基于边缘检测的图像分割的超声诊断机器人控制系统设计

Design of Ultrasonic Diagnosis Robot Control System Based on Image Detection Based on Edge Detection

摘要:

传统系统在嵌入信息后峰值信噪比较高，使图像分割结果与实际效果相差较大，导致控制系统超声诊断结果并不精准，针对该问题，提出基于边缘检测的图像分割的超声诊断机器人控制系统设计。在控制系统的硬件结构部分，以STM32F103C8T6单片机为核心的控制器，使用型号为3MC58的步进电机驱动器，通过角位移量控制脉冲个数，以实现更加准确的定位。在软件设计中，通过图像分割技术检测图像边缘特征，提高图像分割精度和准确度，帮助诊断机器人提高诊断功能。分析不同嵌入率下峰值信噪比，在确定该值后将传统系统与该系统的超声诊断功能对比分析，由实验结果可知，该系统在嵌入信息后峰值信噪比较高的情况下也能保证图像分割结果与实际效果一致，对0.8 bpp嵌入率图像的分割处理效果平均值为89%，超声诊断准确率平均值为88.6%，表明该系统的控制性能较好，能够为医学、航天航空及军事领域提供设备支持。

Abstract:

After embedding information, the traditional system has a relatively high peak signal-to-noise, which makes the image segmentation result different from the actual effect, resulting in inaccurate ultrasonic diagnosis results of the control system. To solve this problem, an ultrasonic diagnostic robot control based on image segmentation based on edge detection is proposed system design. In the hardware structure part of the control system, the controller with STM32F103C8T6 single-chip microcomputer as the core uses a stepper motor driver model 3MC58, and the number of pulses is controlled by the angular displacement to achieve more accurate positioning. In software design, image edge features are detected by image segmentation technology to improve image segmentation accuracy and accuracy, and help diagnostic robots improve diagnostic functions. Analyze the peak signal-to-noise ratio at different embedding rates. After determining this value, compare the traditional system with the ultrasonic diagnosis function of the system. From the experimental results, it can be seen that the system can also be used when the peak signal-to-noise is relatively high after embedding information. Ensure that the image segmentation results are consistent with the actual results, the average segmentation effect of 0.8 bpp embedding rate image is 89%, and the average accuracy of ultrasound diagnosis is 88.6%, indicating that the system has good control performance and can provide equipment support for medical, aerospace and military fields.