A hybrid image content analysis system using semantic and neural networks (original) (raw)

Related papers

Image Content Analysis Using Neural Networks and Genetic Algorithms

Computer Engineering and Intelligent Systems, 2014

The analysis of digital images for content discovery is a process of identifying and classifying patterns and subimages that can lead to recognizing contents of the processed image. The image content analysis system presented in this paper aims to provide the machine with the capability to simulate in some sense, a similar capability in human beings. The developed system consists of three levels. In the low level, image clustering is performed to extract features of the input data and to reduce dimensionality of the feature space. Classification of the scene images are carried out using a single layer neural network, trained through Kohonen's self-organizing algorithm, with conscience function, to produce a set of equi-probable weights vector. The intermediate level consists of two parts. In the first part an image is partitioned into homogeneous regions with respect to the connectivity property between pixels, which is an important concept used in establishing boundaries of objects and component regions in an image. For each component, connected components can be determined by a process of component labeling. In the second part, feature extraction process is performed to capture significant properties of objects present in the image. In the high level; extracted features and relations of each region in the image are matched against the stored object models using the genetic algorithm approach. The implemented system is used in the analysis and recognition of colored images that represent natural scenes.

Recognition of Semantic Content in Image and Video

International Journal of Computer Applications, 2013

This paper addresses the problem of recognizing semantic content from images and video for content based retrieval purposes. Semantic features are derived from a collection of low-level features based on color, texture and shape combined together to form composite feature vectors. Both Manhattan distance and Neural Networks are used as classifiers for recognition purposes. Discrimination is done using five semantic classes viz. mountains, forests, flowers, highways and buildings. The composite feature is represented by a 26-element vector comprising of 18 color components, 2 texture components and 6 shape components.

Content Based Image Recognition: A Contemporary Approach Using Neural

Artificial Neural Networks (ANNs) are contemporary development approaches that are inspired from natural neural systems. The capable side of this new technique is its capacity to resolve the issues that are difficult to be fathomed by traditional methods of computing. Three primary visual contents of image are shape, color and texture; these features are playing key role in the recognition of image. This research study briefly describes the ANN and their applications. Multilayer perceptrons has been used as ANN for efficient content based image recognition from image repository.

Neural Network and Genetic Algorithm for Image Processing System

Content of image analysis is a process of discovering and understanding patterns that are relevant to the performance of an image based task. One of the principle goals of content of image analysis by computer is to endow a machine with the capability to approximate in some sense, a similar capability in human beings. The system, which we have developed, consists of three levels. In the low level, image clustering is performed to extract the features of the input data and to reduce the dimensionality of the feature space. Classification of the scene images was carried out by using a single layer neural network trained by the competitive algorithm that that is called Kohonen Self _ Organization with conscience function to produce a set of equiprobable weight vector. The intermediate level consists of two parts. In the first part an image is partitioned into homogeneous regions with respect to the connectivity property between pixels, which is an important concept used in establishing boundaries of objects and component regions in an image. For each component, connected components can be determined by a process called component labeling. In the second part, feature extraction process is performed to capture significant properties of objects present in the image. Binary code will be used to represent the features because GA will be used in the high level. In the high level; extracted features and relations of each region in the image are matched against the stored object models using genetic algorithm. The images used to recognize are colored images that represent natural scenes.

Image processing with neural networks—a review

We review more than 200 applications of neural networks in image processing and discuss the present and possible future role of neural networks, especially feed-forward neural networks, Kohonen feature maps and Hopÿeld neural networks. The various applications are categorised into a novel two-dimensional taxonomy for image processing algorithms. One dimension speciÿes the type of task performed by the algorithm: preprocessing, data reduction=feature extraction, segmentation, object recognition, image understanding and optimisation. The other dimension captures the abstraction level of the input data processed by the algorithm: pixel-level, local feature-level, structure-level, object-level, object-set-level and scene characterisation. Each of the six types of tasks poses speciÿc constraints to a neural-based approach. These speciÿc conditions are discussed in detail. A synthesis is made of unresolved problems related to the application of pattern recognition techniques in image processing and speciÿcally to the application of neural networks. Finally, we present an outlook into the future application of neural networks and relate them to novel developments.

Learning Semantic Concepts from Visual Data Using Neural Networks

2003

Abstract. For content-based image retrieval techniques, query image is used to pick up and rank some relevant images from a database using some certain similarity metric. If semantic features are not involved in the modeling of visual data, the resulting system may demonstrate a disability of retrieving images likely associated with interesting semantic concepts of objects in the images.

A Contribution to Image Semantic Analysis

2004

This contribution deals with semantic analysis of image. The image is divided into areas called segments. Each segment may have assigned one or more semantic networks. These semantic networks are applied when providing an image description or completing image based on segments and might be created based on a verbal description of image or based on verbal facts creating basis for completing image. However, this contribution deals with a life cycle of image, structure, features and creation of the above-mentioned semantic networks, as well.

Recognition of Semantic Content in Image and Video (IJCA 2013)

Int. Journal of Computer Applications (IJCA), 2013

This paper addresses the problem of recognizing semantic content from images and video for content based retrieval purposes. Semantic features are derived from a collection of low-level features based on color, texture and shape combined together to form composite feature vectors. Both Manhattan distance and Neural Networks are used as classifiers for recognition purposes. Discrimination is done using five semantic classes viz. mountains, forests, flowers, highways and buildings. The composite feature is represented by a 26-element vector comprising of 18 color components, 2 texture components and 6 shape components.

Semantic Image Analysis Using a Symbolic Neural Architecture

Image Analysis & Stereology, 2010

Image segmentation and classification are basic operations in image analysis and multimedia search which have gained great attention over the last few years due to the large increase of digital multimedia content. A recent trend in image analysis aims at incorporating symbolic knowledge representation systems and machine learning techniques. In this paper, we examine interweaving of neural network classifiers and fuzzy description logics for the adaptation of a knowledge base for semantic image analysis. The proposed approach includes a formal knowledge component, which, assisted by a reasoning engine, generates the a-priori knowledge for the image analysis problem. This knowledge is transferred to a kernel based connectionist system, which is then adapted to a specific application field through extraction and use of MPEG-7 image descriptors. Adaptation of the knowledge base can be achieved next. Combined segmentation and classification of images, or video frames, of summer holidays...

Image Classification Using Neural Networks and Ontologies

The advent of extremely powerful home PCs and the growth of the Internet have made the appearance of multimedia documents a common sight in the computer world. In the world of unstructured data composed of images and other media types, classification often comes at the price of countless hours of manual labor. This research aims to present a scalable system capable of examining images and accurately classifying the image based on its visual content. When retrieving images based on a user's query, the system will yields a minimal amount of irrelevant information (high precision) and insure a maximum amount of relevant information (high recall).