Robust normalization of silhouettes for recognition applications

Cortadellas, Javier; Amat, Josep; Torre, Fernando De la

doi:10.1016/j.patrec.2003.12.003

Cited by 28 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last row, the new method aligns the fist with the full hand better than the traditional method because the latter normalizes the size of both shapes to unit area and results that the fist looks larger than the full hand in the alignment. The second experiment compares the robustness of localization and orientation estimation between the proposed method and [1]. Fig.…”

Section: Resultsmentioning

confidence: 99%

“…In principal, our method can be extended to normalize shapes in higher dimensions because of the nature of implicit representations. Experiments of normalization of different shape classes are presented with comparison to previous work [1]. The results demonstrate that our approach offers a more robust and general solution to shape normalization.…”

Section: Introduction and Related Workmentioning

confidence: 95%

“…With the way we have defined the axis of a shape so far, we would get the same result if we rotated the shape 180 degrees and then recomputed the axis. One solution to resolve the ambiguity is to let the orientation of the shape point towards the half plane that contains the region of the shape with larger weighted area [1]. Here we choose the direction which is closer to the "average" direction of gradient vectors of the implicit level set function, which is defined as the weighted sum of the normalized gradient vectors of φ:…”

Section: Robust Shape Normalizationmentioning

confidence: 99%

“…shape deformations. Based on the traditional method, [1] proposed a robust estimation method for shape orientation. In this work, we are motivated by some classes of shapes, such as the silhouettes of animals (Fig.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Robust shape normalization based on implicit representations

Jiang

Tomasi

2008

2008 19th International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 95%

Section: Robust Shape Normalizationmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Robust shape normalization based on implicit representations

Jiang

Tomasi

2008

2008 19th International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…It is usually used as an initial step in many image processing operations. Due to the importance of the shape orientation, several techniques [21][22][23][24][25][26][27][28] are proposed to solve this problem based on different concepts like geometric moments, complex moments and principal component analysis. Some of them are area based which takes into account all points that belong to the shape.…”

Section: Shape Orientationmentioning

confidence: 99%

Rotation-Invariant Neural Pattern Recognition System Using Extracted Descriptive Symmetrical Patterns

Abdel-Kader¹,

Ramadan²,

Zaki³

et al. 2012

IJACSA

View full text Add to dashboard Cite

Abstract-In this paper a novel rotation-invariant neural-based pattern recognition system is proposed. The system incorporates a new image preprocessing technique to extract rotationinvariant descriptive patterns from the shapes. The proposed system applies a three phase algorithm on the shape image to extract the rotation-invariant pattern. First, the orientation angle of the shape is calculated using a newly developed shape orientation technique. The technique is effective, computationally inexpensive and can be applied to shapes with several nonequally separated axes of symmetry. A simple method to calculate the average angle of the shape's axes of symmetry is defined. In this technique, only the first moment of inertia is considered to reduce the computational cost. In the second phase, the image is rotated using a simple rotation technique to adapt its orientation angle to any specific reference angle. Finally in the third phase, the image preprocessor creates a symmetrical pattern about the axis with the calculated orientation angle and the perpendicular axis on it. Performing this operation in both the neural network training and application phases, ensures that the test rotated patterns will enter the network in the same position as in the training. Three different approaches were used to create the symmetrical patterns from the shapes. Experimental results indicate that the proposed approach is very effective and provide a recognition rate up to 99.5%.

show abstract