- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 International Conference on Information and Communication Technology Convergence (ICTC) - Jeju (2018.10.17-2018.10.19)] 2018 International Conference on Information and Communication Technology Convergence (ICTC) - High Accuracy Real Time Machine Vision for Diameter Measurement Using Simpson Algorithm
摘要： Diameter is one of the important parameters for quality measurement. Fruit classification, for example, takes diameter as one important indicator, apart from other indicators. Precision measurement has been observed and experimented for example it can be done using laser technology, however the instrument requires a lot of space, therefore mobility is almost impossible. When speed is necessity while doing measurement, a real-time measurement using camera and image processing can give a lot of contribution compared to manual measurement. This paper introduces a diameter measurement method using Simpson algorithm in real-time, using regular camera. Simpson algorithm gave high accuracy measurement with high computation speed. The design indicated good result with accuracy ranged from 93% to 99% depending on calibration.
关键词： size measurement,automatic measurement,camera vision,simpson algorithm,size classification
更新于2025-09-23 15:22:29
-
[Lecture Notes in Computer Science] Pattern Recognition and Computer Vision Volume 11256 (First Chinese Conference, PRCV 2018, Guangzhou, China, November 23-26, 2018, Proceedings, Part I) || Damage Online Inspection in Large-Aperture Final Optics
摘要： Under the condition of inhomogeneous total internal reflection illumination, a novel approach based on machine learning is proposed to solve the problem of damage online inspection in large-aperture final optics. The damage online inspection mainly includes three problems: automatic classification of true and false laser-induced damage (LID), automatic classification of input and exit surface LID and size measurement of the LID. We first use the local area signal-to-noise ratio (LASNR) algorithm to segment all the candidate sites in the image, then use kernel-based extreme learning machine (K-ELM) to distinguish the true and false damage sites from the candidate sites, propose autoencoder-based extreme learning machine (A-ELM) to distinguish the input and exit surface damage sites from the true damage sites, and finally propose hierarchical kernel extreme learning machine (HK-ELM) to predict the damage size. The experimental results show that the method proposed in this paper has a better performance than traditional methods. The accuracy rate is 97.46% in the classification of true and false damage; the accuracy rate is 97.66% in the classification of input and exit surface damage; the mean relative error of the predicted size is within 10%. So the proposed method meets the technical requirements for the damage online inspection.
关键词： Size measurement,Damage online inspection,Classification,Laser-induced damage,Machine learning
更新于2025-09-23 15:21:01
-
Hybrid spherical particle field measurement based on interference technology
摘要： Interferometric particle imaging is widely used in particle size measurement. Conventional algorithms, which focus on single size particle fields, have difficulties in extracting each interference fringe in a hybrid spherical particle field due to the noise. To solve this problem, an iterative mean filter (IMF) algorithm is proposed. Instead of the specific mean filter template coefficient, the noise is reduced by iterating the calculation results under different template coefficients. The average value of the calculation results excluding the gross error is output as the final result. The effect of different template coefficients are simulated, furthermore, the value range of template coefficients has been analyzed. The interferogram of the hybrid spherical particle field from 21.3 μm to 57.9 μm is processed by the conventional algorithms with specific template coefficients of 2, 8, 12 and the IMF algorithm. The corresponding measurement errors are 17.22%, 10.69%, 9.04% and 5.11%. The experimental results show that the IMF algorithm would reduce measurement error, and could be potentially applied in particle field measurement.
关键词： interferometric particle imaging,particle size measurement,hybrid spherical particle field,gross error elimination
更新于2025-09-23 15:19:57
-
Reliable and Accurate Wheel Size Measurement under Highly Reflective Conditions
摘要： Structured-light vision sensor, as an important tool for obtaining 3D data, is widely used in fields of online high-precision measurement. However, the captured stripe images can show high-dynamic characteristics of low signal-to-noise ratio and uneven brightness due to the complexity of the onsite environment. These conditions seriously affect measurement reliability and accuracy. In this study, a wheel size measurement framework based on a structured-light vision sensor, which has high precision and reliability and is suitable for highly reflective conditions, is proposed. Initially, the quality evaluation criterion of stripe images is established, and the entire stripe is distinguished into high- and low-quality segments. In addition, the multi-scale Retinex theory is adopted to enhance stripe brightness, which improves the reliability of subsequent stripe center extraction. Experiments verify that this approach can remarkably improve measurement reliability and accuracy and has important practical value.
关键词： stripe image enhancement,wheel size measurement,reflective conditions,High dynamic
更新于2025-09-19 17:15:36
-
Size measurement of Daphnia pulex using low-coherence Gabor digital holography
摘要： We measured the size of Daphnia pulex (D. pulex), which is an indicator organism used for examining toxicity, under freely-swimming and stress-free conditions, made possible by the post-focusing ability of digital holography (DH). This environmental measurement is a new application of DH. This implementation, which is a key point of this research, should be applicable to real on-site use in non-sterile and unstable mechanical situations. Through trial and error, we arrived at the simplest interferometer configuration using a single beam line that can withstand vibrations, a low-coherence light source for reducing coherent noise, and single-shot image capturing. Automatic size measurement based on DH with image processing was performed. The originality of this research is the quantitative size measurement and performance estimation achieved by comparing the results with those from conventional manual eye measurement using ordinary optical microscope observation and image processing software. The estimation also allowed us to determine the proper parameters in the image processing for DH measurement.
关键词： Digital holography,Size measurement,Daphnia pulex,Image processing,Low-coherence light
更新于2025-09-12 10:27:22
-
Evaluation of in-line particle measurement with an SFT-probe as monitoring tool for process automation using a new time-based buffer approach
摘要： The Process Analytical Technology (PAT) initiative published by the Food and Drug administration (FDA) describes PAT systems as important tools to optimize pharmaceutical processes in order to ensure the final product quality. Real-time particle size measurements provide a promising approach for process automation of fluid bed granulation processes. This work focuses on the introduction and evaluation of a new time-based buffer approach for in-line spatial filtering technique (SFT) in order to provide a minimum time delay of the real-time measurement. Comparing the new buffer system to the conventionally used number-based approach, a reduced influence of the particle rate and a constant response time was found. A performance qualification of the Parsum probe IPP 80 using this buffer approach according to the ICH guideline Q2 was performed to investigate whether common variations of process parameters influence the real-time particle size measurement. Focussing on the main requirements for process control, hereby a good precision and specificity as well as an adequate robustness was found. Summarized, this study identified the time-based buffer system as more suitable buffer system for process automation.
关键词： In-line particle size measurement,Fluid bed granulation,Spatial filtering technology,Process automation,Process analytical technologies
更新于2025-09-09 09:28:46