Color indexing

By M. Swain, Dana H. Ballard. 1991

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

LabelMe: A Database and Web-Based Tool for Image Annotation (2008, methodology): “Then, we can use histogram intersection [36] to assign the region of intersection to the polygon with the closest color histogram.”
DeltaPhish: Detecting Phishing Webpages in Compromised Websites (2017, background): “(3) is inspired to the histogram intersection kernel [39].”
On Valid Optimal Assignment Kernels and Applications to Graph Classification (2016, background): “The histogram intersection kernel [20] is defined as Ku(g,h) = ∑t i=1 min{[g]i, [h]i}, t ∈ N, and known to be a valid kernel on R [2, 5].”
SIFT Flow: Dense Correspondence across Scenes and Its Applications (2011, methodology): “Under this framework, we apply SIFT flow to two novel applications: motion prediction from a single static image, where a motion field is hallucinated from a large database of videos, and motion transfer, where a still image is animated using object motions transferred from a similar moving scene.”
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization (2009, unknown): “For 1⁄4 1, we obtain the ordinary histogram intersection measure [20], [21].”
Deep Long-Tailed Learning: A Survey (2021, methodology): “Almost all these approaches extract image features based on Scale Invariant Feature Transform (SIFT) [69], Histogram of Gradient Orientation (HOG) [70], or RGB color histogram [71].”
SGAS: Sequential Greedy Architecture Search (2019, methodology): “) o ) log(jOj 1) (4) Selection Stability. In order to incorporate the history information, we measure the movement of the operation distribution. KullbackLeibler divergence and histogram intersection [43] are two popular methods to detect changes in distribution. For simplicity, we choose the latter”
A review of content-based image retrieval systems in medical applications - clinical benefits and future directions (2004, background): “Several other distance measures do exist for the vector space model such as the city– block distance, the Mahalanobis distance [15] or a simple histogram intersection [60].”
Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY (2020, background): “Implementations can be found, for instance, in [6,7,143–145], which have proven to be worthy as low-level processes in defect detection.”
The Pyramid Match Kernel: Efficient Learning with Sets of Features (2007, methodology): “This is an expected outcome, since the L 1 distance over histograms is directly related to histogram intersection if those histograms have equal masses (Swain and Ballard, 1991), as they do for the bijective matching test: , if m = |Y| = |Z|.”
Supervised pattern classification based on optimum‐path forest (2009, methodology): “Similarly, one may conclude that D6 (BIC in Stehling et al., 2002) outperforms D7, (color histogram in Swain and Ballard, 1991) in B2 (COREL).”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, background): “First introduced as a metric for color-based and content-based image matching [71], [77], it has gained popularity in the saliency community as a simple comparison between pairs of saliency maps.”
Spatial pyramid matching (2009, unknown): “The origin of many of today’s image classiﬁcation systems can be traced to empirical appearance-based methods for recognition, including subspace methods (Turk and Pentland, 1991; Murase and Nayar, 1995) and histograms (Swain and Ballard, 1991; Schiele and Crowley, 2000).”
Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face Recognition (2007, methodology): “One of initial applications of histograms was the work of Swain and Ballard for the identification of 3-D objects [17].”
On the removal of shadows from images (2006, background): “For example, shading, shadows, specularities and inter-reﬂections, as well as changes due to local variation in the intensity or colour of the illumination all make it more difﬁcult to achieve basic visual tasks such as image segmentation [1], object recognition [2] and tracking [3].”
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, background): “[43], histogram of oriented gradients (HOG) [44], and GIST [45].”
Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (2015, background): “Descriptor implementations The implementations of ACC, BIC, LCH, SASI, and LAS descriptors follow the specifications of [26].”