Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
The Images Database
Applying One of Automatic Annotation Methods
References

A Review of Methods of Instance-based Automatic Image Annotation

Profile image of morad derakhshanmorad derakhshan

2016, International Journal of Intelligent Systems and Applications

https://doi.org/10.5815/IJISA.2016.12.04
visibility

…

description

11 pages

link

1 file

Abstract

Today, to use automatic image annotation in order to fill the semantic gap between low level features of images and understanding their information in retriev ing process has become popular. Since automatic image annotation is crucial in understanding digital images several methods have been proposed to automatically annotate an image. One of the most important of these methods is instance-based image annotation. As these methods are vastly used in this paper, the most impo rtant instance-based image annotation methods are analy zed. First of all the main parts of instance-based automatic image annotation are analyzed. Afterwards, the main methods of instance-based automatic image annotation are reviewed and co mpared based on various features. In the end the most important challenges and open-ended fields in instance-based image annotation are analyzed.

Related papers

Review: Automatic Semantic Image Annotation
Aliaa Youssif

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 2016

There are many approaches for automatic annotation in digital images. Nowadays digital photography is a common technology for capturing and archiving images because of the digital cameras and storage devices reasonable price. As amount of the digital images increase, the problem of annotating a specific image becomes a critical issue. Automated image annotation is creating a model capable of assigning terms to an image in order to describe its content. There are many image annotation techniques that seek to find the correlation between words and image features such as color, shape, and texture to provide an automatically correct annotation words to images which provides an alternative to the time consuming work of manual image annotation. This paper aims to cover a review on different Models (MT, CRM, CSD-Prop, SVD-COS and CSD-SVD) for automating the process of image annotation as an intermediate step in image retrieval process using Corel 5k images.

View PDFchevron_right
Semi-Automatic Image Annotation
Brent Field, Yanfeng Sun

2001

A novel approach to semi-automatically and progressively annotating images with keywords is presented. The progressive annotation process is embedded in the course of integrated keyword-based and content-based image retrieval and user feedback. When the user submits a keyword query and then provides relevance feedback, the search keywords are automatically added to the images that receive positive feedback and can then facilitate keyword-based image retrieval in the future. The coverage and quality of image annotation in such a database system is improved progressively as the cycle of search and feedback increases. The strategy of semi-automatic image annotation is better than manual annotation in terms of efficiency and better than automatic annotation in terms of accuracy. A performance study is presented which shows that high annotation coverage can be achieved with this approach, and a preliminary user study is described showing that users view annotations as important and will likely use them in image retrieval. The user study also suggested user interface enhancements needed to support relevance feedback. We believe that similar approaches could also be applied to annotating and managing other forms of multimedia objects.

View PDFchevron_right
Automatic Annotation Process with Objects and Relationships Detection of Images
Yassine Ayadi

2009

The semantic annotation of the images present diffi culties dependent mainly on the tridimentionnal asp ect of the image structures, either with spatial context i nfluence, or with the required human effort. It is hus necessary to have automatic methods to facilitate image annotation. T he present study is interested s', registered voter in this context and we interest in the object classifications and autom atic Relationship detection between them.

View PDFchevron_right
A novel refinement method for automatic image annotation systems
Fatos Tunay Yarman Vural

2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU), 2011

I hereby declare that all information in this document has been obtained and presented in accordance with academic rules and ethical conduct. I also declare that, as required by these rules and conduct, I have fully cited and referenced all material and results that are not original to this work.

View PDFchevron_right
A Novel Technique to Image Annotation using Neural Network.pdf
Dr. Amit Sinhal

Automatic annotation of digital pictures is a key technology for managing and retrieving images from large image collection. Traditional image semantics extraction and representation schemes were commonly divided into two categories, namely visual features and text annotations. However, visual feature scheme are difficult to extract and are often semantically inconsistent. On the other hand, the image semantics can be well represented by text annotations. It is also easier to retrieve images according to their annotations. Traditional image annotation techniques are time-consuming and requiring lots of human effort. In this paper we propose Neural Network based a novel approach to the problem of image annotation. These approaches are applied to the Image data set. Our main work is focused on the image annotation by using multilayer perceptron, which exhibits a clear-cut idea on application of multilayer perceptron with special features. MLP Algorithm helps us to discover the concealed relations between image data and annotation data, and annotate image according to such relations. By using this algorithm we can save more memory space, and in case of web applications, transferring of images and download should be fast. This paper reviews 50 image annotation systems using supervised machine learning Techniques to annotate images for image retrieval. Results obtained show that the multi layer perceptron Neural Network classifier outperforms conventional DST Technique.

