An optimum solution for scale-invariant object recognition based on the multiresolution approximation

Yoon, Sung Ho; Kim, Jung Ho; Alexander, W.E.; Park, Seong M.; Sohn, Kwanghoon

doi:10.1016/s0031-3203(97)00111-8

Cited by 11 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lot of researchers pay attention to this subject, and many methods are developed. Recently, new methods in accordance with the wavelet-based approach are made [23,[25][26][27]. In this section, two of them are introduced [26,27].…”

Section: Invariant Representation Of Patternsmentioning

confidence: 99%

“…[27], where the theory of the continuous multiresolution approximation (CMA) is established, and a fast algorithm for the continuous wavelet transform (CWT) is implemented as well. The CMT is a vehicle for scale-invariant matching or coarse-to-fine matching.…”

Section: Scale-invariant Based On the Multiresolution Approximationmentioning

confidence: 99%

“…Ref. [27] proposes good representations for boundary-based object matching. The representations obtained by the CMA allow us to recognize objects in the presence of noise, occlusion, scale variation, rotation, and translation.…”

Section: Scale-invariant Based On the Multiresolution Approximationmentioning

confidence: 99%

“…N Analysis and detection of singularities with wavelets [10][11][12][13][14][15][16][17][18][19][20], N Wavelet descriptors for shapes of the objects [12,[21][22][23][24], N Invariant representation of patterns [25][26][27], N Handwritten and printed character recognition [16,21,22,24,[28][29][30], N Texture analysis and classification [25,[31][32][33][34], N Image indexing and retrieval [35][36][37][38][39][40], N Classification and clustering [41][42][43], N Document analysis with wavelets [17,[44][45][46][47], N Iris pattern recognition [48], N Face recognition using wavelet transform [49][50]…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Status of pattern recognition with wavelet analysis

Tang

2008

Front. Comput. Sci. China

View full text Add to dashboard Cite

Pattern recognition has become one of the fastest growing research topics in the fields of computer science and electrical and electronic engineering in the recent years. Advanced research and development in pattern recognition have found numerous applications in such areas as artificial intelligence, information security, biometrics, military science and technology, finance and economics, weather forecast, image processing, communication, biomedical engineering, document processing, robot vision, transportation, and endless other areas, with many encouraging results. The achievement of pattern recognition is most likely to benefit from some new developments of theoretical mathematics including wavelet analysis. This paper aims at a brief survey of pattern recognition with the wavelet theory. It contains the following respects: analysis and detection of singularities with wavelets; wavelet descriptors for shapes of the objects; invariant representation of patterns; handwritten and printed character recognition; texture analysis and classification; image indexing and retrieval; classification and clustering; document analysis with wavelets; iris pattern recognition; face recognition using wavelet transform; hand gestures classification; character processing with B-spline wavelet transform; wavelet-based image fusion, and others.

show abstract

Section: Invariant Representation Of Patternsmentioning

confidence: 99%

Section: Scale-invariant Based On the Multiresolution Approximationmentioning

confidence: 99%

Section: Scale-invariant Based On the Multiresolution Approximationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Status of pattern recognition with wavelet analysis

Tang

2008

Front. Comput. Sci. China

View full text Add to dashboard Cite

show abstract

“…There have come forth a lot of methods (see, for example, Crowley and Sanderson, 1987;Gopalan and David, 1994;Rowley et al, 1998;Yoone et al, 1998;Gavrila and Philomin, 1999;Stone et al, 1999;Keren et al, 2001;Tsai and Chiang, 2002;and their references). Among these methods, multitemplate method (Gavrila and Philomin, 1999;Keren et al, 2001) and methods based on rotation-invariant correlation (Gopalan and David, 1994;Rowley et al, 1998;Tsai and Chiang, 2002) have long been used to deal with the in-plane rotation problem.…”

Section: Introductionmentioning

confidence: 99%

Lie group method: A new approach to image matching with arbitrary orientations

Ying

Qiao

2010

Int J Imaging Syst Tech

View full text Add to dashboard Cite

In this article, we develop a new method for image matching of any two images with arbitrary orientations. The idea comes from the workpiece localization in machining industry. We first describe an image as a 3D point set other than the common 2D function f(x, y), then, making the sets corresponding to the compared images form solid surfaces, we equivalently translate the matching problem into an optimization problem on the Lie group SE(3). Through developing a kind of steepest descent algorithms on a general Lie group, we present an practical algorithm for matching problem. Simulations of eye detection and face detection are presented to show the feasibility and efficiency of the proposed algorithm. Key words: template matching; Lie groups; Lie algebras; steepest descent algorithm I. INTRODUCTIONTemplate matching is a commonly used technique in many fields, such as face detecting (Yang et al., 2002), biophysical data processing (Yao et al., 2003) and photogrammetry and remote sensing (Keipke, 1996), etc. In template matching, we are given a template image T to find the desired pattern in a test image P (usually much larger) by sliding the window of T in a pixel-by-pixel basis and meanwhile computing the correlation between T and the window-overlapping part of P (Theodoridis and Koutroumbas, 2003). However, this pixel-bypixel template matching is very time-consuming. In fact, it has been shown that for a test image of size R 3 S and a template image of size M 3 N, the computational complexity is O(M 3 N 3 R 3 S), provided the orientations in both compared images T and P are coincident (Tsai and Chiang, 2002). The computational complexity will become much higher when the orientation of the pattern we desire to find is unknown, for instance, when rotation (in-plane and/or out-ofplane rotation) is present in the test image. In practice, it is almost impossible to employ the pixel-by-pixel template matching to robustly deal with the presence of arbitrary rotation.

show abstract