Object Orientation Detection And Character-Recognition Using Optimal Feedforward Network And Kohonen Feature Map

Date

1992

Author

Baykal, Nazife

Metadata

Show full item record

Item Usage Stats

180
views

0
downloads

A neural network model, namely, Kohonen's Feature Map, together with the optimal feedforward network is used for variable font machine printed character recognition with tolerance to rotation, shift in position, and size errors. The determination of object orientation is found using the many rotated versions of individual symbols. Orientations are detected from printed text, but no knowledge of the context is used. The optimal Bayesian detector is derived, and it is shown that the optimal detector has the form of a feedforward network. This network together with the learning vector quantization (LVQ) approach is able to implement an inspection system which determines the orientation of the fonts. After the size normalization, rotation, and component finding process as a preprocessing step, the text becomes the input for the feature map. The feature map is trained first in an unsupervised manner. The algorithm is then adapted for supervised learning using improved LVQ technique. Rectangular and minimal spanning tree (MST) neighborhood topologies are experimented with. The results are encouraging, 87% of the characters of various fonts are correctly recognized even though the pattern is distorted in shape and transformed in a shift, size, and rotation invariant manner. Experimental results and comparisons are described.

Subject Keywords

3RD ANNUAL INTERNATIONAL CONF ON APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS

URI

https://hdl.handle.net/11511/52499

DOI

https://doi.org/10.1117/12.140010

Collections

Graduate School of Informatics, Conference / Seminar

Suggestions

OpenMETU
Core

Object Detection with Convolutional Context Features Kaya, Emre Can; Alatan, Abdullah Aydın (2017-01-01) A novel extension to Huh B-ESA object detection algorithm is proposed in order to learn convolutional context features for determining boundaries of objects better. For input images, the hypothesis windows and their context around those windows are learned through convolutional layers as two parallel networks. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection ben...
Utilization of dense depth information for monoview object detection and instance segmentation Çakırgöz, Çağlayan Can; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2022-5-10) Object detection aims for detecting objects of certain classes in an image by bounding them in rectangular boxes whereas instance segmentation tries to detect objects in pixel level. Deep learning techniques, which have shown great improvements over the last decade, are utilized in these topics as well, and a significant success is achieved against the traditional methods. Similar improvements can be observed in dense depth estimation which deals with deducing dense information of a scene from a single imag...
Neural Network Based Beamforming Using a Cylindrical Patch Array Gureken, Murat; Dural Ünver, Mevlüde Gülbin; Caylar, Selcuk (2009-06-05) A neural network algorithm is implemented for beamforming problem. The cylindrical array with M directive MPA elements has a full coverage of 360deg. Considering the total angular coverage of 360deg in terms of 12 sectors of 30deg each and activating only some MPA elements in the related sector reduces the training set and increases the performance of the beamformer. Increasing the number of targets in different sectors has no effect on the performance of the beamformer.
E3D-D2D: EMBEDDING IN 3D, DETECTION IN 2D THROUGH PROJECTIVE INVARIANTS Yasaroglu, Yagiz; Alatan, Abdullah Aydın (2014-10-30) A novel watermarking method is presented in which the data embedded into a 3D model is extracted from an arbitrary 2D view by using a perspective projective invariant. The data is embedded into 3D positions of selected interest points on a 3D mesh. Determining the interest point modification vectors for ensuring watermark detection constitutes an important part of the proposed method. Different watermark embedding schemes based on optimization of the watermark function are implemented and evaluated. Another...
Domain compression via anisotropic metamaterials designed by coordinate transformations Ozgun, Ozlem; Kuzuoğlu, Mustafa (Elsevier BV, 2010-02-01) We introduce a spatial coordinate transformation technique to compress the excessive white space (i.e. free-space) in the computational domain of finite methods. This approach is based on the form-invariance property of Maxwell's equations under coordinate transformations. Clearly, Maxwell's equations are still satisfied inside the transformed space, but the medium turns into an anisotropic medium whose constitutive parameters are determined by the coordinate transformation. The proposed technique can be em...

Citation Formats

N. Baykal, “Object Orientation Detection And Character-Recognition Using Optimal Feedforward Network And Kohonen Feature Map,” 1992, vol. 1709, p. 292, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52499.