Development of a Multispectral Structured Illumination Reflectance Imaging (SIRI) System and Its Application to Bruise Detection of Apples

2017 ◽  
Vol 60 (4) ◽  
pp. 1379-1389 ◽  
Author(s):  
Yuzhen Lu ◽  
Renfu Lu
Keyword(s):  
Defect Detection ◽  
Imaging Modality ◽  
Principal Component ◽  
Tunable Filter ◽  
Structured Illumination ◽  
Uniform Illumination ◽  
Two Phase ◽  
Phase Transform ◽  
Amplitude Component ◽  
20 Nm

Abstract. SIRI is a promising new imaging modality for enhancing quality detection of food. A liquid-crystal tunable filter (LCTF)-based multispectral SIRI system was developed and used for selecting optimal wavebands to detect bruising in apples. Immediately after impact bruising, ‘Delicious’, ‘Royal Gala’, ‘Granny Smith’, and ‘Golden Delicious’ apples were imaged by the system over the spectral region of 650 to 950 nm with 20 nm increments under sinusoidally modulated illumination at a spatial frequency of 100 cycles m-1. Each sample was subjected to two phase-shifted sinusoidal patterns of illumination with phase offsets of 0 and 2p/3 that were generated by a digital light projector. For comparison, spectral images were also captured under conventional uniform illumination. Spiral phase transform, a newly developed two-phase based demodulation method, was then used to retrieve amplitude component (AC) and direct component (DC) images from the SIRI images, from which ratio images were obtained by dividing the AC images by the DC images. It was found that the uniform illumination images failed to reveal the bruises in apples, whereas bruises were distinctly visible in the ratio images, with contrast varying with wavelength. Principal component analysis (PCA) showed that seven wavelengths from 710 to 830 nm were more relevant to bruise detection. A modified Otsu thresholding method based on the between-class variance was proposed for bruise segmentation from the ratio images at each of the seven wavelengths as well as the first principal component (PC1) images, which resulted in overall detection errors of 11.7% to 14.2%. This study has shown the potential of using a multispectral SIRI system for defect detection of fruit. Further research is needed to develop a general algorithm for defect detection of apples and upgrade the system toward real-time detection. Keywords: Defects, Detection, Fruit, Image analysis, LCTF, Structured illumination.

Detection of Surface and Subsurface Defects of Apples Using Structured- Illumination Reflectance Imaging with Machine Learning Algorithms

2018 ◽  
Vol 61 (6) ◽  
pp. 1831-1842 ◽  
Author(s):  
Yuzhen Lu ◽  
Renfu Lu
Keyword(s):  
Machine Learning ◽  
Empirical Mode Decomposition ◽  
Defect Detection ◽  
Support Vector ◽  
Structured Illumination ◽  
Uniform Illumination ◽  
Machine Learning Classification ◽  
Mode Decomposition ◽  
Better Than ◽  
Subsurface Defects

Abstract. Machine vision technology coupled with uniform illumination is now widely used for automatic sorting and grading of apples and other fruits, but it still does not have satisfactory performance for defect detection because of the large variety of defects, some of which are difficult to detect under uniform illumination. Structured-illumination reflectance imaging (SIRI) offers a new modality for imaging by using sinusoidally modulated structured illumination to obtain two sets of independent images: direct component (DC), which corresponds to conventional uniform illumination, and amplitude component (AC), which is unique for structured illumination. The objective of this study was to develop machine learning classification algorithms using DC and AC images and their combinations for enhanced detection of surface and subsurface defects of apples. A multispectral SIRI system with two phase-shifted sinusoidal illumination patterns was used to acquire images of ‘Delicious’ and ‘Golden Delicious’ apples with various types of surface and subsurface defects. DC and AC images were extracted through demodulation of the acquired images and were then enhanced using fast bi-dimensional empirical mode decomposition and subsequent image reconstruction. Defect detection algorithms were developed using random forest (RF), support vector machine (SVM), and convolutional neural network (CNN), for DC, AC, and ratio (AC divided by DC) images and their combinations. Results showed that AC images were superior to DC images for detecting subsurface defects, DC images were overall better than AC images for detecting surface defects, and ratio images were comparable to, or better than, DC and AC images for defect detection. The ensemble of DC, AC, and ratio images resulted in significantly better detection accuracies over using them individually. Among the three classifiers, CNN performed the best, with 98% detection accuracies for both varieties of apples, followed by SVM and RF. This research demonstrated that SIRI, coupled with a machine learning algorithm, can be a new, versatile, and effective modality for fruit defect detection. Keywords: Apple, Defect, Bi-dimensional empirical mode decomposition, Machine learning, Structured illumination.

scholarly journals Camera-based localization microscopy optimized with calibrated structured illumination

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Martin Schmidt ◽  
Adam C. Hundahl ◽  
Henrik Flyvbjerg ◽  
Rodolphe Marie ◽  
Kim I. Mortensen
Keyword(s):  
Data Analysis ◽  
Super Resolution ◽  
Wide Field ◽  
Structured Illumination ◽  
Uniform Illumination ◽  
Localization Microscopy ◽  
Localization And Tracking ◽  
Field Imaging ◽  
Wide Field Imaging ◽  
Localization Information

AbstractUntil very recently, super-resolution localization and tracking of fluorescent particles used camera-based wide-field imaging with uniform illumination. Then it was demonstrated that structured illuminations encode additional localization information in images. The first demonstration of this uses scanning and hence suffers from limited throughput. This limitation was mitigated by fusing camera-based localization with wide-field structured illumination. Current implementations, however, use effectively only half the localization information that they encode in images. Here we demonstrate how all of this information may be exploited by careful calibration of the structured illumination. Our approach achieves maximal resolution for given structured illumination, has a simple data analysis, and applies to any structured illumination in principle. We demonstrate this with an only slightly modified wide-field microscope. Our protocol should boost the emerging field of high-precision localization with structured illumination.

scholarly journals Super-resolution imaging of fluorescent dipoles via polarized structured illumination microscopy

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Karl Zhanghao ◽  
Xingye Chen ◽  
Wenhui Liu ◽  
Meiqi Li ◽  
Yiqiong Liu ◽  
...  
Keyword(s):  
Hippocampal Neurons ◽  
Fluorescent Protein ◽  
Imaging Modality ◽  
Super Resolution ◽  
Vital Role ◽  
Molecular Structures ◽  
Polarization Microscopy ◽  
Structured Illumination ◽  
Structured Illumination Microscopy ◽  
Resolution Imaging

Abstract Fluorescence polarization microscopy images both the intensity and orientation of fluorescent dipoles and plays a vital role in studying molecular structures and dynamics of bio-complexes. However, current techniques remain difficult to resolve the dipole assemblies on subcellular structures and their dynamics in living cells at super-resolution level. Here we report polarized structured illumination microscopy (pSIM), which achieves super-resolution imaging of dipoles by interpreting the dipoles in spatio-angular hyperspace. We demonstrate the application of pSIM on a series of biological filamentous systems, such as cytoskeleton networks and λ-DNA, and report the dynamics of short actin sliding across a myosin-coated surface. Further, pSIM reveals the side-by-side organization of the actin ring structures in the membrane-associated periodic skeleton of hippocampal neurons and images the dipole dynamics of green fluorescent protein-labeled microtubules in live U2OS cells. pSIM applies directly to a large variety of commercial and home-built SIM systems with various imaging modality.

Dimensioni e direttrici del mutamento socio-economico in prospettiva territoriale dal 1951 a oggi

2013 ◽  
pp. 78-92
Author(s):  
Domenico Maddaloni ◽  
Fiorenzo Parziale
Keyword(s):  
Principal Component Analysis ◽  
Linear Regression ◽  
Southern Italy ◽  
Principal Component ◽  
Research Strategy ◽  
Two Phase ◽  
Economic Changes ◽  
Local Contexts ◽  
Italian Provinces ◽  
History Of

In this study we go back to examine the economic and sociological changes throughout the local contexts and divisions of our country. The instrument used is a research strategy that combines a two-phase principal component analysis developed by Di Franco and Marradi with multiple linear regression. From data inherent to four key moments in the recent history of Southern Italy and the whole country - 1951, 1971, 1991 and 2007 - we obtain four «photographs» of dimensions that clarify the structure of the selected variables. We then propose two models of path analysis that underline the causal links between the factors emerged from the PCA, in order to reconstruct the socio-economic changes in the Italian provinces from 1951 to 2007.

3D Defect detection using weighted principal component thermography

2020 ◽  
Vol 128 ◽  
pp. 106039
Author(s):  
Seppe Sels ◽  
Boris Bogaerts ◽  
Simon Verspeek ◽  
Bart Ribbens ◽  
Gunther Steenackers ◽  
...  
Keyword(s):  
Defect Detection ◽  
Principal Component ◽  
Weighted Principal Component

Email Worm Detection Using Data Mining

2011 ◽  
pp. 20-34
Author(s):  
Mohammad M. Masud ◽  
Latifur Khan ◽  
Bhavani Thuraisingham
Keyword(s):  
Data Mining ◽  
Feature Selection ◽  
Principal Component ◽  
Classification Model ◽  
Support Vector ◽  
Two Phase ◽  
Feature Selection Technique ◽  
Worm Detection ◽  
Phase Selection ◽  
Using Data

This chapter applies data mining techniques to detect email worms. Email messages contain a number of different features such as the total number of words in message body/subject, presence/absence of binary attachments, type of attachments, and so on. The goal is to obtain an efficient classification model based on these features. The solution consists of several steps. First, the number of features is reduced using two different approaches: feature-selection and dimension-reduction. This step is necessary to reduce noise and redundancy from the data. The feature-selection technique is called Two-phase Selection (TPS), which is a novel combination of decision tree and greedy selection algorithm. The dimensionreduction is performed by Principal Component Analysis. Second, the reduced data is used to train a classifier. Different classification techniques have been used, such as Support Vector Machine (SVM), Naïve Bayes and their combination. Finally, the trained classifiers are tested on a dataset containing both known and unknown types of worms. These results have been compared with published results. It is found that the proposed TPS selection along with SVM classification achieves the best accuracy in detecting both known and unknown types of worms.

scholarly journals Nanoscale imaging of bacterial infections by sphingolipid expansion microscopy

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Ralph Götz ◽  
Tobias C. Kunz ◽  
Julian Fink ◽  
Franziska Solger ◽  
Jan Schlegel ◽  
...  
Keyword(s):  
Lipid Bilayers ◽  
Bacterial Infections ◽  
Super Resolution ◽  
Structured Illumination ◽  
Structured Illumination Microscopy ◽  
Nanoscale Imaging ◽  
Intracellular Organelles ◽  
Resolution Imaging ◽  
Simkania Negevensis ◽  
20 Nm

AbstractExpansion microscopy (ExM) enables super-resolution imaging of proteins and nucleic acids on conventional microscopes. However, imaging of details of the organization of lipid bilayers by light microscopy remains challenging. We introduce an unnatural short-chain azide- and amino-modified sphingolipid ceramide, which upon incorporation into membranes can be labeled by click chemistry and linked into hydrogels, followed by 4× to 10× expansion. Confocal and structured illumination microscopy (SIM) enable imaging of sphingolipids and their interactions with proteins in the plasma membrane and membrane of intracellular organelles with a spatial resolution of 10–20 nm. As our functionalized sphingolipids accumulate efficiently in pathogens, we use sphingolipid ExM to investigate bacterial infections of human HeLa229 cells by Neisseria gonorrhoeae, Chlamydia trachomatis and Simkania negevensis with a resolution so far only provided by electron microscopy. In particular, sphingolipid ExM allows us to visualize the inner and outer membrane of intracellular bacteria and determine their distance to 27.6 ± 7.7 nm.

Sign in / Sign up

Export Citation Format

Share Document