【專利核准公告】P111004US-以波段用於超頻譜檢測物件影像之方式「METHOD FOR DETECTING OBJECT IMAGE USING HYPERSPECTRAL IMAGING BY BAND SELECTION」
|
專利國別 |
美國 |
發表日期 |
2025-10-08 |
|
本校案號 |
P111004US | ||
|
專利名稱 |
以波段用於超頻譜檢測物件影像之方式「METHOD FOR DETECTING OBJECT IMAGE USING HYPERSPECTRAL IMAGING BY BAND SELECTION」 | ||
|
發明人 |
王祥辰、曹育銘、紀宇盛、史弦鋐 | ||
|
所屬院 |
工學院 |
提案單位 |
先進工具機研究中心 |
|
類型 |
發明 |
專利權人 |
國立中正大學 |
|
申請號 |
18/162,083 |
申請日期 |
2023.01.31 |
|
公開號 |
US20230281818A1 |
公開日期 |
2023.09.07 |
|
證書號 |
US 12,387,333 B2 |
核准日期 |
2025.08.12 |
|
國際分類號 |
G06T 7/00(2006.01);G06V 20/69(2006.01);G06V 10/32(2006.01);G06V 10/82(2006.01);G06V 10/58(2006.01);G06V 10/77(2006.01);A61B 1/06(2006.01);A61B 1/273(2006.01);G16B 30/40(2006.01) | ||
|
專利權期間 |
2023.01.31~2043.01.31 | ||
|
專利摘要 |
The present application related to a method for detecting image using hyperspectral imaging by band selection. Firstly, obtaining a hyperspectral imaging information according to a reference image, hereby, obtaining corresponded hyperspectral image from an input image, and obtaining corresponded feature values by band selection for operating Principal components analysis to simplify feature values. Then, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the esophageal cancer sample image, the image of the object under detected is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the image of the object under detected. | ||
|
圖示 |
|||
