scholarly journals Survey and Analysis on Machine Learning Approaches for Image Annotation

2021 ◽  
Vol 22 (12) ◽  
Author(s):  
Palekar V.R ◽  
◽  
Palekar V.R ◽  
Dr. Satish Kumar L ◽  
◽  
...  
Keyword(s):  
Social Networking Sites ◽  
Image Annotation ◽  
Main Idea ◽  
Computation Time ◽  
Image Data ◽  
Image Understanding ◽  
Model Complexity ◽  
Learning Approaches ◽  
Rural And Urban ◽  
Modal Semantic

In current years, a large amount of image data is being collected worldwide, which is majorly generated by corporate organizations, health industry and social networking sites. With the strength of substantial level depiction of images, Annotating image has numerous applications not only in image understanding and analysis but also in some of the concern domain like medical research, rural and urban management. Automatic Image Annotation (AIA) has been raised since the late 1990s due to inherent weaknesses of manual image annotation. In this paper, a deep review of the most recent stage in the development of AIA methods is presented by synthesizing 32 literatures published during the past decades. We classify AIA methods into five categories: 1) Kernel Logistic Regression (KLR), 2) Tri-relational Graph (TG), 3) Semantically Regularised CNN- RNN (S-CNN-RNN), 4) Label Correlation guided Deep Multi-view (LCDM), and 5) Multi-Modal Semantic Hash Learning (MMSHL). Considering inspiration on the basis of main idea, framework of model, complexity of computation, time complexity and accuracy in annotation Comparative analysis for various AIA methods are done.

Using manifold structure for automatic image annotation by fusion of multiple feature spaces

2015 ◽  
Vol 2 ◽  
pp. 1 ◽  
Author(s):  
Mohammad Ali Zare Chahooki ◽  
Hamid Kargar Shooroki
Keyword(s):  
Image Annotation ◽  
Similarity Measures ◽  
Main Idea ◽  
Image Data ◽  
Spatial Relations ◽  
Data Sets ◽  
Automatic Image Annotation ◽  
Manifold Structure ◽  
Feature Spaces ◽  
Multiple Feature

Automatic image annotation has been an active research topic in recent years. Low level features like as color, texture, shape as well as object spatial relations are extracted to represent images in general. These syntaxes are further used to retrieve images from large image data sets.  However, the similarity of images could not be found correctly by similarity measures such as Euclidean distance in many situations. On the other hand, graph models have been shown powerful in solving many machine learning problems in recent years. In this paper, we propose a graph-based learning approach, named Conceptual Manifold Structure (CMS), based on transition from conceptual to observation space. In the proposed method, a graph including both the trained and tested samples is constructed by fusion of multiple feature spaces. Conceptual transition in graph structure is found by altering the edge values in an innovative manner. This is caused to learn the manifold structure where the samples dissimilarity is closer to the conceptual distance. Furthermore, the continuity between the instances of a semantic in the conceptual space is kept in feature space. Keeping the continuity in manifold structure is the main idea to decrease the semantic gap in this study. The experiments on different image data sets indicated that the geometrical distances between the samples on the manifold space are closer to their conceptual distance. The proposed method has been compared to other well-known approaches. The results confirmed the effectiveness and validity of the proposed method.

Deep Learning Approaches for Whiteboard Image Quality Enhancement

2019 ◽  
Vol 2019 (1) ◽  
pp. 360-368
Author(s):  
Mekides Assefa Abebe ◽  
Jon Yngve Hardeberg
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Image Data ◽  
Quality Enhancement ◽  
Network Architectures ◽  
Learning Approaches ◽  
Data Set ◽  
Image Quality Enhancement ◽  
Processing Techniques ◽  
White Balancing

Different whiteboard image degradations highly reduce the legibility of pen-stroke content as well as the overall quality of the images. Consequently, different researchers addressed the problem through different image enhancement techniques. Most of the state-of-the-art approaches applied common image processing techniques such as background foreground segmentation, text extraction, contrast and color enhancements and white balancing. However, such types of conventional enhancement methods are incapable of recovering severely degraded pen-stroke contents and produce artifacts in the presence of complex pen-stroke illustrations. In order to surmount such problems, the authors have proposed a deep learning based solution. They have contributed a new whiteboard image data set and adopted two deep convolutional neural network architectures for whiteboard image quality enhancement applications. Their different evaluations of the trained models demonstrated their superior performances over the conventional methods.

