A Review: MIML Framework and Image Annotation

International Journal of Intelligent Systems and Applications, 2016

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.

The Semantic Web: …, 2005

Lecture Notes in Computer Science, 2003

The success of the Semantic Web hinges on being able to produce semantic markups on Web pages and their components, in a way that is cost-effective and consistent with adopted schemas and ontologies. Since images are an essential component of the Web, this work focuses on an intelligent approach to semantic annotation of images. We propose a three-layer architecture, in which the bottom layer organizes visual information extracted from the raw image contents, which are mapped to semantically meaningful keywords in the middle layer, which are then connected to schemas and ontologies on the top layer. Our key contribution is the use of machine learning algorithms for user-assisted, semi-automatic image annotation, in such a way that the knowledge of previously annotated images-both at metadata and visual levels-is used to speed up the annotation of subsequent images within the same domain (ontology) as well as to improve future query and retrieval of annotated images.

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.

2005

This paper describes a functioning system that associates semantic annotations (in the form of a table of triples of identifiers) with digital video. The first part describes a subsystem (in existence since 2002, desktop version 1995) of adding annotations to digital video. The second part builds on that subsystem, creating additional semantic annotations that enable semantic-web retrieval. The key component of the second subsystem is a glossary for the text being indexed, created by the user in interaction with Princeton's WordNet. The resulting glossary is a microformat within an XHTML document, which we validate using our microformat validator. Additional techniques for harvesting metadata from the domain expert are described. 1 Multimedia Annotator XML (MannX) MannX consists of two programs, MannX-author and MannX-player. MannX-author creates MannX applications that are accessible via MannX-player. The main functionality of MannX-author is to establish a segment-by-segment c...

Proceedings of SPIE, 2003

The paper describes an innovative image annotation tool for classifying image regions in one of seven classes -sky, skin, vegetation, snow, water, ground, and buildings -or as unknown. This tool could be productively applied in the management of large image and video databases where a considerable volume of images/frames there must be automatically indexed. The annotation is performed by a classification system based on a multi-class Support Vector Machine. Experimental results on a test set of 200 images are reported and discussed.

Internet Imaging V, 2003

The paper describes an innovative image annotation tool for classifying image regions in one of seven classes -sky, skin, vegetation, snow, water, ground, and buildings -or as unknown. This tool could be productively applied in the management of large image and video databases where a considerable volume of images/frames there must be automatically indexed. The annotation is performed by a classification system based on a multi-class Support Vector Machine. Experimental results on a test set of 200 images are reported and discussed.

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.

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.

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.