In business transactions, to enable computers to recognize coins and other different forms of cur... more In business transactions, to enable computers to recognize coins and other different forms of currency has become an essential process. If the computers are able to perform such recognitions, monetary transactions becomes much easier in all forms of trade. Keeping all the necessary factors in mind we have created a system that could easily identify the numeral in the coins. To limit the scope of this problem, our research focuses on recognizing the exact numeral in a 1-rupee, 2-rupee and 5-rupee Indian coin. The proposed system focuses only on the numerals rather than the use of other images presented in the front and rear side of the coin. In the proposed approach coin images are acquired and numeral in the coins are extracted. Unlike other edge detection process, the coin edges are not sharp and gradually become dull by years of usage. Moreover, numeral edges are same as the background pixel value, which increases the complexity of edge detection process. Hence statistical color threshold method is suggested and implemented in the coin recognition process. After finding the Cartesian co-ordinates of numeral in the coins, the sub image of the numeral is extracted from the given coin image. This sub image is used for character recognition process. In this phase, rotation-invariant character recognition is carried out by multi channel Gabor filter and back propagation network methods. The overall collection contains 72 images in which skewed images are acquired in various angles of rotation varying from 30 degrees onwards.
Neural networks have been used in the development of intelligent recognition systems that simulat... more Neural networks have been used in the development of intelligent recognition systems that simulate our ability recognize patterns. However, rotated objects may cause incorrect identification by recognition systems. Our quick glance provides an overall approximation of a pattern regardless of noise or rotations. This paper proposes that the overall approximation of a pattern can be achieved via pattern averaging prior to training a neural network to recognize that pattern in various rotations. Pattern averaging provides the neural network with “fuzzy” rather than “crisp” representations of the rotated objects, thus, minimizing computational costs and providing the neural network with meaningful learning of various rotations of an object. The proposed method will be used to recognize rotated coins and is implemented to solve an existing problem where slot machines in Europe accept the new Turkish 1 Lira coin as a 2 Euro coin.
In business transactions, to enable computers to recognize coins and other different forms of cur... more In business transactions, to enable computers to recognize coins and other different forms of currency has become an essential process. If the computers are able to perform such recognitions, monetary transactions becomes much easier in all forms of trade. Keeping all the necessary factors in mind we have created a system that could easily identify the numeral in the coins. To limit the scope of this problem, our research focuses on recognizing the exact numeral in a 1-rupee, 2-rupee and 5-rupee Indian coin. The proposed system focuses only on the numerals rather than the use of other images presented in the front and rear side of the coin. In the proposed approach coin images are acquired and numeral in the coins are extracted. Unlike other edge detection process, the coin edges are not sharp and gradually become dull by years of usage. Moreover, numeral edges are same as the background pixel value, which increases the complexity of edge detection process. Hence statistical color threshold method is suggested and implemented in the coin recognition process. After finding the Cartesian co-ordinates of numeral in the coins, the sub image of the numeral is extracted from the given coin image. This sub image is used for character recognition process. In this phase, rotation-invariant character recognition is carried out by multi channel Gabor filter and back propagation network methods. The overall collection contains 72 images in which skewed images are acquired in various angles of rotation varying from 30 degrees onwards.
Neural networks have been used in the development of intelligent recognition systems that simulat... more Neural networks have been used in the development of intelligent recognition systems that simulate our ability recognize patterns. However, rotated objects may cause incorrect identification by recognition systems. Our quick glance provides an overall approximation of a pattern regardless of noise or rotations. This paper proposes that the overall approximation of a pattern can be achieved via pattern averaging prior to training a neural network to recognize that pattern in various rotations. Pattern averaging provides the neural network with “fuzzy” rather than “crisp” representations of the rotated objects, thus, minimizing computational costs and providing the neural network with meaningful learning of various rotations of an object. The proposed method will be used to recognize rotated coins and is implemented to solve an existing problem where slot machines in Europe accept the new Turkish 1 Lira coin as a 2 Euro coin.
Uploads
Papers