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

scholarly journals Machine learning approaches to calibrate individual-based infectious disease models

2021 ◽  
Author(s):  
Theresa Reiker ◽  
Monica Golumbeanu ◽  
Andrew Shattock ◽  
Lydia Burgert ◽  
Thomas A. Smith ◽  
...  
Keyword(s):  
Machine Learning ◽  
Disease Transmission ◽  
Goodness Of Fit ◽  
Epidemiological Data ◽  
Bayesian Optimization ◽  
Model Complexity ◽  
Learning Approaches ◽  
Dimensional Parameter ◽  
Novel Approach ◽  
Transmission Models

AbstractIndividual-based models have become important tools in the global battle against infectious diseases, yet model complexity can make calibration to biological and epidemiological data challenging. We propose a novel approach to calibrate disease transmission models via a Bayesian optimization framework employing machine learning emulator functions to guide a global search over a multi-objective landscape. We demonstrate our approach by application to an established individual-based model of malaria, optimizing over a high-dimensional parameter space with respect to a portfolio of multiple fitting objectives built from datasets capturing the natural history of malaria transmission and disease progression. Outperforming other calibration methodologies, the new approach quickly reaches an improved final goodness of fit. Per-objective parameter importance and sensitivity diagnostics provided by our approach offer epidemiological insights and enhance trust in predictions through greater interpretability.One Sentence SummaryWe propose a novel, fast, machine learning-based approach to calibrate disease transmission models that outperforms other methodologies

Intelligent Agent-Based e-Learning System for Adaptive Learning

2012 ◽  
pp. 145-158
Author(s):  
Hokyin Lai ◽  
Minhong Wang ◽  
Huaiqing Wang
Keyword(s):  
Individual Differences ◽  
Learning Outcomes ◽  
Adaptive Learning ◽  
Main Idea ◽  
Learning Approaches ◽  
E Learning ◽  
Treatment Interaction ◽  
Multi Agent ◽  
The Individual ◽  
Intended Learning Outcomes

Adaptive learning approaches support learners to achieve the intended learning outcomes through a personalized way. Previous studies mistakenly treat adaptive e-Learning as personalizing the presentation style of the learning materials, which is not completely correct. The main idea of adaptive learning is to personalize the earning content in a way that can cope with individual differences in aptitude. In this study, an adaptive learning model is designed based on the Aptitude-Treatment Interaction theory and Constructive Alignment Model. The model aims at improving students’ learning outcomes through enhancing their intrinsic motivation to learn. This model is operationalized with a multi-agent framework and is validated under a controlled laboratory setting. The result is quite promising. The individual differences of students, especially in the experimental group, have been narrowed significantly. Students who have difficulties in learning show significant improvement after the test. However, the longitudinal effect of this model is not tested in this study and will be studied in the future.

scholarly journals Study of methods for dimension reduction of complex dynamic linear systems models

2018 ◽  
Vol 226 ◽  
pp. 04036
Author(s):  
Yuriy M. Manatskov ◽  
Torsten Bertram ◽  
Danil V. Shaykhutdinov ◽  
Nikolay I. Gorbatenko
Keyword(s):  
Linear Systems ◽  
Main Idea ◽  
Computation Time ◽  
Order Reduction ◽  
Complex Dynamic ◽  
Model Order ◽  
Reduced Order ◽  
Advantages And Disadvantages ◽  
Optimization Stage ◽  
Linear Systems Of Equations

Complex dynamic linear systems of equations are solved by numerical iterative methods, which need much computation and are timeconsuming ones, and the optimization stage requires repeated solution of these equation systems that increases the time on development. To shorten the computation time, various methods can be applied, among them preliminary (estimated) calculation or oversimple models calculation, however, while testing and optimizing the full model is used. Reduced order models are very popular in solving this problem. The main idea of a reduced order model is to find a simplified model that may reflect the required properties of the original model as accurately as possible. There are many methods for the model order reduction, which have their advantages and disadvantages. In this article, a method based on Krylov subspaces and SVD methods is considered. A numerical experiments is given.

scholarly journals Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 726 ◽  
Author(s):  
Vanesa Lopez-Vazquez ◽  
Jose Manuel Lopez-Guede ◽  
Simone Marini ◽  
Emanuela Fanelli ◽  
Espen Johnsen ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Barents Sea ◽  
Temporal Dynamics ◽  
Image Annotation ◽  
Sustainable Use ◽  
Area Under The Curve ◽  
Video Image ◽  
Learning Approaches ◽  
Monitoring Networks ◽  
Goods And Services

