The Experts below are selected from a list of 100803 Experts worldwide ranked by ideXlab platform

Minoru Fukumi - One of the best experts on this subject based on the ideXlab platform.

  • Rotation-invariant Neural Pattern recognition system estimating a rotation angle
    IEEE Transactions on Neural Networks, 1997
    Co-Authors: Minoru Fukumi, Sigeru Omatu, Yoshikazu Nishikawa
    Abstract:

    A rotation-invariant Neural Pattern recognition system, which can recognize a rotated Pattern and estimate its rotation angle, is considered. It is well-known that humans sometimes recognize a rotated form by means of mental rotation. The occurrence of mental rotation can be explained in terms of the theory of information types. Therefore, we first examine the applicability of the theory to a rotation-invariant Neural Pattern recognition system. Next, we present a rotation-invariant Neural network which can estimate a rotation angle. The Neural network consists of a preprocessing network to detect the edge features of input Patterns and a trainable multilayered network. Furthermore, a rotation-invariant Neural Pattern recognition system which includes the rotation-invariant Neural network is proposed. This system is constructed on the basis of the above-mentioned theory. Finally, it is shown that, by means of computer simulations of a binary Pattern and a coin recognition problem, the system is able to recognize rotated Patterns and estimate their rotation angle.

  • Rotation-invariant Neural Pattern recognition system with application to coin recognition
    IEEE Transactions on Neural Networks, 1992
    Co-Authors: Minoru Fukumi, Sigeru Omatu, Fumiaki Takeda, Toshihisa Kosaka
    Abstract:

    In Pattern recognition, it is often necessary to deal with problems to classify a transformed Pattern. A Neural Pattern recognition system which is insensitive to rotation of input Pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation Pattern recognition. >

Sigeru Omatu - One of the best experts on this subject based on the ideXlab platform.

  • Rotation-invariant Neural Pattern recognition system estimating a rotation angle
    IEEE Transactions on Neural Networks, 1997
    Co-Authors: Minoru Fukumi, Sigeru Omatu, Yoshikazu Nishikawa
    Abstract:

    A rotation-invariant Neural Pattern recognition system, which can recognize a rotated Pattern and estimate its rotation angle, is considered. It is well-known that humans sometimes recognize a rotated form by means of mental rotation. The occurrence of mental rotation can be explained in terms of the theory of information types. Therefore, we first examine the applicability of the theory to a rotation-invariant Neural Pattern recognition system. Next, we present a rotation-invariant Neural network which can estimate a rotation angle. The Neural network consists of a preprocessing network to detect the edge features of input Patterns and a trainable multilayered network. Furthermore, a rotation-invariant Neural Pattern recognition system which includes the rotation-invariant Neural network is proposed. This system is constructed on the basis of the above-mentioned theory. Finally, it is shown that, by means of computer simulations of a binary Pattern and a coin recognition problem, the system is able to recognize rotated Patterns and estimate their rotation angle.

  • Rotation-invariant Neural Pattern recognition system with application to coin recognition
    IEEE Transactions on Neural Networks, 1992
    Co-Authors: Minoru Fukumi, Sigeru Omatu, Fumiaki Takeda, Toshihisa Kosaka
    Abstract:

    In Pattern recognition, it is often necessary to deal with problems to classify a transformed Pattern. A Neural Pattern recognition system which is insensitive to rotation of input Pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation Pattern recognition. >

Yoshikazu Nishikawa - One of the best experts on this subject based on the ideXlab platform.

  • Rotation-invariant Neural Pattern recognition system estimating a rotation angle
    IEEE Transactions on Neural Networks, 1997
    Co-Authors: Minoru Fukumi, Sigeru Omatu, Yoshikazu Nishikawa
    Abstract:

    A rotation-invariant Neural Pattern recognition system, which can recognize a rotated Pattern and estimate its rotation angle, is considered. It is well-known that humans sometimes recognize a rotated form by means of mental rotation. The occurrence of mental rotation can be explained in terms of the theory of information types. Therefore, we first examine the applicability of the theory to a rotation-invariant Neural Pattern recognition system. Next, we present a rotation-invariant Neural network which can estimate a rotation angle. The Neural network consists of a preprocessing network to detect the edge features of input Patterns and a trainable multilayered network. Furthermore, a rotation-invariant Neural Pattern recognition system which includes the rotation-invariant Neural network is proposed. This system is constructed on the basis of the above-mentioned theory. Finally, it is shown that, by means of computer simulations of a binary Pattern and a coin recognition problem, the system is able to recognize rotated Patterns and estimate their rotation angle.

Toshihisa Kosaka - One of the best experts on this subject based on the ideXlab platform.

  • Rotation-invariant Neural Pattern recognition system with application to coin recognition
    IEEE Transactions on Neural Networks, 1992
    Co-Authors: Minoru Fukumi, Sigeru Omatu, Fumiaki Takeda, Toshihisa Kosaka
    Abstract:

    In Pattern recognition, it is often necessary to deal with problems to classify a transformed Pattern. A Neural Pattern recognition system which is insensitive to rotation of input Pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation Pattern recognition. >

Shanthini Sockanathan - One of the best experts on this subject based on the ideXlab platform.

  • a requirement for retinoic acid mediated transcriptional activation in ventral Neural Patterning and motor neuron specification
    Neuron, 2003
    Co-Authors: Bennett G Novitch, Hynek Wichterle, Thomas M Jessell, Shanthini Sockanathan
    Abstract:

    Abstract The specification of neuronal fates in the ventral spinal cord depends on the regulation of homeodomain (HD) and basic-helix-loop-helix (bHLH) proteins by Sonic hedgehog (Shh). Most of these transcription factors function as repressors, leaving unresolved the link between inductive signaling pathways and transcriptional activators involved in ventral neuronal specification. We show here that retinoid signaling and the activator functions of retinoid receptors are required to Pattern the expression of HD and bHLH proteins and to specify motor neuron identity. We also show that fibroblast growth factors (FGFs) repress progenitor HD protein expression, implying that evasion of FGF signaling and exposure to retinoid and Shh signals are obligate steps in the emergence of ventral Neural Pattern. Moreover, joint exposure of Neural progenitors to retinoids and FGFs suffices to induce motor neuron differentiation in a Shh-independent manner.