View PDFchevron_right
Automatic Image Annotation
Adrian Iftene

In the recent years, multimedia content has grown increasingly over the Internet, especially in social networks, where users often post images using their mobile devices. In these networks such as Flickr, the content is later used in search operations when some users want to find something using a specific query. Nowadays, searching into these networks is primarily made using the title and the keywords associated to resources added by users that have posted the content. The problem we face comes from the fact that in many cases, the title or the related keywords are not relevant to the resource and only after we analyse the image, can we conclude what it contains in reality. The project that we want to present in this article proposes that each image is connected to relevant keywords according to its content. In order to do this, the first step was to create a collection of images that was annotated by human annotators, while the second step was to expand this collection of images performing search on the Internet using keywords associated to the initial collection of annotated images. Currently, for a new picture, we can identify similar images in our collection of images and based on the keywords associated with them, we can determine what keywords characterize this new image. The evaluation of this system has demonstrated that our approach works efficiently for images for which we can find similar images in our collection.

View PDFchevron_right
Image Content Annotation Based on Visual Features
Philip Ogunbona

Eighth IEEE International Symposium on Multimedia (ISM'06), 2006

Automatic image content annotation techniques attempt to explore structural visual features of images that describe image content and associate them with image semantics. In this paper, two types of concept spaces, atomic concept and collective concept spaces, are defined and the annotation problems in those spaces are formulated as feature classification and Bayesian inference, respectively. A scheme of image content annotation in this framework is presented and evaluated as an application of photo categorization using MPEG-7 VCE2 dataset and its ground truth. The experimental results show a promising performance.

View PDFchevron_right
Cascade of Multi-Level Multi-Instance Classifiers for Image Annotation
Cam Ha Le

Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, 2011

This paper introduces a new scheme for automatic image annotation based on cascading multi-level multiinstance classifiers (CMLMI). The proposed scheme employs a hierarchy for visual feature extraction, in which the feature set includes features extracted from the whole image at the coarsest level and from the overlapping sub-regions at finer levels. Multi-instance learning (MIL) is used to learn the "weak classifiers" for these levels in a cascade manner. The underlying idea is that the coarse levels are suitable for background labels such as "forest" and "city", while finer levels bring useful information about foreground objects like "tiger" and "car". The cascade manner allows this scheme to incorporate "important" negative samples during the learning process, hence reducing the "weakly labeling" problem by excluding ambiguous background labels associated with the negative samples. Experiments show that the CMLMI achieve significant improvements over baseline methods as well as existing MIL-based methods.

View PDFchevron_right
A Review of Image Annotation Methods
Editor IJMTER

Image annotation has been an active research issue in the recent years due to its potentially large impact on both image understanding and image retrieval. Image annotation can be viewed as multi-label learning problem in most of the studies where each image could contain multiple objects and consequently could be associated with a set of labels. Large amount of research have been done on image retrieval in the past two decades. However, recently research is focusing to bridge the semantic gap between low level image features and high level semantic tags used to express image content. In this paper, we present acomprehensive survey on latest development in automatic image annotation and tag ranking.

View PDFchevron_right
A Mathematical Approach Towards Semi-Automatic Image Annotation
Lasantha Seneviratne

2011

Publication in the conference proceedings of EUSIPCO, Barcelona, Spain, 2011

View PDFchevron_right

References (17)

