Gaussian mixture models of texture and colour for image database retrieval

By Haim Henri Permuter, Joseph M. Francos, Ian H. Jermyn. 2003

143 citations recorded by the source corpus.

We introduce Gaussian mixture models of 'structure' and colour features in order to classify coloured textures in images, with a view to the retrieval of textured colour images from databases. Classifications are performed separately using structure and colour and then combined using a confidence criterion. We apply the models to the VisTex database and to the classification of man-made and natural areas in aerial images. We compare these models with others in the literature, and show an overall improvement in performance.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Information Retrieval & Search, Probabilistic & Bayesian Methods

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

1. Fang Wen
2. Xiaogang Wang
3. Xiaoou Tang
4. Dong Chen
5. Jianmin Bao
6. Luc Van Gool
7. Gang Hua
8. Dacheng Tao

In Media Technology

1. Haim Henri Permuter
2. Joseph M. Francos
3. Ian H. Jermyn
4. Gang Hua
5. Fang Wen
6. Dong Chen
7. Jianmin Bao

In Information Retrieval & Search

1. Haim Henri Permuter
2. Joseph M. Francos
3. Ian H. Jermyn
4. Fang Wen

In Probabilistic & Bayesian Methods

1. Haim Henri Permuter
2. Joseph M. Francos
3. Ian H. Jermyn
4. Gang Hua
5. Fang Wen
6. Dong Chen
7. Jianmin Bao

Citations in the corpus

• Content-Based Image Retrieval Using Multiresolution Color and Texture Features (2008, background): “However, it is hard to attain satisfactory retrieval results by using a single feature because, in general, an image contains various visual characteristics.”
• Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity (2010, unknown): “Gaussian mixture models (GMM) have been shown to provide powerful tools for data clas sification and segmentation applications (see for example [14], [30], [54], [58]), however, they have not y et been shown to generate state-of-the-art in a general class of inverse problems.”
• A study of Gaussian mixture models of color and texture features for image classification and segmentation (2006, methodology): “Inrecentwork [34], we proposed the use of Gaussian mixture models (GMMs) for texture classification, demonstrating improved performance over other, computationally more expensive methods.”
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training (2017, background): “Conventional wisdom and early research of generative models, including Principle Component Analysis (PCA) [40], Independent Component Analysis (ICA) [10],and the Gaussian Mixture Model (GMM) [46, 27, 37], all assume a simple formation of data.”