Features for image retrieval: an experimental comparison

By Thomas Deselaers, Daniel Keysers, Hermann Ney. Information retrieval (Boston), 2008

654 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/06cf3f55b2bd959d9228d29e1aa3e71ba7cece94

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. G. Wang
2. Jiebo Luo
3. Dacheng Tao
4. Luc Van Gool
5. Shiv Ram Dubey
6. Yi Yang
7. Christian Beecks
8. Jiawei Han

Citations in the corpus

• Distance based similarity models for content based multimedia retrieval (2013, methodology): “After having identified interesting features within an image, they are described mathematically by feature descriptors [Penatti et al., 2012, Li and Allinson, 2008, Deselaers et al., 2008, Mikolajczyk and Schmid, 2005].”
• Convolutional Neural Network-based Place Recognition (2014, neutral): “However, global features are computed from the entire image, rendering them unsuitable to effects such as partial occlusion, lighting change or perspective transformation [Deselaers, et al., 2008].”
• A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, background): “are represented in the form of a feature descriptor [6].”
• Reinforced Similarity Integration in Image-Rich Information Networks (2013, background): “Image similarity can be estimated from image content features [10], [20], [21], such as color histogram, edge histogram [22], Color Correlogram [23], CEDD [24], GIST, texture features [25], [26], Gabor features [27], [28], shape [29], [30], and SIFT [31].”
• Discrimination between tumour epithelium and stroma via perception-based features (2015, background): “Nor is the matter solved in posterior works [21, 22].”
• A Visual Analytics Approach Using the Exploration of Multidimensional Feature Spaces for Content-Based Medical Image Retrieval (2015, background): “Correlation values serve as an intuitive indicator for finding feature combinations as they are closely connected to similaritybased classification tasks [32], [33].”