Local association based recognition of two-dimensional objects

Sethi, Ishwar K.; Ramesh, N.

doi:10.1007/bf01212715

Cited by 13 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The indexing structure is based on work presented in [22] and [23]. In contrast to many shape comparison methods, the polygon hashing method maps all local features to a common space, denoted in Figure 2 as the index space.…”

Section: Polygon Hashingmentioning

confidence: 99%

Local shape association based retrieval of infrared satellite images

Sethi

2005

Seventh IEEE International Symposium on Multimedia (ISM'05)

View full text Add to dashboard Cite

show abstract

Section: Polygon Hashingmentioning

confidence: 99%

Local shape association based retrieval of infrared satellite images

Sethi

2005

Seventh IEEE International Symposium on Multimedia (ISM'05)

View full text Add to dashboard Cite

show abstract

“…Then the two highest results, called here W, 1 and W, 2 associated to the masks m 1 and m 2 , respectively, are determined. If the highest sum, always assumed to be W,I' is equal to zero then the center pixel of the window does necessarily not belong to the path, and the output pixel is set to 0.…”

Section: Pathfinder IImentioning

confidence: 99%

“…A second condition to be analyzed is when W, 1 and W, 2 have an equal value and m 1 and m 2 are adjacent (adjacent paths are those which are different from one another by just one pixel). This situation is considered a stalemate, because the two different pixels in each path could be equally labeled contour pixels.…”

Section: Pathfinder IImentioning

confidence: 99%

“…Polygonal modeling has traditionally been one of the most popular methods for shape representation and still is largely used in applications where shape recognition of two-dimensional objects or surfaces is needed [1,2]. Currently a lot of attention is paid to image sequence and video coding due to the increasing importance of high speed multimedia applications [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

“…Currently a lot of attention is paid to image sequence and video coding due to the increasing importance of high speed multimedia applications [1][2][3]. In fact, modelbased image coding is a powerful technique for compressing head-shoulder images, as in the MPEG-4 sequences imposing very low bitrate coding.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

VLSI Implementation of Contour Extraction from Real Time Image Sequences

Melcher¹,

Naviner²,

Carvalho³

et al. 1997

VLSI: Integrated Systems on Silicon

View full text Add to dashboard Cite

In this work a parallel architecture is proposed for VLSI implementation of a dataflow algorithm for 20 boundary (or contour) detection. The algorithm works on the gradient image and uses a set of primitive paths to generate all possible contour paths on a neighborhood defined by a 5x5 window. The objective is to determine whether or not the neighborhood central pixel belongs to a continuous boundary line passing across the window. Test results show that one-pixel wide continuous boundary lines can be extracted using this algorithm.

show abstract

Matching Occluded Objects Invariant to Rotations, Translations, Reflections, and Scale Changes

El-Sonbaty

Ismail

2003

Image Analysis

View full text Add to dashboard Cite

In this paper, a new algorithm for recognizing partially occluded objects is introduced. The proposed algorithm is based on searching for first three matched connected lines in both occluded and model objects, then left and right lines in both occluded and model objects are marked as matched lines as long as they have the same relations of distance ratio and angle to the last matched and connected lines. The process is repeated until there is no more three matched connected lines. The ratio_test is then performed to detect scattered matched points and lines. The new algorithm is invariant to translations, rotations, reflections and scale changes and has computational complexity of O(m.n).

show abstract

Local association based recognition of two-dimensional objects

Cited by 13 publications

References 22 publications

Local shape association based retrieval of infrared satellite images

Local shape association based retrieval of infrared satellite images

VLSI Implementation of Contour Extraction from Real Time Image Sequences

Matching Occluded Objects Invariant to Rotations, Translations, Reflections, and Scale Changes

Contact Info

Product

Resources

About