  1. A. M akadia, V. Pavlovic, and S. Kumar. 2010. Baselines for Image Annotation. International Journal of Computer Vision 90, 1 (2010), 88-105.
  2. M. Guillaumin, T. M ensink, J. Verbeek, and C. Schmid. 2009. TagProp: Discriminative M etric Learning in Nearest Neighbor M odels for Image Auto-Annotation. In Proc. of ICCV.
  3. J. Verbeek, M . Guillaumin, T. M ensink, and C. Schmid. 2010. Image annotation with TagProp on the M IRFLICKR set. In Proc. of ACM M IR.
  4. X. Li, C. Snoek, and M . Worring. 2009b. Learning Social Tag Relevance by Neighbor Voting. IEEE Transactions on M ultimedia 11, 7 (2009), 1310-1322.
  5. D. Liu, X.-S. Hua, L. Yang, M . Wang, and H.-J.Zhang. 2009. Tag Ranking. In Proc. of WWW.
  6. G. Zhu, S. Yan, and Y. M a. 2010. Image Tag Refinement Towards Low-Rank, Content-Tag Prior and Error Sparsity. In Proc. of ACM M ultimedia.
  7. K. van de Sande, T. Gevers, and C. Snoek. 2010. Evaluating Color Descriptors for Object and Scene Recognition. IEEE Transactions on Pattern Analysis and M achine Intelligence 32, 9 (2010), 1582-1596.
  8. J. Sang, C. Xu, and J. Liu. 2012. User-Aware Image Tag Refinement via Ternary Semantic Analysis. IEEE Transactions on M ultimedia 14, 3 (2012), 883-895.
  9. L. Chen, D. Xu, I. Tsang, and J. Luo. 2012. Tag-Based Image Retrieval Improved by Augmented Features and Group-Based Refinement. IEEE Transactions on M ultimedia 14, 4 (2012), 1057-1067.
  10. X. Li and C. Snoek. 2013. Classify ing tag relevance with relevant positive and negative examples. In Proc. of ACM M ultimedia.
  11. A. Znaidia, H. Le Borgne, and C. Hudelot. 2013. Tag Completion Based on Belief Theory and Neighbor Voting. In Proc. of ACM ICM R.
  12. Z. Lin, G. Ding, M . Hu, J. Wang, and X. Ye. 2013. Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions. In Proc. of CVPR.
  13. X. Zhu, W. Nejdl, and M . Georgescu. 2014. An Adaptive Teleportation Random Walk M odel for Learning Social Tag Relevance. In Proc. of SIGIR.
  14. Y. Yang, Y. Gao, H. Zhang, J. Shao, and T.-S. Chua. 2014. Image Tagging with Social Assistance. In Proc. Of ACM ICM R..
  15. K. van de Sande, T. Gevers, and C. Snoek. 2010. Evaluating Color Descriptors for Object and Scene Recognition. IEEE Transactions on Pattern Analysis and M achine Intelligence 32, 9 (2010), 1582-1596.
  16. G. Zhu, S. Yan, and Y. M a. 2010. Image Tag Refinement Towards Low-Rank, Content-Tag Prior and Error Sparsity. In Proc. of ACM M ultimedia.
  17. B. Truong, A. Sun, and S. Bhowmick. 2012. Content is still king: the effect of neighbor voting schemes on tag relevance for social image retrieval. In Proc. of ACM ICM R.

Related papers

Automated annotation system for natural images
Gabriel Mihai

Automated annotation of digital images remains a highly challenging task. This process can be used for indexing, retrieving, and understanding of large collections of image data. This paper presents an image annotation system used for annotating natural images. The proposed system is using an efficient annotation model called Cross Media Relevance Model for the annotation process. Image's regions are described using a vocabulary of blobs generated from image features using the K-means clustering algorithm. Using SAIAPR TC-12 Dataset of annotated images it is estimated the joint probability of generating a word given the blobs in an image. The annotation process of each new image starts with a segmentation phase. An original and efficient segmentation algorithm based on a hexagonal structure is applied to obtain the list of regions. Each meaningful word assigned to the annotated image is retrieved from an ontology derived in an original manner starting from the hierarchical vocab...

View PDFchevron_right
Methods for automatic and assisted image annotation
Arnaldo Abrantes

Multimedia Tools and Applications, 2011

Personal memories composed of digital pictures are very popular at the moment. To retrieve these media items annotation is required. During the last years, several approaches have been proposed in order to overcome the image annotation problem. This paper presents our proposals to address this problem. Automatic and semi-automatic learning methods for semantic concepts are presented. The automatic method is based on semantic concepts estimated using visual content, context metadata and audio information. The semi-automatic method is based on results provided by a computer game. The paper describes our proposals and presents their evaluations.

