基于改进的U-Net,快速准确的ROI提取用于复杂背景的非接触背部手脉检测
Rongwen Zhang1, Xiangqun Zou2, Xiaoling Deng1,3,4
1College of Electronic Engineering (College of Artifificial Intelligence), South China Agricultural University, Guangzhou 510642, China.
Sensors (Basel, Switzerland)
|July 11, 2023
概括
这项研究引入了一种改进的U-Net模型,用于精确检测静脉图像中的背手关键点. 改进的模型在更小的文件大小下达到98.6%的准确性,非常适合边缘系统.
科学领域:
- 计算机视觉 计算机视觉
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 传统的图像处理难以从复杂的背手静脉图像中准确地提取区域.
- 非接触静脉成像由于背景复杂性和特征变异性而存在挑战.
研究的目的:
- 开发一个改进的U-Net模型,用于精确的背部手键点检测.
- 为了增强特征提取和解决背手静脉分析中的模型退化.
- 创建一个适合低资源平台的计算效率模型.
主要方法:
- 一个改进的U-Net架构,在下采样路径中包含一个剩余模块.
- 利用Jensen-Shannon (JS) 的分歧损失函数来改善特征地图分布.
- 使用Soft-argmax进行端到端的关键点坐标计算.
主要成果:
- 改进的U-Net模型实现了98.6%的准确性,超过了原来的U-Net1%.
- 模型尺寸被缩小到1.16M,表明参数显著减少.
- 在特征地图多峰问题上表现出卓越的特征提取和稳定性.
结论:
- 建议改进的U-Net模型有效地执行背手关键点检测非接触静脉图像.
- 该模型的高精度和缩小尺寸使其适合在边缘嵌入式系统上部署.
- 这种方法为资源有限的环境中兴趣地区的开采提供了实际的解决方案.
更多相关视频
04:48Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.8K
09:56Universal Hand-held Three-dimensional Optoacoustic Imaging Probe for Deep Tissue Human Angiography and Functional Preclinical Studies in Real Time
Published on: November 4, 2014
10.8K
相关概念视频
01:17Veins of Upper Limbs
1.2K
The human circulatory system, a marvel of biological engineering, is a complex network of vessels that transport blood throughout the body. Among these, the veins responsible for carrying blood from the upper limbs are divided into two categories: deep and superficial.
The deep venous system is primarily composed of the ulnar and radial veins. The ulnar vein, which drains the fingers through the superficial palmar venous arches, and the radial vein, which serves the palms via the deep palmar...
The deep venous system is primarily composed of the ulnar and radial veins. The ulnar vein, which drains the fingers through the superficial palmar venous arches, and the radial vein, which serves the palms via the deep palmar...
1.2K
00:56Extraction: Advanced Methods
493
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
493
01:05Difference from Background: Limit of Detection
6.5K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
6.5K