A Simple Region Descriptor Based on Object Area per Scan Line

Kumar, R. Deepak; Ramareddy, K.; Rao, B. Madhusudan

doi:10.5120/742-1048

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…photodiodes), exploiting the advantage of having spatial information. Initially, all the connected regions of the binary image are identified and classified [15]; in other words, all the connected white blobs of the binary image are isolated from the whole image and enumerated. Afterwards, the melt pool is identified among all regions as the region characterized by the maximum area and the minimum blob centroid -image center distance (coaxial setup).…”

Section: B Analysis Of Thermal Emission Images -Htbmentioning

confidence: 99%

Estimation of melt pool size by complementary use of external illumination and process emission in coaxial monitoring of selective laser melting

Pacher

Mazzoleni

Caprio

et al. 2019

Journal of Laser Applications

View full text Add to dashboard Cite

Coaxial imaging of melt pool dynamics provides several advantages over other monitoring methods in SLM. The ability to track the processing zone ensures the possibility to observe defect formation dynamics mainly related to melting and solidification. Commonly, the melt pool dynamics are observed by means of process emission. In process emission images, geometrical information of the melt pool are not directly available and their extraction would require the use of a calibrated sensor in order to measure the temperature levels; as a consequence commonly an arbitrary threshold is applied to the image. The use of external illumination for monitoring purposes allows for suppressing the process emission and observing the melt pool geometry by means of the reflected light. On the other hand, the obtained images show lower contrast and can be difficult to process by means of image processing algorithms. Accordingly, this work proposes the complementary use of external illumination and process emission for characterizing the melt pool dynamics in SLM. For the purpose, an open SLM platform with an inhouse designed coaxial monitoring module is used. Images with external illumination were used to estimate the melt pool size for AISI 316L. The information was used to set a threshold value for determining the melt pool size observed at the near infrared emission band. The proposed strategy proved promising for real time monitoring and control applications and can represent a feasible solution for industrial systems.

show abstract

Section: B Analysis Of Thermal Emission Images -Htbmentioning

confidence: 99%

Estimation of melt pool size by complementary use of external illumination and process emission in coaxial monitoring of selective laser melting

Pacher

Mazzoleni

Caprio

et al. 2019

Journal of Laser Applications

View full text Add to dashboard Cite

show abstract

“…Therefore, an algorithm based on connected components is used [17,18]. The region labeling stage evaluates each pixel with a 4 neighbor-connectivity, using a heuristic stated on pixel values according to predecessor labels at north and west position.…”

Section: Labelingmentioning

confidence: 99%

Machine vision system for weed detection using image filtering in vegetables crops

Pulido-Rojas

Molina-Villa

Solaque-Guzmán

2016

Rev. Fac. Ing. Univ. Antioquia

View full text Add to dashboard Cite

124test results obtain between 70.4 and 72.5% classification accuracy. Another work involves two processes: image segmentation and decision [2]. Source image is binarized applying a threshold from RGB format; with plant pixels, crop row direction is estimated; next, a Support Vector Machine classifier is trained and implemented to decide presence of weed offering an optimum performance in terms of computational cost.In [3], a work to identify weeds using an off-line training from RGB images of corn, these images are segmented to differentiate vegetation and soil, estimating a probability density function and partitioning the image into cells formed detecting from culture lines using Hough transform. In operation, the system calculates the cells of a new image and applies Bayes' theorem to make the decision process of belonging to the Weed class. The authors in [4] use a JAI AD-130 machine vision camera capable of simultaneously capturing visible and near-infrared light spectrums; they characterized soil, green and dry plants using difference between red grey level and near infrared grey level (index NIR-R) in crop images, achieving a clear threshold for separate and segment objects in the scene; the results indicate that 0 to 50 grey level for dry plants and 150 to 250 for green plants is a good way to classify vegetation, suggesting that plants and soil can be separated using a threshold from histogram. Another work about weed Machine vision system for weed detection using image filtering in vegetables cropsABSTRACT: This work presents a machine vision system for weed detection in vegetable crops using outdoor images, avoiding lighting and sharpness problems during acquisition step. This development will be a module for a weed removal mobile robot with camera obscura (Latin for "dark room") for lighting controlled conditions. The purpose of this paper is to develop a useful algorithm to discriminate weed, using image filtering to extract color and area features, then, a process to label each object in the scene is implemented, finally, a classification based on area is proposed, including sensitivity, specificity, positive and negative predicted values in order to evaluate algorithm performance. RESUMEN:El presente trabajo expone un sistema de visión de máquina para la detección de maleza en cultivos de hortalizas, usando imágenes exteriores, evadiendo problemas de iluminación y nitidez durante la etapa de adquisición, ya que el presente desarrollo será un módulo para un robot móvil removedor de maleza con una cámara oscura para controlar las condiciones de luz. El enfoque de diseño se enmarca en el desarrollo de un algoritmo útil para discriminar maleza usando filtros en la imagen extrayendo características de color y área, luego se implementa un proceso de etiquetado para cada objeto en la escena. Finalmente, una clasificación basada en área es propuesta incluyendo el cálculo de los índices de sensibilidad, especificidad, valores predictivos positivos y negativos con el fin de evaluar el rendimiento del algor...

show abstract

“…Labeling process is based on connected components algorithm with a 4 connectivity given a heuristic stated on pixel values according predecessor labels at north and west position exposed in [20,21]. The feature extraction step is carry out by defining labeled objects area, counting number of pixels for each one and storing values for all items [22].…”

Section: Low Level Features Extractionmentioning

confidence: 99%

A Comparative Analysis of Weed Images Classification Approaches in Vegetables Crops

Rojas¹,

Guzmán²,

Toledo³

2017

View full text Add to dashboard Cite

Abstract. This paper exposes a comparative analysis of three weed classification strategies based on area and texture features over images of vegetable crops, focus on provide a technological tool to support farmers in their maintenance tasks. The classification alternatives embrace a basic approach which defines an umbral according to scene features, indeed, a detection with a certain degree of uncertainty on the decision region is purposed and a rigid boundary decision arrangement are exposed. A first mode carries out an unsupervised learning, it uses area and color features with a practical thresholding classifier to differentiate between weed and vegetable classes, the following two, extracts statistical measures of autocorrelation, contrast, correlation and others, from grey level cooccurrence matrices to calculate texture features, next, a principal component analysis is made for dimensionality reduction. These patterns serve as basis for training K-Nearest Neighbor and Support Vector Machine classifiers. The algorithms performance is measured calculating sensitivity (SN), specificity (SP), positive and negative predicted values (PPV and NPV), also, the execution time is stored and tabulated in order to evaluate the proposed methods. Finally, the results show a similar performance of correct classification over 90 and 80% on SN and SP indices respectively, however, approaches present a clear difference in execution time respect of train an evaluation stages.

show abstract

A Simple Region Descriptor Based on Object Area per Scan Line

Cited by 6 publications

References 8 publications

Estimation of melt pool size by complementary use of external illumination and process emission in coaxial monitoring of selective laser melting

Estimation of melt pool size by complementary use of external illumination and process emission in coaxial monitoring of selective laser melting

Machine vision system for weed detection using image filtering in vegetables crops

A Comparative Analysis of Weed Images Classification Approaches in Vegetables Crops

Contact Info

Product

Resources

About