Patent
Image recognition device, image recognition method, computer program, and product monitoring system
Jinhui Chen,Takashi Kamihigashi,Ito Munehiko,Yasuo Takatsuki +3 more
- 25 Oct 2018
1
TL;DR: In this article, a hierarchical neural network was used to improve the accuracy of image recognition by a hierarchical NN, where the data processing performed by the data generation unit is process of imparting at least one invariance of rotation and inversion to the original image.
read more
Abstract: PROBLEM TO BE SOLVED: To provide an image recognition device, an image recognition method, a computer program, and a product monitoring system improving accuracy of image recognition by a hierarchical neural networkSOLUTION: An image recognition device 10 comprises an arithmetic processing unit 1 having a data generation unit 3 performing predetermined data processing on an original image to generate input data, and an image processing unit 2 having a hierarchical neural network recognizing a type of object included in the generated input data The image processing unit performs process of learning a parameter of the network based on a recognition result of the network if the original image is a sample image, and performs process of outputting the recognition result of the network if the original image is a target image to be recognized The data processing performed by the data generation unit is process of imparting at least one invariance of rotation and inversion to the original imageSELECTED DRAWING: Figure 1
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Model integration device, method, and program, and inference, inspection, and control system
Yonetani Ryo,Suwa Masaki,Miyaura Hiroyuki +2 more
- 23 Jul 2020
TL;DR: In this article, a model integration device according to an aspect of the present invention comprises: a model collection unit which collects a learned learning model from each of a plurality of learning devices; an integration processing unit which executes an integration process for integrating a result of machine learning which is reflected in an integration range set within a common portion for each of the learned learning models; and a model update unit which updates the learning learning models retained by each learning devices by transmitting the result of the integration process to each learning device and causing each of them to apply the results of the integrated process in