Robust order-based methods for feature description

Gupta, Raj Kumar; Patil, Harshal; Mittal, Anurag

doi:10.1109/cvpr.2010.5540195

Cited by 104 publications

(76 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We select five descriptors that are closely related to ours for comparison (see Table 2). SIFT [2] and DAISY [7] are state-of-the-art gradient-based descriptors, HRI-CSLTP [23] is texture-based, LIOP [20] and MROGH [14] share a similar region division method. Binaries and evaluation codes are downloaded from [14], [15], [20].…”

Section: Evaluation Results and Discussionmentioning

confidence: 99%

“…Chan et al [22] compute LOCP from pairwise ordinal information in an adjacent circular neighborhood. Gupta et al [23] introduce HRI-CSLTP, a combination of relative intensities and ternary patterns. These methods generally obtain good results in various applications.…”

Section: Related Workmentioning

confidence: 99%

“…Spatial-based division approaches are most common, which use a Cartesian grid (e.g. 4 × 4 grid in SIFT [2], CS-LBP [3] and HRI-CSLTP [23]) or a log-polar grid (e.g. GLOH [15] with three radial bins and eight angular directions).…”

Section: Region Divisionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Integration of Intensity Order and Texture for Effective Feature Description

Nguyen

Miyata

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper introduces a novel approach of feature description by integrating the intensity order and textures in different support regions into a compact vector. We first propose the Intensity Order Local Binary Pattern (IO-LBP) operator, which simultaneously encodes the gradient and texture information in the local neighborhood of a pixel. We divide each region of interest into segments according to the order of pixel intensities, build one histogram of IO-LBP patterns for each segment, and then concatenate all histograms to obtain a feature descriptor. Furthermore, multi support regions are adopted to enhance the distinctiveness. The proposed descriptor effectively describes a region at both local and global levels, and thus high performance is expected. Experimental results on the Oxford benchmark and images of cast shadows show that our approach is invariant to common photometric and geometric transformations, such as illumination change and image rotation, and robust to complex lighting effects caused by shadows. It achieves a comparable accuracy to that of state-of-art methods while performs considerably faster.

show abstract

Section: Evaluation Results and Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Integration of Intensity Order and Texture for Effective Feature Description

Nguyen

Miyata

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Such works consider strategies based on intensity ordering and spatial sub-division [15,17,19,18,20,45,53]. While these approaches are invariant to monotonically increasing intensity changes, their success rapidly falls when dealing with photometric artifacts produced by complex surface reflectances or strong shadows.…”

Section: Related Workmentioning

confidence: 99%

DaLI: Deformation and Light Invariant Descriptor

2015

View full text Add to dashboard Cite

Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.

show abstract

“…Their approach improves the feature robustness to challenges such as Gaussian noise and image compression. Gupta and Mittal [26] proposed a descriptor to overcome illumination variations by utilizing intensity orders. Tang et al [27] used a 2D histogram of positions and intensity orders to overcome illumination problems.…”

Section: Image Region Descriptorsmentioning

confidence: 99%

Local Intensity Ordering based Binary Patterns for Image Region Description

Kannan¹,

Kannaiyan²

2017

AIVP

View full text Add to dashboard Cite

Local image region description is a fundamental task for image feature matching in the field of Computer Vision. A good image region descriptor should have the ability to discriminate image features even though the images differ due to photometric variations and geometric transformations. Over these years, many local region descriptors have been proposed to tackle the aforementioned challenges. Achieving rotation invariance in keypoint description is considered one of the main challenges in local region description and matching. Previous approaches proposed to tackle rotation variations depend on unreliable dominant orientation estimation. In this paper, two novel local image region descriptors called Local Intensity Order-based Center Symmetric Local Binary Patterns (LIOCSLBP) and Local Intensity Order-based Orthogonally Combined Local Binary Patterns (LIOOCLBP) are proposed to build rotation invariant local region descriptions. The rotation invariance characteristic of the proposed binary pattern-based local region description is achieved by applying a simple and efficient mechanism called Local Intensity Ordering (LIO). The proposed descriptors use double interest regions for each interest point to improve feature discrimination. In order to further improve the feature discrimination ability RGBLIOCSLBP, RGBLIOOCLBP, HSVLIOCSLBP and HSVLIOOCLBP are also proposed exploiting RGB and HSV color models. Extensive experiments are conducted to evaluate the performance of the proposed descriptors on standard benchmark datasets for image matching, object recognition and scene recognition against the state-of-the-art descriptors. The experimental results show that the proposed descriptors are highly competitive to several stateof-the-art local region descriptors where the proposed descriptors outperformed the comparative approaches in many cases.

show abstract

Robust order-based methods for feature description

Cited by 104 publications

References 21 publications

A Novel Integration of Intensity Order and Texture for Effective Feature Description

A Novel Integration of Intensity Order and Texture for Effective Feature Description

DaLI: Deformation and Light Invariant Descriptor

Local Intensity Ordering based Binary Patterns for Image Region Description

Contact Info

Product

Resources

About