Current Issue : April - June Volume : 2016 Issue Number : 2 Articles : 4 Articles
In several machine vision problems, a relevant issue is the estimation of homographies between two different perspectives that\nhold an extensive set of abnormal data. A method to find such estimation is the random sampling consensus (RANSAC); in this,\nthe goal is to maximize the number of matching points given a permissible error (Pe), according to a candidate model. However,\nthose objectives are in conflict: a low Pe value increases the accuracy of the model but degrades its generalization ability that refers\nto the number of matching points that tolerate noisy data, whereas a high Pe value improves the noise tolerance of the model but\nadversely drives the process to false detections. This work considers the estimation process as a multi objective optimization problem\nthat seeks to maximize the number of matching points whereas Pe is simultaneously minimized. In order to solve the multiobjective\nformulation, two different evolutionary algorithms have been explored: the Nondominated Sorting Genetic Algorithm II (NSGA-II)\nand the Nondominated Sorting Differential Evolution (NSDE). Results considering acknowledged quality measures among original\nand transformed images over a well-known image benchmark show superior performance of the proposal than Random Sample\nConsensus algorithm....
In machine-vision-based systems for detecting foreign fibers, due to the background of the cotton\nlayer has the absolute advantage in the whole image, while the foreign fiber only account for a\nvery small part, and what�s more, the brightness and contrast of the image are all poor. Using the\ntraditional image segmentation method, the segmentation results are very poor. By adopting the\nmaximum entropy and genetic algorithm, the maximum entropy function was used as the fitness\nfunction of genetic algorithm. Through continuous optimization, the optimal segmentation threshold\nis determined. Experimental results prove that the image segmentation of this paper not\nonly fast and accurate, but also has strong adaptability....
Recently, machine vision is gaining attention in food science as well as in food industry concerning\nfood quality assessment and monitoring. Into the framework of implementation of\nProcess Analytical Technology (PAT) in the food industry, image processing can be used\nnot only in estimation and even prediction of food quality but also in detection of adulteration.\nTowards these applications on food science, we present here a novel methodology for\nautomated image analysis of several kinds of food products e.g. meat, vanilla cr�¨me and\ntable olives, so as to increase objectivity, data reproducibility, low cost information extraction\nand faster quality assessment, without human intervention. Image processingâ��s outcome\nwill be propagated to the downstream analysis. The developed multispectral image\nprocessing method is based on unsupervised machine learning approach (Gaussian Mixture\nModels) and a novel unsupervised scheme of spectral band selection for segmentation\nprocess optimization. Through the evaluation we prove its efficiency and robustness against\nthe currently available semi-manual software, showing that the developed method is a high\nthroughput approach appropriate for massive data extraction from food samples....
Over the past few years, the application of camera-equipped Unmanned Aerial Vehicles (UAVs) for visually monitoring\nconstruction and operation of buildings, bridges, and other types of civil infrastructure systems has exponentially\ngrown. These platforms can frequently survey construction sites, monitor work-in-progress, create documents for\nsafety, and inspect existing structures, particularly for hard-to-reach areas. The purpose of this paper is to provide\na concise review of the most recent methods that streamline collection, analysis, visualization, and communication\nof the visual data captured from these platforms, with and without using Building Information Models (BIM) as\na priori information. Specifically, the most relevant works from Civil Engineering, Computer Vision, and Robotics\ncommunities are presented and compared in terms of their potential to lead to automatic construction monitoring\nand civil infrastructure condition assessment....
Loading....