Search results for "convolutional neural network"

showing 10 items of 179 documents

A convolutional neural network framework for blind mesh visual quality assessment

2017

In this paper, we propose a new method for blind mesh visual quality assessment using a deep learning approach. To do this, we first extract visual representative features by computing locally curvature and dihedral angles from each distorted mesh. Then, we determine from these features a set of 2D patches which are learned to a convolutional neural network (CNN). The network consists of two convolutional layers with two max-pooling layers. Then, a multilayer perceptron (MLP) with two fully connected layers is integrated to summarize the learned representation into an output node. With this network structure, feature learning and regression are used to predict the quality score of a given d…

Computer sciencebusiness.industryDeep learningNode (networking)Feature extraction020207 software engineeringPattern recognition02 engineering and technologyConvolutional neural networkVisualizationSet (abstract data type)Multilayer perceptron0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessFeature learning2017 IEEE International Conference on Image Processing (ICIP)
researchProduct

A Deep Learning Approach for Automated Fault Detection on Solar Modules Using Image Composites

2021

Aerial inspection of solar modules is becoming increasingly popular in automatizing operations and maintenance in large-scale photovoltaic power plants. Current practices are typically time-consuming as they make use of manual acquisitions and analysis of thousands of images to scan for faults and anomalies in the modules. In this paper, we explore and evaluate the use of computer vision and deep learning methods for automating the analysis of fault detection and classification in large scale photovoltaic module installations. We use convolutional neural networks to analyze thermal and visible color images acquired by cameras mounted on unmanned aerial vehicles. We generate composite images…

Computer sciencebusiness.industryDeep learningPhotovoltaic systemComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processingFault (power engineering)Convolutional neural networkFault detection and isolationFeature (computer vision)HistogramComputer visionArtificial intelligencebusiness2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)
researchProduct

CrowdVAS-Net: A Deep-CNN Based Framework to Detect Abnormal Crowd-Motion Behavior in Videos for Predicting Crowd Disaster

2019

With the increased occurrences of crowd disasters like human stampedes, crowd management and their safety during mass gathering events like concerts, congregation or political rally, etc., are vital tasks for the security personnel. In this paper, we propose a framework named as CrowdVAS-Net for crowd-motion analysis that considers velocity, acceleration and saliency features in the video frames of a moving crowd. CrowdVAS-Net relies on a deep convolutional neural network (DCNN) for extracting motion and appearance feature representations from the video frames that help us in classifying the crowd-motion behavior as abnormal or normal from a short video clip. These feature representations a…

Computer sciencebusiness.industryFeature extraction020207 software engineering02 engineering and technologyVideo processingMachine learningcomputer.software_genreConvolutional neural networkMotion (physics)Random forestFeature (computer vision)Mass gathering0202 electrical engineering electronic engineering information engineeringTask analysis020201 artificial intelligence & image processingArtificial intelligencebusinesscomputer2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
researchProduct

Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency

2018

In this work, we propose a convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes without having access to the reference. The proposed CNN architecture is fed by small patches selected carefully according to their level of saliency. To do so, the visual saliency of the 3D mesh is computed, then we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Afterward, the obtained views are split to obtain 2D small patches that pass through a saliency filter to select the most relevant patches. Experiments are conducted on two MVQ assessment databases, and the results show that the trained CNN achieves good rates in terms of corre…

Computer sciencebusiness.industryQuality assessmentDistortion (optics)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION020207 software engineeringPattern recognition02 engineering and technologyFilter (signal processing)Convolutional neural networkVisualizationSalience (neuroscience)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSaliency mapArtificial intelligencebusinessComputingMethodologies_COMPUTERGRAPHICSVisual saliency2018 25th IEEE International Conference on Image Processing (ICIP)
researchProduct

Color illusions also deceive CNNs for low-level vision tasks: Analysis and implications.

2019

The study of visual illusions has proven to be a very useful approach in vision science. In this work we start by showing that, while convolutional neural networks (CNNs) trained for low-level visual tasks in natural images may be deceived by brightness and color illusions, some network illusions can be inconsistent with the perception of humans. Next, we analyze where these similarities and differences may come from. On one hand, the proposed linear eigenanalysis explains the overall similarities: in simple CNNs trained for tasks like denoising or deblurring, the linear version of the network has center-surround receptive fields, and global transfer functions are very similar to the human …

Computer sciencemedia_common.quotation_subjectIllusionColor spaceConvolutional neural network050105 experimental psychology03 medical and health sciences0302 clinical medicinePerceptionHumans0501 psychology and cognitive sciencesVision Ocularmedia_commonArtificial neural networkbusiness.industryOptical illusion05 social sciencesIllusionsSensory SystemsOphthalmologyVision scienceHuman visual system modelArtificial intelligenceNeural Networks Computerbusiness030217 neurology & neurosurgeryVision research
researchProduct

Transferability of Deep Learning Algorithms for Malignancy Detection in Confocal Laser Endomicroscopy Images from Different Anatomical Locations of t…

