Information processing systems and programs, information processing methods, servers

The system accurately detects crack locations and identifies affected objects by estimating crack regions and object areas using machine learning and shape analysis, addressing misclassification issues in crack detection systems.

JP7873441B2Active Publication Date: 2026-06-12SENSYN ROBOTICS INC

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
SENSYN ROBOTICS INC
Filing Date
2023-02-06
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

Existing crack detection systems misdetect tiles with cracks as divided tiles due to cracks, leading to incorrect crack location recognition.

Method used

An information processing system that estimates crack regions, colors them based on surrounding colors, and estimates object regions to prevent misdetection of cracked tiles, using machine learning models and Hessian matrix-based shape analysis.

🎯Benefits of technology

Accurately detects crack locations and identifies which objects have cracks, reducing misclassification and improving crack detection precision.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007873441000003
    Figure 0007873441000003
  • Figure 0007873441000004
    Figure 0007873441000004
  • Figure 0007873441000005
    Figure 0007873441000005
Patent Text Reader

Abstract

To provide an information processing system and a program configured to prevent a cracked object from being detected in a split state.SOLUTION: An information processing system comprises: a crack estimation unit that estimates, with respect to an original image containing one or more objects in a structure, a crack region in the objects; a crack coloring unit that colors the estimated crack region in the original image according at least to a color of surroundings of the crack region; and an object region estimation unit that estimates, with respect to an image resulting from the coloring, an object region where the objects exist.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art