Shadow Codes for Representation of Binary Visual Patterns

• Item type: Journal(1)
• 公開日: 1998-02-15
• タイトル: Shadow Codes for Representation of Binary Visual Patterns
• タイトル / 言語: en
• タイトル: Shadow Codes for Representation of Binary Visual Patterns
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 論文
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• その他タイトル / その他のタイトル: 生体情報処理
• 著者所属: Faculty of Engineering The University of Tokushima
• 著者所属: Systems Engineering Group Fujitsu Limited
• 著者所属: Faculty of Engineering The University of Tokushima
• 著者所属(英): en
• 著者所属(英): Faculty of Engineering, The University of Tokushima
• 著者所属(英): en
• 著者所属(英): Systems Engineering Group, Fujitsu Limited
• 著者所属(英): en
• 著者所属(英): Faculty of Engineering, The University of Tokushima
• 著者名: Julio, Tanomaru; Atsushi, Inubushi; Yoshizo, Takahashi
• 著者名(英): Julio, Tanomaru; Atsushi, Inubushi; Yoshizo, Takahashi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this paper a novel approach to the representation of binary visual patterns is proposed and the applicability of the method to recognition of handwritten patterns by neural network and conventional classifiers is investigated.The proposed approach has been named shadow codes because it is based on shadow projections of pixels of the thinned input image onto the bars of a frame surrounding the image.A number of variations of the method can be devised and the case in which the region of attention consists of a rectangle with orientation given by the principal axes of inertia of the input image is considered in detail.A frame composed by 16 bars classified into three categories is superposed on the attention region containing the thinned input image and each pixel projects a shadow on the nearest bar of each category.While the determination of the attention region is inherently a translation-invariant process scaling invariance is achieved by normalizing and quantzing the shadow lengths resulting in a low-dimensional shadow vector.For a task consisting of the recognition of handwritten numerical characters using both a neural net namely a self-organizing map fine-tuned by learning vector quantization and a conventional classifier high recognition rates were ob-tained confirming the effectiveness of the proposed representation method.Also comparison with other graphical featureextraction techniques yielding feature vectors of the same dimension indicates that although compact shadow codes succeed in preserving information that can be used for recognition.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this paper,a novel approach to the representation of binary visual patterns is proposed,and the applicability of the method to recognition of handwritten patterns by neural network and conventional classifiers is investigated.The proposed approach has been named shadow codes,because it is based on shadow projections of pixels of the thinned input image onto the bars of a frame surrounding the image.A number of variations of the method can be devised,and the case in which the region of attention consists of a rectangle with orientation given by the principal axes of inertia of the input image is considered in detail.A frame composed by 16 bars classified into three categories is superposed on the attention region containing the thinned input image,and each pixel projects a shadow on the nearest bar of each category.While the determination of the attention region is inherently a translation-invariant process,scaling invariance is achieved by normalizing and quantzing the shadow lengths,resulting in a low-dimensional shadow vector.For a task consisting of the recognition of handwritten numerical characters using both a neural net,namely,a self-organizing map fine-tuned by learning vector quantization,and a conventional classifier,high recognition rates were ob-tained,confirming the effectiveness of the proposed representation method.Also,comparison with other graphical featureextraction techniques yielding feature vectors of the same dimension indicates that,although compact,shadow codes succeed in preserving information that can be used for recognition.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 39, 号 2, p. 480-491, 発行日 1998-02-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764