 10.1109/TIP.2005.849770”
Feature Coding in Image Classification: A Comprehensive Study (2014, neutral): “image and video retrieval [2], web content analysis [3],”
Automatic Image Annotation Using Auxiliary Text Information (2008, background): “The earliest approaches are closely related to image classiﬁcation (Vailaya et al., 2001; Smeulders et al., 2000), where pictures are assigned a set of simple descriptions such as indoor, out-door, landscape, people, animal.”
Applying Fuzzy DLs in the Extraction of Image Semantics (2009, background): “Statistical concept classifiers exhibit highly variable performance, yet support generic learning for a substantial number of concepts [15,34, 35 ,36].”
Automatic Caption Generation for News Images (2013, background): “The literature is littered with various attempts to learn the associations between image features and words using supervised classification [1], [2], instantiations of the noisy-channel model [3], latent variable models [4], [5], [6], and models inspired by information retrieval [7], [8].”
A review on automatic image annotation techniques (2012, background): “Popular texture models are Markov random field (MRF) [6] [20] [91] [93] [94] [96] [97], simultaneous auto-regressive (SAR) model [8], fractal dimension (FD) [91] [95], etc.”
Features for image retrieval: an experimental comparison (2008, background): “Obviously, object recognition and CBIR are closely related fields [63, 64] and for some clearly defined retrieval tasks, object recognition methods might actually be the only possible solution: e.”
Concept-Based Video Retrieval (2009, background): “Typical concepts and their detectors are news anchor person by Zhang et al. [298], sunsets by Smith and Chang [214], indoor and outdoor by Szummer and Picard [233], and the work on distinguishing cityscape, landscape, mountains, and forests by Vailaya et al. [243] [244].”