Optical character recognition by the method of moments

Cash, Glenn L.; Hatamian, M.

doi:10.1016/s0734-189x(87)80183-4

Cited by 122 publications

(33 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since the introduction by Hu in 1961, this method of moment invariant has become one of the most important techniques for image analysis (Teh and Chin, 1988). Its successful applications have been reported in areas such as aircraft identification (Dudani et al, 1977), remotely sensed data matching (Wong and Hall, 1978), character recognition (Cash and Hatamian, 1987), edge detection (Ghosal and Mehrotra, 1993) and so on (Ko et al, 2000;Petrakis et al, 2002;Shih and Chen, 2002;Zhang and Lu, 2002). Detailed steps of moment transformation are described later.…”

Section: Preliminariesmentioning

confidence: 99%

Trademark image retrieval by distance–angle pair‐wise histogram

Lin

Shie

Chen

et al. 2005

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Because of the continuously increasing number of registered trademarks, it is more and more difficult to design and register a new trademark without conflicting with the registered trademarks or logos. Traditionally, trademark indexing by text description is applied for trademark image databases. However, as more and more trademarks have been designed with complex content, describing a trademark only with text description is not an efficient approach any more. Therefore, trademark indexing by its content is required for comparing, retrieving and classifying similar trademarks. In this article, a content-based trademark image retrieval system is proposed. The newly designed trademarks can be avoided from being similar with the registered ones with such a system. This scheme makes use of the distance-angle pair-wise histogram as a feature vector of trademark shape for retrieving similar registered trademarks. Several momentbased trademark retrieval schemes have also been implemented in computer simulations. Experiments have been conducted on registered trademark databases. Impressive results are shown to demonstrate the robustness of the proposed scheme. Moreover, it is quite simple to construct the distance-angle pair-wise histogram for a trademark object. Therefore, the retrieval speed is acceptable and the system can be accessed through internet on a web browser.

show abstract

Section: Preliminariesmentioning

confidence: 99%

Trademark image retrieval by distance–angle pair‐wise histogram

Lin

Shie

Chen

et al. 2005

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Since introduced by Hu in 1961, the method of moment invariant has become one of the most important techniques for image analysis. Its successful applications have been reported in areas such as aircraft identification, remotely sensed data matching, character recognition, edge detection, pavement distress classification, breast cancer detection, and so on (Cash and Hatamian, 1987;Cheng et al, 1998;H. Chou and Chen, 1990;J.…”

Section: The Proposed Color Plane Momentmentioning

confidence: 99%

Image indexing by Color Plane Moment

Lin

Chen

Yang

2002

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Among the features of content-based image retrieval, color features provide important clues to search similar image contents. In addition to color, there exists more information in the image. In this article, we propose a new method for content-based image retrieval: Color Plane Moment (CPM). This method combines colors' content and their spatial distribution to improve image query results. It integrates the ideas of color histogram, backprojection, and moments. The CPM uses backprojection as one of the image preprocessing methods and computes the invariant moments with those dominant color plane images after preprocessing. There are several dominant colors chosen by color histogram in an image, and each can be expressed by seven invariant moment values that represent spatial distribution of those dominant color planes, respectively. Simulation results demonstrate that the proposed technique outperforms the other techniques.

show abstract

“…A metamorphosis animation from a man to a woman was performed by creating intermediate models and relying on linear interpolation of the moments of inertia of the simulated body parts. Another useful application of moments can be found, for example, in optical character recognition systems [1]. Being intrinsic, moments of inertia can clearly be used in other object recognition applications; see Ref.…”

Section: Introductionmentioning

confidence: 99%

Exact and efficient computation of moments of free-form surface and trivariate based geometry

Soldea

Elber

Rivlin

2002

Computer-Aided Design

View full text Add to dashboard Cite

Two schemes for computing moments of free-form objects are developed and analyzed. In the ®rst scheme, we assume that the boundary of the analyzed object is represented using parametric surfaces. In the second scheme, we represent the boundary of the object as a constant set of a trivariate function. These schemes rely on a pre-computation step which allows fast re-evaluation of the moments when the analyzed object is modi®ed. Both schemes take advantage of a representation that is based on the B-spline blending functions. q

show abstract

Optical character recognition by the method of moments

Cited by 122 publications

References 7 publications

Trademark image retrieval by distance–angle pair‐wise histogram

Trademark image retrieval by distance–angle pair‐wise histogram

Image indexing by Color Plane Moment

Exact and efficient computation of moments of free-form surface and trivariate based geometry

Contact Info

Product

Resources

About