An image retrieval system is a computer system for browsing, searching and retrieving images from a large database of digital images. A robust natural, geographic and medical image retrieval using a supervised classifier which concentrates on extracted features is proposed. Gray level co-occurrence matrix (GLCM),Scale invariant feature technique(SIFT) and moment invariant features are implemented to extract the features from natural images and GLCM and Gabor feature extraction is done on medical images. Then these features are passed through SVM classifier. SVM classifies whether the input is Geographic or natural or medical image. Based on the SVM result, the retrieval process is done with Euclidean distance. The performance comparison is done with standard features such as colour and texture.
Keywords-Gabor, GLCM, moment invariant, SIFT, SVM.
Content-based image retrieval is a technique, which uses visual contents to search images from large scale image databases according to users' interests and it has been an active and fast advancing research area since the 1990s. A necessity for developing a successful CBIR system is the extraction of discriminant features to describe the images in the database. As such, the development of feature extraction algorithms has dominated the literature in the field, where the ultimate goal is to retrieve visually similar images.
In this paper, retrieval is done for natural and geographic images using SIFT, GLCM and moment invariant techniques .In similar to this, GLCM and Gabor techniques are adopted for medical images. Advantages of using these feature extraction algorithms are better error tolerance with fewer matches, reliability, efficient and best image matching task.
... middle of paper ...
...of-visual words’, IEEE Geosci. Remote Sens. Lett, vol. 7, no. 2, pp. 366–370.
 Goncalves J and Goncalves H (2011),’Automatic image registration through image segmentation and SIFT’, IEEE Trans. Geosci.Remote Sens., vol. 49, no. 7, pp. 2589–2600.
 Gool L.J, Moons T and Ungureanu D (2000),’Affine/photometric invariants for planar intensity patterns’, in Proc. Eur. Conf. Comput. Vis., pp. 642–651.
 Hongyu Y and Wen C (2004), ‘Remote sensing imagery retrieval based- on Gabor texture feature classification, in Proc. Int. Conf. Signal Process., pp. 733–736.
 Lindeberg T (1998), ‘Feature detection with automatic scale selection’, Int. J. Comput. Vis., vol. 30, no. 2, pp. 79–116.
 H.Lang, R. Hanka, and H. H. S. Ip(2003), “Histological image retrieval based on semantic content analysis,” IEEE Trans. Inf. Technol. Biomed., vol. 7, no. 1, pp. 26–36.
Need Writing Help?
Get feedback on grammar, clarity, concision and logic instantly.Check your paper »
- Introduction This paper discusses the design and implementation of an image recognition /retrieval system indexed with parameterized color histogram. As the usage of multimedia data has increased in recent years, effective and efficient methods for storing and retrieving multimedia have been required and are being developed. In particular, images are used as important inputs in a variety of areas. The area of content-based image retrieval is a hybrid research area that requires knowledge of both computer vision and of database systems.... [tags: image recognition, query images, color]
1685 words (4.8 pages)
- The biggest issue when it comes to creating a system for image retrieval based on image queries is the semantic gap. The semantic gap is defined as “the lack of coincidence between the information that one can extract from the visual data and the interpretation that the same data have for a user in a given situation” (Smeulders). What a system can discern from an image can be completely different to what a human user can discern. It can also be the case that two human users assign different descriptions for the same image, adding to the complexity of the problem.... [tags: vision science, human vision system HVS]
1271 words (3.6 pages)
- This paper introduces an effective method for query adaptive image retrieval using low-level feature extraction and hashing method. The low-level feature primarily constitute color, shape and texture features. For color feature extraction color moments, color Histogram and color correlogram method were implemented and for texture feature extraction used wavelet moment method. Hashing methods is used to embed high-dimensional image features into Hamming space, where search can be performed in real-time based on Hamming distance of compact hash codes.... [tags: effective method, querry adaptive image retrieval]
1021 words (2.9 pages)
- ... In these systems, there exists a tradeoff between accuracy and computational cost. This tradeoff decreases as more efficient algorithms are utilized and increased computational power thus making it inexpensive. Moreover, the existing systems produce efficient results with small and medium sized image databases, but are generally ill-suited when applied to large sized image databases. This research work designs and proposes techniques to improve the process of image retrieval from large databases in terms of accuracy and speed.... [tags: multimedia, searching, indexing]
722 words (2.1 pages)
- Question 1. Differentiate between database management system and information retrieval system by focusing on their functionalities. Database Management System (as known as DBMS) is a set of application that enable user to create, edit, update, store and retrieve data from database files. By using DBMS, data in a database can be added, deleted, changed, sorted and searched. DBMSs are usually used to manage employee information of a big company, customer information and stock information. By using the DBMS, there are advantages and disadvantages.... [tags: Technology, Data]
1417 words (4 pages)
- Introduction: The chapter we will be looking at today will be discussing electronic and image records. We will focus are time on key terms and key idea throughout of the chapter. The first part of this paper we are going to be look at electronic media; the second part will be record security and safety; and the final part will be image media. Electronic media will be addressing the key ideas; such as relationship between “electronic and image records; magnetic and optical media; removable data storage devices; data input; storage and retrieval procedures.”(342-348) The second part we will look at records safety and security.... [tags: electronic media, security, safety, image media]
1428 words (4.1 pages)
- While first reading the article entitled as the seven ages of information retrieval written by Micheal Lesk, it shows that the development of information retrieval is discussed by using the concept of life span produced by the most popular literature, Shakespeare. The author was highlighted the major point used by Shakespeare starting from childhood until retirement to be adapted on the expectation of the article that he has been read before which is the article written by Vennevar Bush in 1945.... [tags: Life Span, Elements]
1634 words (4.7 pages)
- Michael Lesk adopts Shakespeare’s theory of seven ages of human being which start from infancy to senility to predict the evolution of Information Retrieval from 1945 to 2010. In this paper, Lesk tried to compare two approaches to information retrieval. The first approach is intellectual analysis by human and machine – artificial intelligence introduced by Vannevar Bush’s. The second approach is simple exhaustive processing – statistical detail introduced by Warren Weaver’s .The paper was written in 1995, when the Internet and World Wide Web technology still crawling to grow.... [tags: Intellectual Analysis, Exhaustive Processing]
1286 words (3.7 pages)
- ... Here, a new candidate mark is compared with existing marks for trademark image searching (Wei et al., 2009; Phan and Androutsos, 2010) or a hidden secret image is compared to identify the intellectual owners for copyright mark searching (Zhang and Ye, 2009). CBIR systems belonging to this category include TRADEMARK (Kato, 1992), STAR (Wu et al., 1996) and ARTISAN (Eakins et al., 1998). • Architectural and Engineering Design Architectural and Engineering design share a number of common features like the use of stylized 2D and 3D models to represent design objects (Khokher and Talwar, 2012).... [tags: analysis, database, crime prevention]
2749 words (7.9 pages)
- I. INTRODUCTION Digital images are composed of pixels. Each pixel represents the colour at a single point of the image. Rectangular array of pixels are called as a bitmap or a digital image. Advance development of image procurement and storage technology have lead to marvellous development in very huge and detailed image databases . A massive volume of image data such as digital photographs, medical images and satellite images are generated every day . Image mining can automatically extract meaningful information from a huge of image data are increasingly in demand.... [tags: Image Mining Essays]
3064 words (8.8 pages)