Affine-invariant recognition of gray-scale characters using global affine transformation correlation

Wakahara, Toru; Kimura, Yoshimasa; Tomono, Akira

doi:10.1109/34.917573

Cited by 75 publications

(36 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A typical method is the Global Affine Transform method [6]. However, it should be different from pure alignment algorithms in that the retune should rationally make use of the feedback information from the matching or classification procedure.…”

Section: Definition 1: Curse Of Mis-alignment (Hereinafter Abbreviatementioning

confidence: 99%

“…More recently, Martinez has addressed the imprecise localization problem by finding the subspace that represents this error for each of the training images [4]. Note that, perturbation method [5] and global affine transformation correlation [6] has also been proposed to address the similar problem in the OCR field. Yet, these solutions are far from being systematical and deep.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution

Shan¹,

Chang

Gao

et al. 2004

Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings.

View full text Add to dashboard Cite

In this paper, we present the rarely concerned curse of mis-alignment problem in face recognition, and propose a novel mis-alignment learning solution. Mis-alignment problem is firstly e mpirically investigated through systematically evaluating Fisherface' s sensitivity to misalignment on the FERET face database by perturbing the eye coordinates, which reveals that the imprecise localization of the facial landmarks abruptly degenerates the Fisherface system. We explicitly define this problem as curse of mis-alignment for highlighting its graveness. We then analyze the sources of curse of mis-alignment and group the possible solutions into three categories: invariant features, mis-alignment modeling, and alignment retuning. And then we propose a set of measurement combining the recognition rate with the alignment error distribution to evaluate the overall performance of specific face recognition approach with its robustness against the mis-alignment considered. Finally, a novel mis-alignment learning method, named E-Fisherface, is proposed to reinforce the recognizer to model the mis-alignment variations. Experimental results have impressively indicated the effectiveness of the proposed E-Fisherface to tackle the curse of misalignment problem.

show abstract

Section: Definition 1: Curse Of Mis-alignment (Hereinafter Abbreviatementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution

Shan¹,

Chang

Gao

et al. 2004

Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings.

View full text Add to dashboard Cite

show abstract

“…All possible triplets are considered and the affine invariants of the remaining points are computed and stored in a hash table, which is then used in the matching stage. In [51], a global correlation for affine transforms is used to align affine transformed gray-level images. For similarity transforms, [46] introduces an algorithm that determines both the transformation and correspondences between two images.…”

Section: Previous Workmentioning

confidence: 99%

Higher-Dimensional Affine Registration and Vision Applications

Nejhum

Chi

et al. 2011

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-Affine registration has a long and venerable history in computer vision literature, and in particular, extensive work has been done for affine registration in IR 2 and IR 3 . This paper studies affine registration in IR m with m typically ranging from 4 to 12. To justify breaking of this dimension barrier, the first part of the paper describes three novel matching problems that can be formulated and solved as affine point-set registration problems in dimensions greater than three: stereo correspondence under motion, image set matching, and covariant point-set matching, problems that are not only interesting in their own right but also have potential for important vision applications. Unfortunately, most of the existing affine registration algorithms do not generalize easily to higher dimensions due to their inefficiency. Therefore, the second part of this paper develops a novel algorithm for estimating the affine transform between two point sets in IR m . Specifically, the algorithm follows the common approach of iteratively solving the correspondences and transform. The initial correspondences are determined using the novel notion of local spectral features, features constructed from local distance matrices. Unlike many correspondence-based methods, the proposed algorithm is capable of registering point sets of different size, and the use of local features provides some degree of robustness against noise and outliers. The proposed algorithm is validated on a variety of synthetic point sets in different dimensions with varying degrees of deformation and noise, and the paper also shows experimentally that several instances of the aforementioned three matching problems can indeed be solved satisfactorily using the proposed affine registration algorithm.

show abstract

“…This is a typical empirical model and has been developed according to the observation that character patterns often preserve their topologies. Affine deformation models (Wakahara, 1994;Wakahara & Odaka, 1997;Wakahara et al, 2001) and local perturbation models (or image distortion models (Keysers et al, 2004)) are also popular empirical deformation models. While the empirical models generally work well in handwritten character recognition tasks, they are not well-grounded by actual deformations of handwritten characters.…”

Section: Introductionmentioning

confidence: 99%

Statistical Deformation Model for Handwritten Character Recognition

Uchida

2014

Advances in Digital Document Processing and Retrieval

View full text Add to dashboard Cite

Affine-invariant recognition of gray-scale characters using global affine transformation correlation

Cited by 75 publications

References 9 publications

Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution

Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution

Higher-Dimensional Affine Registration and Vision Applications

Statistical Deformation Model for Handwritten Character Recognition

Contact Info

Product

Resources

About