- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
An automatic multi-thread image segmentation embedded system for surface plasmon resonance sensor
摘要： In order to reduce the uncertainties associated with manual selection of regions of interest (ROIs) commonly used in Surface Plasmon Resonance (SPR) imaging system, we proposed and implemented an automatic image segmentation method in an embedded system to facilitate the potential real-time applications. Intuitive marker-controlled watershed algorithm is developed to segment ROIs (reaction, blank, and background regions) from images acquired from an experimental image SPR system. The marker assignment algorithms and pre-processing algorithms are executed in parallel by multi-threading programming on the multi-core embedded system to both real-time and good quality of segmentation. This method exhibited a good robustness in a series of ROIs segmentation test. Furthermore, the intensity response from triplicate detection of glucose standard solutions indicated a good reproducibility of data. The linear range was from 2.5 mg/mL to 20.4 mg/mL, with a correlation coefficient (R2) of 0.999 and sensitivity of 2.69 a.u./mg/mL. In conclusion, the proposed automatic image segmentation method effectively makes the measurement more precise and simplified.
关键词： Optical sensor,Surface plasmon resonance (SPR),Biosensor,Watershed algorithm,Image segmentation
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) - Chongqing, China (2018.10.12-2018.10.14)] 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) - Medical image segmentation based on improved watershed algorithm
摘要： The watershed segmentation algorithm has the problem of over-segmentation. The paper proposed an improved watershed algorithm for medical image segmentation. Combined with improved gray morphological reconstruction and watershed algorithm, the segmentation of medical cells and brain CT images is improved, which improves the accuracy of image segmentation of medical tissues and organs and assists doctors to diagnose the diseases. The simulation results show that the improved algorithm can effectively suppress the over-segmentation for two different medical tissue images.
关键词： watershed algorithm,medical image,segmentation,grayscale morphology
更新于2025-09-23 15:23:52
-
Enhancement of thermographic images of composite laminates for debond detection: An approach based on Gabor filter and watershed
摘要： Spacecraft structures use materials which require high stiffness and low mass. Subjected to high thermal and acoustic loads, their health is of utmost importance. These structures are vulnerable to debonding and delaminations which are identified as defects. Non-destructive way of inspecting these components is very essential to detect the debonding defects. Debond defects are not visible to naked eyes and hence conventional optical cameras will not serve the purpose of automating inspection. For this purpose, we have used thermography. Passing the thermographic images through stages like enhancement, segmentation and feature extraction by using techniques like watershed segmentation, active contours and texture classification through Gabor filter are attempted in this study. Defects are brought out which help in taking corrective steps to avoid failure of the materials during actual life of the spacecraft.
关键词： Noise removal,Feature Extraction,Watershed algorithm,Active Contours,Gabor filter,Thermal Imaging
更新于2025-09-19 17:15:36