2019

Squamous Cell Carcinoma (SCC) is the most common cancer type of the epithelium and is often detected at a late stage. Besides invasive diagnosis of SCC by means of biopsy and histo-pathologic assessment, Confocal Laser Endomicroscopy (CLE) has emerged as noninvasive method that was successfully used to diagnose SCC in vivo. For interpretation of CLE images, however, extensive training is required, which limits its applicability and use in clinical practice of the method. To aid diagnosis of SCC in a broader scope, automatic detection methods have been proposed. This work compares two methods with regard to their applicability in a transfer learning sense, i.e. training on one tissue type (f…

Confocal laser endomicroscopyComputer sciencebusiness.industryDeep learningTransferabilityPattern recognitionMalignancymedicine.diseaseConvolutional neural network03 medical and health sciences0302 clinical medicine030220 oncology & carcinogenesismedicinePreprocessorUpper gastrointestinalArtificial intelligence030223 otorhinolaryngologybusinessTransfer of learning
researchProduct

Deep CNN-ELM Hybrid Models for Fire Detection in Images

2018

In this paper, we propose a hybrid model consisting of a Deep Convolutional feature extractor followed by a fast and accurate classifier, the Extreme Learning Machine, for the purpose of fire detection in images. The reason behind using such a model is that Deep CNNs used for image classification take a very long time to train. Even with pre-trained models, the fully connected layers need to be trained with backpropagation, which can be very slow. In contrast, we propose to employ the Extreme Learning Machine (ELM) as the final classifier trained on pre-trained Deep CNN feature extractor. We apply this hybrid model on the problem of fire detection in images. We use state of the art Deep CNN…

Contextual image classificationArtificial neural networkComputer sciencebusiness.industryPattern recognition02 engineering and technologyConvolutional neural networkBackpropagationSupport vector machine03 medical and health sciences0302 clinical medicineSoftmax function0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessClassifier (UML)030217 neurology & neurosurgeryExtreme learning machine
researchProduct

Convolutional Neural Network for Dust and Hotspot Classification in PV Modules

2020

20th IEEE International Conference on Environment and Electrical Engineering, EEEIC 2020, online, 9 Jun 2020 - 12 Jun 2020; Energies : open-access journal of related scientific research, technology development and studies in policy and management 13(23), 6357 (2020). doi:10.3390/en13236357 special issue: "Special Issue "Selected Papers from 20 IEEE International Conference on Environment and Electrical Engineering (EEEIC 2020)" / Special Issue Editor: Prof. Dr. Rodolfo Araneo, Guest Editor"

Control and OptimizationComputer science020209 energyReal-time computingEnergy Engineering and Power Technologydiagnosticconvolutional neural network02 engineering and technology010501 environmental sciencesSettore ING-IND/32 - Convertitori Macchine E Azionamenti Elettricilcsh:Technology01 natural sciencesConvolutional neural networkphotovoltaic energyhot spotHotspot (geology)diagnostics0202 electrical engineering electronic engineering information engineeringenergy efficientElectrical and Electronic EngineeringEngineering (miscellaneous)0105 earth and related environmental sciencesSettore ING-IND/11 - Fisica Tecnica Ambientalelcsh:TRenewable Energy Sustainability and the Environmentbusiness.industryPhotovoltaic systemDirtartificial intelligencerenewable energy620Renewable energyElectricity generationinfrared thermographydustddc:620businessEnergy (miscellaneous)Efficient energy use
researchProduct

Study and Evaluation of Pre-trained CNN Networks for Cultural Heritage Image Classification

2021

The classification of digital images is an essential task during the restoration and preservation of cultural heritage (CH). In computer vision, cultural heritage classification relies on the classification of asset images regarding a certain task such as type, artist, genre, style identification, etc. CH classification is challenging as various CH asset images have similar colors, textures, and shapes. In this chapter, the aim is to study and evaluate the use of pre-trained deep convolutional neural networks such as VGG16, VGG-19, ResNet50, and Inception-V3 for cultural heritage images classification using transfer learning techniques. The main idea is to start with CNN models previously t…

Cultural heritageIdentification (information)Digital imageContextual image classificationComputer sciencebusiness.industryDeep learningPattern recognitionArtificial intelligenceTransfer of learningbusinessConvolutional neural networkTask (project management)
researchProduct

A cultural heritage experience for visually impaired people

2020

Abstract In recent years, we have assisted to an impressive advance of computer vision algorithms, based on image processing and artificial intelligence. Among the many applications of computer vision, in this paper we investigate on the potential impact for enhancing the cultural and physical accessibility of cultural heritage sites. By using a common smartphone as a mediation instrument with the environment, we demonstrate how convolutional networks can be trained for recognizing monuments in the surroundings of the users, thus enabling the possibility of accessing contents associated to the monument itself, or new forms of fruition for visually impaired people. Moreover, computer vision …

Cultural heritagePotential impactComputer scienceVisually impairedHuman–computer interactionSettore ING-INF/03 - TelecomunicazioniMediationComputer vision algorithmsImage processingnavigation visually impaired computer vision augmented reality cultural context convolutional neural network machine learning hapticPhysical accessibility
researchProduct