Mitsubishi Electric Corporation

Mikihito Kanno

Yosuke Watanabe

Mitsuhiro Matsumoto

Eri Kataoka

Takamichi Koide

Shunsuke Yamamoto

Hiroshi Yokochi

A similarity calculation unit () treats each of a plurality of classifications as a target classification, and calculates a similarity between a reference feature value, which is a feature value extracted from image data of the target classification, and a recognition feature value, which is a feature value extracted from recognition target data, which is image data to be recognized. An influence calculation unit () calculates an influence on the similarity with regard to each partial image of the recognition target data by taking as input the similarity with regard to each of the classifications and the recognition feature value. A feature identification unit () changes the recognition feature value in accordance with the influence.

Feature identification device, feature identification method, and computer readable medium

In an entry field extraction device, a learning unit obtains a learning model by learning, from images of a plurality of documents, features corresponding to types of the documents. A feature field extraction unit extracts, from an image of a document sample, a feature field being a field indicating a feature corresponding to a type of the document sample, using the learning model. An entry field extraction unit extracts an entry field, being a field of an entry column, from a field that remains in the image of the document sample from which the feature field extracted by the feature field extraction unit has been excluded.

Entry field extraction device and computer readable medium

Growing community of inventors

Tokyo, Japan

Mikihito Kanno