View PDFchevron_right
Automated image annotation process: A general overview
Gabriel Mihai

2014

Automated image annotation process consists in assigning meaningful keywords to an image by taking into account its visual content. This process has received a great interest because it allows indexing, retrieving, and understanding of large collections of image data. The results of the annotation process are directly influenced by the quality of the regions obtained during the segmentation process. Image segmentation is a difficult and challenging task in image processing, consisting in dividing an image into different and homogeneous regions. Since there are multiple segmentation algorithms in the literature, numerical evaluations are needed in order to quantify the consistency between them. Error measures can be used for consistency quantification because are allowing a principled comparison between segmentation results on different images. This paper presents the steps involved by the annotation process: choosing a segmentation algorithm based on an evaluation performed with seg...

View PDFchevron_right
A Neural Network Model for Automatic Image Annotation and Annotation Refinement: A survey
Bhavesh Prajapati

International Journal of Engineering Development and Research, 2014

To retrieve an image from large image database is somehow very difficult task of image retrieval system. There are many methods proposed in the past to retrieve an image but still research has been going on to build an efficient method. Image can be retrieve by using visual low-level content such as shape, color, and texture or by using tags or keywords which are described by the semantic meaning of given image. To retrieve images using low-level visual features user needs to give an input as a query image and image retrieval gives set of images which are visually similar to given query image. But it is very difficult for many users to get query image each time which suffice their requirement. Content based image retrieval (CBIR) is a method which retrieves image based on low-level visual features. So to overcome problem of CBIR another method is to classify semantically all the images of the database as keywords. The entire database images are classified as a set of keywords and images can be retrieved based on these keywords. The main advantage of such method is that user can retrieve image in the same manner as they retrieve text document. One method is to manually classify all images; but it is very difficult and time consuming to classify large quantity of images manually, so some sort of automated method is required to perform this task. Automatic Image Annotation (AIA) is an automated method which maps low-level visual features for the high-level semantic features of the given image. This research paper is based on our survey of various AIA methods, where All the AIA methods consist of Artificial Neural Networks as a classification network. I.INTRODUCTION Nowadays; with the frequent and easy access to the digital gadgets such as Digital Cameras and Mobiles etc., information in the form of digital images is increasing. Image based database is increasing leaps and bounds. To retrieve the unique image from the large image database, effective and efficient method is required. One method is content based image retrieval (CBIR) in which image is retrieved based on low level features like shape, color and texture. In this method user needs to apply query image in CBIR and similar images based on sample query image is retrieve by the system. But there is a semantic gap between low level visual feature and high level semantic concept that are used by the user. In manual image annotation, images are annotated manually by the user, so that images can be retrieved as easy as retrieving text document. This method is accurate but it is also inefficient because of the manual assignment of keywords to image, which is cumbersome and time consuming process. To overcome such problems of manual image annotation and to bridge the semantic gap, research in this area shifted to Automatic Image Annotation [1]. Automatic Image Annotation (AIA) is a technique in which keywords are automatically assigned to image by using some machine learning techniques. The main concept of AIA is to automatically learn semantic concept model from large number of image database and use the concept model to label new images. Basically AIA techniques can be divided into two parts: (1) Visual feature extraction and (2) classification and Annotation. A surveys on different AIA techniques is given in zhang et al[1] and hafidha et al[2]. From various known techniques; to build a classification network for AIA, One method is to learn semantic concept is using Artificial Neural Networks (ANN). ANNs are information processing system inspired by the ability of the human brain to learn from observation. ANN is a learning network which consists of multiple layers of interconnected nodes, which are also known as neurons or perceptions. An ANN can learn from example and make decision for a new sample. Different from other common classifiers which usually learn one class at a time, ANN can learn multiple classes at a time. The rest part of paper is arranged in four sections. Section II describes an AIA system. Section III shows various low level visual features. Section IV described how neural network is used in AIA and Section V focus on annotation refinement methods, finely conclusion is given in section VI.

View PDFchevron_right
An Approach to Efficient Image Annotation
shivanand singh

As the number of Web images is increasing at a rapid rate, searching them semantically presents a significant challenge. Many raw images are constantly uploaded with few meaningful direct annotations of semantic content, limiting their search and discovery. In this paper, a semantic annotation technique based on the use of image parametric dimensions and metadata is presented. Using SVM classifier and rule induction, a rule-based approach is developed to formulate explicit annotations for images fully automatically, so that by the use of this method, a semantic query can be answered. Experimental results indicate that this approach is able to deliver a highly competent performance, attaining good recall and precision rates. This approach enables a new degree of semantic richness to be automatically associated with images which previously could only be performed manually.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved