Integrating Vision System to a Pick and Place Cartesian Robot

Vision aided pick and place cartesian robot is a combination of machine vision system and robotic system. They communicate with each other simultaneously to perform object sorting. In this project, machine vision algorithm for object sorting to solve the problem in failure sorting due to imperfection of images edges and different types of colours is proposed. The image is acquired by a camera and followed by image calibration. Pre-processing of image is performed through these methods, which are HSI colour space transformation, Gaussian filter for image filtering, Otsu’s method for image binarization, and Canny edge detection. LabVIEW edge-based geometric matching is selected for template matching. After the vision application analysed the image, electrical signal will send to robotic arm for object sorting if the acquired image is matched with template image. The proposed machine vision algorithm has yielded an accurate template matching score from 800 to 1000 under different disturbances and conditions. This machine vision algorithm provides more customizable parameters for each methods yet improves the accuracy of template matching.

Quantification of pulmonary perfusion abnormalities using DCE-MRI in COPD: comparison with quantitative CT and pulmonary function

Objectives Pulmonary perfusion abnormalities are prevalent in patients with chronic obstructive pulmonary disease (COPD), are potentially reversible, and may be associated with emphysema development. Therefore, we aimed to evaluate the clinical meaningfulness of perfusion defects in percent (QDP) using DCE-MRI. Methods We investigated a subset of baseline DCE-MRIs, paired inspiratory/expiratory CTs, and pulmonary function testing (PFT) of 83 subjects (age = 65.7 ± 9.0 years, patients-at-risk, and all GOLD groups) from one center of the “COSYCONET” COPD cohort. QDP was computed from DCE-MRI using an in-house developed quantification pipeline, including four different approaches: Otsu’s method, k-means clustering, texture analysis, and 80th percentile threshold. QDP was compared with visual MRI perfusion scoring, CT parametric response mapping (PRM) indices of emphysema (PRMEmph) and functional small airway disease (PRMfSAD), and FEV1/FVC from PFT. Results All QDP approaches showed high correlations with the MRI perfusion score (r = 0.67 to 0.72, p < 0.001), with the highest association based on Otsu’s method (r = 0.72, p < 0.001). QDP correlated significantly with all PRM indices (p < 0.001), with the strongest correlations with PRMEmph (r = 0.70 to 0.75, p < 0.001). QDP was distinctly higher than PRMEmph (mean difference = 35.85 to 40.40) and PRMfSAD (mean difference = 15.12 to 19.68), but in close agreement when combining both PRM indices (mean difference = 1.47 to 6.03) for all QDP approaches. QDP correlated moderately with FEV1/FVC (r = − 0.54 to − 0.41, p < 0.001). Conclusion QDP is associated with established markers of disease severity and the extent corresponds to the CT-derived combined extent of PRMEmph and PRMfSAD. We propose to use QDP based on Otsu’s method for future clinical studies in COPD. Key Points • QDP quantified from DCE-MRI is associated with visual MRI perfusion score, CT PRM indices, and PFT. • The extent of QDP from DCE-MRI corresponds to the combined extent of PRMEmph and PRMfSAD from CT. • Assessing pulmonary perfusion abnormalities using DCE-MRI with QDP improved the correlations with CT PRM indices and PFT compared to the quantification of pulmonary blood flow and volume.

Analysis of water quality at hydrographic basin scale using satellite images, co-occurrence matrices and Bayes classifier

Given the increased risks of water scarcity and the presence of polluting agents in water resources, this paper aims at the development and presentation of a computational tool capable of assessing water quality based on digital processing techniques applied to satellite images. Initially, a database was created for Brazilian regions, consisting of hydrographic basins satellite images associated with the Water Quality Index (WQI), according to the criteria established by the National Water Agency (ANA). Hitherto, the database consists of 85 images, 61 are used in the training stage and 24 in the testing stage. In both stages, the images are subjected to thresholding using the Otsu's Method, binarization, linear expansion on saturation, application of a Laplacian filter, extraction of characteristics by using co-occurrence matrices and classification by the Bayes Discriminant. Such techniques were also implemented on a computational platform in MATLAB® environment, responsible for the interface between the system and users. The proposed system presented an approximate 70% success rate regarding the classification of WQIs, which can be improved as more information is made available to improve the databases.

Идентификация пор ультрафильтрационных мембран на основе электронно-микроскопических исследований

В работе проанализированы методы, способы, приемы и прикладные программы для идентификации пор в полимерных мембранах. На основе сравнения достоинств и недостатков методов предложен подход к разработке программной реализации исследования пор полимерных полупроницаемых мембран. Объектами исследования служили ультрафильтрационные мембраны вида УАМ-50, УАМ-100, УПМ-К, УПМ-100, выбор которых обеспечен высокой задерживающей способностью, хорошей производительностью и наибольшей применяемостью в промышленной практике. Приведена методика по расчету коэффициента засоренности мембран, которая позволяет определить срок эффективной работы ультрафильтрационных мембран, элементов и установок при баромембранном и электробаромембранном разделении, концентрировании и очистке промышленных растворов и стоков. Выделенные участки ультрафильтрационных мембран УАМ-50, УАМ-100, УПМ-К, УПМ-100 площадью 1000000 нм2 обрабатывались при помощи Matlab 2017 таким образом, что были получены основные параметры, такие как средний диаметр засоренности (диаметры пор и коэффициент засоренности мембран). При обработке больших массивов данных по средним диаметрам пор и коэффициенту засоренности мембран использовался ПК, который позволил снизить и рассчитать погрешность выполненных измерений при помощи стандартных методов математической статистики. Расчет коэффициента засоренности мембран производили при помощи программы, изучающей описание основных функций imaging processing toolbox. Разработанный метод существенно сокращает время эксперимента и позволяет автоматизировано рассчитывать количество объектов, среднюю площадь, диаметр пор на сорбционной поверхности. Метод, сочетающий электронно-микроскопические исследования, обработку изображений Otsu's method, программную реализацию в Matlab 2017, дают возможность получить достоверные и воспроизводимые данные по морфологии поверхности ультрафильтрационных мембран УАМ-50, УАМ-100, УПМ-К, УПМ-100, опирающихся на статистическую обработку большой выборки данных, полученных в результате электронно-микроскопических исследований. Анализ экспериментальных данных, полученных автоматизированным методом, показал, что средняя площадь объекта наименьшая для мембраны УПМ-К и наибольшая для мембраны УАМ-50, а средний диаметр пор поверхности исследуемых мембран находится в интервале от 51 до 60 нм, что сопоставимо с литературными данными, полученных другими методами. При этом коэффициент засоренности выше для мембраны УПМ-К и ниже для мембраны УПМ-100.

Proposta de Implementação em Hardware do Algoritmo de Otsu Aplicado ao Rastreamento em Tempo Real de Vermes

This work proposes an implementation in Field Programmable GateArray (FPGA) of the Otsu’s method applied to real-time trackingof worms called Caenorhabditis elegans. Real-time tracking is necessaryto measure changes in the worm’s behavior in response totreatment with Ribonucleic Acid (RNA) interference. Otsu’s methodis a global thresholding algorithm used to define an optimal thresholdbetween two classes. However, this technique in real-time applicationsassociated with the processing of high-resolution videoshas a high computational cost because of the massive amount ofdata generated. Otsu’s algorithm needs to identify the worms ineach frame captured by a high-resolution camera in a real-timeanalysis of the worm’s behavior. Thus, this work proposes a highperformanceimplementation of Otsu’s algorithm in FPGA. Theresults show it was possible to achieve a speedup up to 5 timeshigher than similar works in the literature.

Nanoparticles visualization and extraction for diagnosis and therapy in nanomedicine

Nanomedicine is a rapidly developing field of science that has the potential to treat a wide range of complicated ailments. This paper uses a mouse with an inflamed calf and iron oxide nanoparticles (IO-NPs) attached to the therapeutic medicine and put into the mouse’s eye to investigate drug delivery efficiency. The idea is to track and quantify drug delivered to the inflamed calf of the mouse. A high-resolution MRI approach was used to capture images of the inflammatory calf area. Knowing that iron oxide has a high magnetic strength in MRI, image processing techniques were used to calculate the position and number of IO-NPs linked to the administered medication. This paper proposes an image processing approach for detecting and extracting IO-NPs. The images go through pre-processing steps that includes noise filtering and background removal. IO-NPs are isolated from the surrounding tissues using Otsu’s method. The number of IO-NPs grouped in the region, as well as the quantity of medications supplied to the region of interest, can be estimated using IO-NPs extraction. The findings on nanoparticle detection and extraction appear to be a potential method for estimating the amount of medicine targeting a specific location.

Segmentation as an effective method of isolating a brain tumor on MRI

Digital image processing, which ensues in many sides of life, is one of the areas that requires rapid development and improvement of existing algorithms, both for accuracy and completeness, and for reasons of speed and cost-effectiveness of both technical and software solutions. Medical application itself is the area where both precision in processing is important, as insufficient information affects the treatment protocol, and the cost for availability and widespread use. In this research, an algorithm for segmentation of digital MRI images of the brain is proposed in order to isolate the segment that contains the tumor. This algorithm is based on the sequential execution of the following steps: threshold Otsu’s method of binarization of the image, selection of brain and tumor tissues by morphological operations, segmentation by marked watershed, removal of the skull line and selection of the segment containing the tumor by an erosion. The verification did not reveal false-positive segmentation results, and the percentage of images correctly segmented to detect the tumor was 96.2%. It should be noted the high speed of the segmentation process obtained by the authors.

Computer-Aided Diagnosis of Malignant Melanoma Using Gabor-Based Entropic Features and Multilevel Neural Networks

The American Cancer Society has recently stated that malignant melanoma is the most serious type of skin cancer, and it is almost 100% curable, if it is detected and treated early. In this paper, we present a fully automated neural framework for real-time melanoma detection, where a low-dimensional, computationally inexpensive but highly discriminative descriptor for skin lesions is derived from local patterns of Gabor-based entropic features. The input skin image is first preprocessed by filtering and histogram equalization to reduce noise and enhance image quality. An automatic thresholding by the optimized formula of Otsu’s method is used for segmenting out lesion regions from the surrounding healthy skin regions. Then, an extensive set of optimized Gabor-based features is computed to characterize segmented skin lesions. Finally, the normalized features are fed into a trained Multilevel Neural Network to classify each pigmented skin lesion in a given dermoscopic image as benign or melanoma. The proposed detection methodology is successfully tested and validated on the public PH2 benchmark dataset using 5-cross-validation, achieving 97.5%, 100% and 96.87% in terms of accuracy, sensitivity and specificity, respectively, which demonstrate competitive performance compared with several recent state-of-the-art methods.