A Neural Network for Recognizing Rotation, Translation and Scale-Change Transformation of Patterns

识别图案旋转、平移和尺度变化的神经网络

• 批准号: 04650332
• 负责人: SUZAKI Kenichi
• 金额: $ 0.38万
• 依托单位: FUKUOKA INSTITUTE OF TECHNOLOGY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (C)
• 财政年份: 1992
• 资助国家: 日本
• 起止时间: 1992 至 1993
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-04650332/
• 关键词: neural Network; back-propagation method; rotation-invariant; translation-invariant; scale-change-invariant; copy-learning; three-layr; recognition; 誤差〓伝播法; 回転,位置ずれ,拡大縮小; 学習・並びに認識; パターン認識; 複写学習モデル; パターン回転モデル; 回転マトリックス; パターン作成

In character recognition, certain basic patterns need to be recognized correctly as the same patterns even if the patterns undergo transformations such as (1) scale-change, (2) translation, and (3) rotation. We developed three type of neural network model capable of learning and recognizing scale-change, translation and rotation of patterns. They are (1) A Rotation Invariant Learning Model ; (2) A Pattern Rotation Model ; (3) A Copy-Learning Model. These are all three layr neural networks. Each of the three models features a simple network structure of a compact size, and a substantially reduced time required for learning and recognition.

在字符识别中，某些基本图案需要被正确地识别为相同的图案，即使这些图案经历了诸如(1)比例改变、(2)平移和(3)旋转的变换。我们开发了三种类型的神经网络模型，能够学习和识别模式的尺度变化、平移和旋转。它们是(1)旋转不变学习模型；(2)模式旋转模型；(3)抄袭学习模型。这些都是三层神经网络。这三种模型都具有紧凑的简单网络结构，并大大减少了学习和识别所需的时间。

项目成果

Kenichi Suzaki,Shinji Araya,Ryozo Nakamura: "Three-layer Neural Network Models for Rotated Patterns Recognition" IFIP 12th World Computer Congress. 1. 667-673 (1992)

Kenichi Suzaki、Shinji Araya、Ryozo Nakamura：“用于旋转模式识别的三层神经网络模型”IFIP 第十二届世界计算机大会。

Kenichi Suzaki,Shinji Araya,Ryozo Nakamura: "A Copy-Learning Model for Recognizing Pattern Rotated at Various Angles" Trans.IEICE. E76-A. 1207-1211 (1993)

Kenichi Suzaki、Shinji Araya、Ryozo Nakamura：“用于识别各种角度旋转的图案的复制学习模型”Trans.IEICE。

Suzaki, Arayama, Nakamura: "An Experiment on Generalization of BP-Network in Rotated Patterns" Trans.IEE Japan. Vol.113-c, No.5. 366-367 (1993)

Suzaki、Arayama、Nakamura：“旋转模式中 BP 网络的泛化实验” Trans.IEE Japan。

須崎 健一: "位置ずれ・回転パターンを認識するニューラルネットワーク" 情報処理学会論文誌. 34. 2277-2281 (1993)

Kenichi Susaki：“用于识别错位和旋转模式的神经网络”，日本信息处理学会汇刊 34. 2277-2281 (1993)。

Suzaki, Arayama, Nakamura: "Three-layr Neural Network Models for Rotated Patterns Recognition" IFIP 12 th World Computer Congress. 1. 667-673 (1992)

Suzaki、Arayama、Nakamura：“用于旋转模式识别的三层神经网络模型”IFIP 第 12 届世界计算机大会。