M
Masakazu Matsugu
Researcher at Canon Inc.
Publications - 153
Citations - 4284
Masakazu Matsugu is an academic researcher from Canon Inc.. The author has contributed to research in topics: Image processing & Feature (computer vision). The author has an hindex of 36, co-authored 153 publications receiving 4258 citations.
Papers
More filters
Patent
Object extraction method, and image sensing apparatus using the method
TL;DR: In this paper, an object extraction method for performing processing for extracting and cutting out a specific object from a sensed image at high speed, and an image sensing apparatus using the method.
Patent
Method of extracting image from input image using reference image
TL;DR: In this paper, an image processing method for precisely and automatically recognizing a specific image extraction region to be divided from an input image, and extracting the specific image extract region is presented, where intensity differences of edge data obtained from the input data to extract difference edge data.
Patent
Image recognition/reproduction method and apparatus
Masakazu Matsugu,Katsumi Iijima +1 more
TL;DR: In this paper, an image recognition/reproduction method includes an extraction step of extracting local feature elements of an image, and a selection step of selecting a pair composed of a prescribed local feature element and position information indicative thereof.
Patent
Information processing apparatus, information processing method, pattern recognition apparatus, and pattern recognition method
TL;DR: In a hierarchical neural network, learning necessary for detection of a new feature class is executed by a processing module which has not finished learning yet and includes a plurality of neurons which should learn an unlearned feature class and have an undetermined receptor field structure by presenting a predetermined pattern to a data input layer as mentioned in this paper.
Patent
Image sensing and image processing apparatuses
Tatsushi Katayama,Shigeki Okauchi,Nobuo Fukushima,Masakazu Matsugu,Katsumi Iijima,Masayoshi Sekine,Kotaro Yano,Sunao Kurahashi,Motohiro Ishikawa +8 more
TL;DR: In this article, an image of an object in each of the sensed images is separated from a background image on the basis of the processed image signals, and the separated image signals representing the image of the object enter the image processor 220, where a three-dimensional shape of the objects is extracted based on parameters used upon sensing the images.