Image Classification Device Resolving Event Grouping Precision

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image classification methods struggle to accurately classify images within an image group that were taken during the same event, often misclassifying images due to differences in features among the images.

Innovation Solution

An image classification device that specifies images with a predetermined feature, calculates an evaluation value based on the dispersion of these images over time, and classifies the image group accordingly to prevent misclassification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If images are classified by extracting features from each image individually, then classification precision for individual images is improved, but reliability of event-based classification deteriorates because images from the same event may be classified into different categories

Engineering Contradiction:

Improveclassification precisionVSAvoidevent-based classification reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent merges individual image classification results with event-level temporal analysis. By combining feature extraction from each image with dispersion degree calculation across the image group, the system achieves both precise individual classification and reliable event-based classification, resolving the contradiction between the two requirements

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent implements feedback by using the classification results of individual images to calculate the dispersion degree, which then feeds back to determine the event category. This feedback mechanism allows the system to adjust classification based on the overall consistency of images within an event, improving both precision and reliability

Inventive Principle:

Principle #23Feedback

2Measurement precision

If images with different features within the same event group are classified separately, then classification accuracy for diverse images is improved, but productivity of event-based classification deteriorates due to increased complexity and time consumption

Engineering Contradiction:

Improveclassification accuracyVSAvoidevent-based classification efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent applies partial action by focusing classification efforts on key features that differentiate events, rather than analyzing all possible image features in depth. The dispersion degree calculation uses a simplified temporal approach that provides sufficient classification accuracy without excessive computational overhead, thus maintaining productivity

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS9058342B2Image classification device, method, program, recording media with program thereon, and integrated circuit

Publication Date: 2015.06.16 PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA

AI summary

According to a conventional image classification device that extracts a feature from an image and classifies the image with use of the extracted feature, in the case where one image and another one image, which are included in an image group, each have a different feature, the one image and the other one image might be each classified into a different category. In order to solve this problem, an image classification device relating to the present invention calculates, with respect to each of persons appearing in a plurality of images included in an image group which have been photographed with respect to one event, a main character degree that is an index indicating an important degree in units of image groups, and classifies the images into any one of different classification destination events in units of image groups based on the calculated main character degrees.