Information processing device

Patent metadata

Field	Value
Publication number	US-2020279166-A1
Application number	US-201816649751-A
Country	US
Kind code	A1
Filing date	Sep 26, 2018
Priority date	Sep 26, 2017
Publication date	Sep 3, 2020
Grant date	—

Abstract

An image recognition device includes: an image processing device that acquires a feature amount from an image; and an identification device that determines whether a prescribed identification object is present in the image, and identifies the identification object. The identification device includes a BNN that has learned the identification object in advance, and performs identification processing by performing a binary calculation with the BNN on the feature amount acquired by the image processing device. Then, the identification device selects a portion effective for identification from among high-dimensional feature amounts output by the image processing device to reduce the dimensions used in identification processing, and copies low-dimensional feature amounts output by the image processing device to increase dimensions.

First claim

1 . An information processing device comprising:
an identification object data acquiring means configured to acquire identification object data; an identification means configured to have learned an identification object using multiple-valued weighting; a duplication means configured to duplicate the identification object data acquired by the identification object data acquiring means; an input means configured to input the identification object data duplicated by the duplication means into the identification means; and an output means configured to output an identification result of being identified by the identification means using the identification object data input by the input means.

2 . The information processing device according to claim 1 , wherein in the identification means, the learning of the identification object is conducted by binarized weighting.

3 . The information processing device according to claim 1 , wherein
the identification means is a binary neural network.

4 . The information processing device according to claim 1 , further comprising:
a feature amount acquiring means configured to acquire a feature amount of an identification object from recording data in which the aforementioned identification object is recorded, wherein the identification object data acquiring means acquires the feature amount acquired by the feature amount acquiring means as an identification object data.

5 . The information processing device according to claim 4 , wherein
the recording data are image data, and the feature amount acquiring means acquires distribution of co-occurrence of a luminance gradient in the image data as the feature amount.

6 . The information processing device according to claim 3 , wherein
the binary neural network is composed using an adder for multiple-valuing and adding the identification object data duplicated by the duplication means, and a counter for calculating an output of the adder.

Assignees

• Equos Res Co Ltd
• Kyushu Inst Tech

Inventors

• Yamada Hideo
• Muramatsu Ryuya
• Shibata Masatoshi
• TAMUKOH Hakaru
• Enokida Shuichi
• Yamasaki Yuta

Classifications

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G06V10/50

  by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis · CPC title

• G06N3/08 Primary

  Learning methods · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06N3/084 Primary

  Backpropagation, e.g. using gradient descent · CPC title