A compact and efficient image retrieval approach based on border/interior pixel classification
By Renato O. Stehling, Mario A. Nascimento, Alexandre Xavier Falcão. International Conference on Information and Knowledge Management, 2002
342 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/8b78aa7954d05a3dd5062c2dc2f6e16112b62a88
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
- Terrance E. Boult
- Walter J. Scheirer
- Keiller Nogueira
- Otávio Augusto Bizetto Penatti
- J. A. D. Santos
- Anderson de Rezende Rocha
- Ricardo da Silva Torres
- Siome Klein Goldenstein
Citations in the corpus
- DOCToR: The Role of Deep Features in Content-Based Mammographic Image Retrieval (2018, methodology): “Feature Extractor Category #Features BIC Histogram [15] Color 512 Edge Histogram [16] Color 150 Normalized Histogram [17] Color 256 Haralick [18] Texture 24 Rotation Invariant LBP [19] Texture 108 Texture Spectrum [20] Texture 8 Daubechies [21] Shape 16 Haar [21] Shape 16 Zernike [22] Shape 36”
- Meta-Recognition: The Theory and Practice of Recognition Score Analysis (2011, background): “Specifically, the three cases k ¼ 0, k > 0, and k 0 correspond to the Gumbel (I), Frechet (II), and Reversed Weibull (III) distributions.”
- Automatic fruit and vegetable classification from images (2010, methodology): “For instance, to train a multi-class classifier using the fusion approach introduced in this paper, with SVM base learner, 48 training examples per class, and the combination of the featur s BIC, CCV, and Unser, it is necessary about one hour in one 2.1GHz machine with 2GB of RAM.”
- A PCA-based similarity measure for multivariate time series (2004, methodology): “The recall-precision graph [9] is then plotted, which has been frequently used to measure the performance of Content Based Image Retrieval (CBIR) systems [34, 19] as well as Information Retrieval (IR) systems.”
- Evaluating the Potential of Texture and Color Descriptors for Remote Sensing Image Retrieval and Classification (2010, methodology): “Border/Interior Pixel Classification (BIC) [14] classifies image pixels as border or interior pixels.”
- Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (2015, background): “The number of connections are (in millions): 2,810 and 5,369 (OverFeatS and OverFeatL, respectively).”