CSIFT: A SIFT Descriptor with Color Invariant Characteristics

By Alaa E. Abdel-Hakim, Aly A. Farag. Computer Vision and Pattern Recognition, 2006

639 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ca7b979c61be9140961fa6dfa56b12e4f98b0c2b

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Distance based similarity models for content based multimedia retrieval (2013, background): “Whereas low-dimensional feature descriptors include for instance the information about the position, the color, or the texture [Tamura et al., 1978] of a feature, more complex high-dimensional feature descriptors such as SIFT [Lowe, 2004] or Color SIFT [Abdel-Hakim and Farag, 2006] summarize the loc”
Predicting Actions from Static Scenes (2014, methodology): “In the rest of this section we use the format <descriptor> <encoding technique> to denote image representation techniques, e.g. CSIFT FV as Fisher Vector encoding for CSIFT descriptors.”
Large-Margin Multi-Modal Deep Learning for RGB-D Object Recognition (2015, methodology): “SURF [3], texton [34] and color histogram [1] are used to de-”
Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review (2017, methodology): “As CSIFT uses color invariants for building the descriptor, it is robust to photometric changes [2].”
Illumination Invariant Imaging : Applications in Robust Vision-based Localisation , Mapping and Classification for Autonomous Vehicles (2014, background): “Approaches to incorporate colour histogram information into descriptors have produced limited improvements in performance [12].”
Evaluating Color Descriptors for Object and Scene Recognition (2010, background): “To increase photometric invariance and discriminative power, color descriptors have been proposed which are robust against certain photometric changes [12], [13], [14], [15], [16].”
Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline (2018, methodology): “After segmentation, current highperformance methods always train a deep convolutional neural network [38] or utilize features around LP characters like SIFT [39].”
Performance evaluation of local colour invariants (2009, neutral): “Furthermore, note that two extra methods from literature have been added, being the hue-colourSIFT descriptor [53], and the hsv-colour-SIFT descriptor [54].”
Recognition of Multiple-Food Images by Detecting Candidate Regions (2012, methodology): “In addition to SIFT, we also extract CSIFT [14] which is extracted SIFT from a RGB color space.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “For instance, CSIFT (Abdel-Hakim and Farag 2006) uses additional color information to enhance the discrimination, and ASIFT (Morel and Yu 2009) simulates all image views obtainable by varying the two camera axis orientation parameters for fully affine invariance.”
Convolutional-Recursive Deep Learning for 3D Object Classification (2012, background): “There have been some attempts to modify these features to colored images via color histograms [23] or simply extending SIFT to the depth channel [2].”
Automatic landslide detection from remote-sensing imagery using a scene classification method based on BoVW and pLSA (2013, background): “Previously, both grey descriptors (Lowe 2004; Lazebnik, Schmid, and Ponce 2005) and colour descriptors (Abdel-Hakim and Farag 2006; Bosch, Zisserman, and Munoz 2006) have been used to represent images.”
Recent advances and trends in visual tracking: A review (2011, methodology): “In [32], color invariants had been ﬁrst used as an input to the SIFT descriptor, which leads to a CSIFT descriptor that is scale-invariant with respect to light intensity.”
Intelligent multi-camera video surveillance: A review (2013, background): “, 2005; Varma and Zisserman, 2005; Leung and Malik, 1999), and local descriptors, such as SIFT (Lowe, 2004), color SIFT (Abdel-Hakim and Farag, 2006), Local Binary Patterns (LBP) (Ojala et al.”
Description of Interest Regions with Center-Symmetric Local Binary Patterns (2006, background): “For some interesting recent work on interest region description done after this study, see [8,9,10,11].”
Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature (2015, background): “Arora et al. [3] presented a comparative study for the task of style classiﬁcation, which evaluated low-level features, such as SIFT and Color SIFT [1], versus semantic-level features, namely Classemes [29], which encodes object presence in the image.”
A review of multimodal image matching: Methods and applications (2021, neutral): “Many variants of SIFT or SURF tend to obtain better performance in computation efficiency, robustness, and discrimination, such as using color or affine information [161,199] or a square root kernel measurement [200] and gradient statistic in different domain sizes [201], just to name a few.”