An understanding of marine ecosystems and their biodiversity is relevant to sustainable use of the goods and services they offer. Since marine areas host complex ecosystems, it is important to develop spatially widespread monitoring networks capable of providing large amounts of multiparametric information, encompassing both biotic and abiotic variables, and describing the ecological dynamics of the observed species. In this context, imaging devices are valuable tools that complement other biological and oceanographic monitoring devices. Nevertheless, large amounts of images or movies cannot all be manually processed, and autonomous routines for recognizing the relevant content, classification, and tagging are urgently needed. In this work, we propose a pipeline for the analysis of visual data that integrates video/image annotation tools for defining, training, and validation of datasets with video/image enhancement and machine and deep learning approaches. Such a pipeline is required to achieve good performance in the recognition and classification tasks of mobile and sessile megafauna, in order to obtain integrated information on spatial distribution and temporal dynamics. A prototype implementation of the analysis pipeline is provided in the context of deep-sea videos taken by one of the fixed cameras at the LoVe Ocean Observatory network of Lofoten Islands (Norway) at 260 m depth, in the Barents Sea, which has shown good classification results on an independent test dataset with an accuracy value of 76.18% and an area under the curve (AUC) value of 87.59%.

scholarly journals Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials

Heredity ◽  
2020 ◽  
Vol 126 (1) ◽  
pp. 92-106 ◽  
Author(s):  
Germano Costa-Neto ◽  
Roberto Fritsche-Neto ◽  
José Crossa
Keyword(s):  
Kernel Methods ◽  
Large Scale ◽  
Additive Model ◽  
Computation Time ◽  
Reaction Norm ◽  
Model Complexity ◽  
Gaussian Kernel ◽  
Environment Interaction ◽  
Complex Structures ◽  
Processing Times

AbstractModern whole-genome prediction (WGP) frameworks that focus on multi-environment trials (MET) integrate large-scale genomics, phenomics, and envirotyping data. However, the more complex the statistical model, the longer the computational processing times, which do not always result in accuracy gains. We investigated the use of new kernel methods and modeling structures involving genomics and nongenomic sources of variation in two MET maize data sets. Five WGP models were considered, advancing in complexity from a main-effect additive model (A) to more complex structures, including dominance deviations (D), genotype × environment interaction (AE and DE), and the reaction-norm model using environmental covariables (W) and their interaction with A and D (AW + DW). A combination of those models built with three different kernel methods, Gaussian kernel (GK), Deep kernel (DK), and the benchmark genomic best linear-unbiased predictor (GBLUP/GB), was tested under three prediction scenarios: newly developed hybrids (CV1), sparse MET conditions (CV2), and new environments (CV0). GK and DK outperformed GB in prediction accuracy and reduction of computation time (~up to 20%) under all model–kernel scenarios. GK was more efficient in capturing the variation due to A + AE and D + DE effects and translated it into accuracy gains (~up to 85% compared with GB). DK provided more consistent predictions, even for more complex structures such as W + AW + DW. Our results suggest that DK and GK are more efficient in translating model complexity into accuracy, and more suitable for including dominance and reaction-norm effects in a biologically accurate and faster way.

scholarly journals Private Evaluation of Decision Trees using Sublinear Cost

2019 ◽  
Vol 2019 (1) ◽  
pp. 266-286 ◽  
Author(s):  
Anselme Tueno ◽  
Florian Kerschbaum ◽  
Stefan Katzenbeisser
Keyword(s):  
Decision Tree ◽  
Decision Trees ◽  
Main Idea ◽  
Computation Time ◽  
Tree Model ◽  
Real World Data ◽  
Data Set ◽  
Attribute Vector ◽  
Garbled Circuits ◽  
Large Trees

Abstract Decision trees are widespread machine learning models used for data classification and have many applications in areas such as healthcare, remote diagnostics, spam filtering, etc. In this paper, we address the problem of privately evaluating a decision tree on private data. In this scenario, the server holds a private decision tree model and the client wants to classify its private attribute vector using the server’s private model. The goal is to obtain the classification while preserving the privacy of both – the decision tree and the client input. After the computation, only the classification result is revealed to the client, while nothing is revealed to the server. Many existing protocols require a constant number of rounds. However, some of these protocols perform as many comparisons as there are decision nodes in the entire tree and others transform the whole plaintext decision tree into an oblivious program, resulting in higher communication costs. The main idea of our novel solution is to represent the tree as an array. Then we execute only d – the depth of the tree – comparisons. Each comparison is performed using a small garbled circuit, which output secret-shares of the index of the next node. We get the inputs to the comparison by obliviously indexing the tree and the attribute vector. We implement oblivious array indexing using either garbled circuits, Oblivious Transfer or Oblivious RAM (ORAM). Using ORAM, this results in the first protocol with sub-linear cost in the size of the tree. We implemented and evaluated our solution using the different array indexing procedures mentioned above. As a result, we are not only able to provide the first protocol with sublinear cost for large trees, but also reduce the communication cost for the large real-world data set “Spambase” from 18 MB to 1[triangleright]2 MB and the computation time from 17 seconds to less than 1 second in a LAN setting, compared to the best related work.

Sign in / Sign up

Export Citation Format

Share Document