nach oben

2017 | Buch

Kapitel lesen Erstes Kapitel lesen

Content-Based Image Retrieval

Ideas, Influences, and Current Trends

verfasst von: Dr. Vipin Tyagi

Verlag: Springer Singapore

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

The book describes several techniques used to bridge the semantic gap and reflects on recent advancements in content-based image retrieval (CBIR). It presents insights into and the theoretical foundation of various essential concepts related to image searches, together with examples of natural and texture image types. The book discusses key challenges and research topics in the context of image retrieval, and provides descriptions of various image databases used in research studies.

The area of image retrieval, and especially content-based image retrieval (CBIR), is a very exciting one, both for research and for commercial applications. The book explains the low-level features that can be extracted from an image (such as color, texture, shape) and several techniques used to successfully bridge the semantic gap in image retrieval, making it a valuable resource for students and researchers interested in the area of CBIR alike.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Content-Based Image Retrieval: An Introduction

Abstract

This chapter provides an introduction to information retrieval and image retrieval. Types of image retrieval techniques, i.e., text-based image retrieval and content-based image retrieval techniques are introduced. A brief introduction to visual features like color, texture, and shape is provided. Similarity measures used in content-based image retrieval and performance evaluation of content-based image retrieval techniques are also given. Importance of user interaction in retrieval systems is also discussed.

Vipin Tyagi

Chapter 2. Content-Based Image Retrieval Techniques: A Review

Abstract

In recent years, a rapid increase in the size of digital image databases has been observed. Everyday gigabytes of images are generated. Consequently, the search for the relevant information from image and video databases has become more challenging. To get accurate retrieval results is still an unsolved problem and an active research area. Content-based image retrieval (CBIR) is a process in which for a given query image, similar images are retrieved from a large image database based on their content similarity. A number of techniques have been suggested by researchers for content-based image retrieval. In this chapter, a review of some state-of-the-art retrieval techniques is provided.

Vipin Tyagi

Chapter 3. Region-Based Image Retrieval

Abstract

Content-based image retrieval involves extraction of global and region features for searching an image from the database. This chapter provides an introduction to content-based image retrieval according to region-based similarity known as region-based image retrieval (RBIR). Regions of interest from an image can be selected automatically by the system or can be specified by the user. It increases the accuracy of the retrieval results as regions of interests are capable of reflecting user-specific interest with greater accuracy. However, success of automatic selection of region of interest-based methods largely depends on the segmentation technique used. In this chapter, state-of-the-art techniques for region-based image retrieval are discussed.

Vipin Tyagi

Chapter 4. Similarity Measures and Performance Evaluation

Abstract

Retrieval performance of a content-based image retrieval system is affected by similarity measures used in the development of the system. Similarity measures indicate that how two images are matching to each other. Several similarity measures for retrieval have been developed by various researchers. In this chapter, some commonly used similarity measures are described. After development of a retrieval system, it is necessary to check performance of the system in terms of output generated in response to a query, in comparison to other state-of-the-art systems. This chapter also describes some common measures that are used to evaluate the performance on CBIR systems.

Vipin Tyagi

Chapter 5. MPEG-7: Multimedia Content Description Standard

Abstract

In this chapter, MPEG-7, Multimedia Description Interface Standard, is described. MPEG-7 provides a standardized metadata system for describing multimedia content using XML. MPEG-7 allows interoperable indexing, searching, and retrieval of video, images, audio, and other forms of multimedia data. In this chapter, the description tools standardized by MPEG-7 are introduced.

Vipin Tyagi

Chapter 6. Shape Feature

Abstract

Modern content-based image retrieval techniques use visual features derived directly from the content of the image. Shape is an important visual feature of an image that can be used for efficient image retrieval. In this chapter, various shape features are introduced, which can be used in deriving a feature vector for CBIR techniques.

Vipin Tyagi

Chapter 7. Color Feature

Abstract

Color is the most extensively used visual feature in content-based image retrieval. Its three-dimensional values make its discrimination potentiality superior to the single-dimensional gray values of images. Color can be retrieved easily from images without any complex preprocessing. Color feature is robust to background complication and invariant of image size and orientation of the image. There are many color spaces designed for different systems and standards. In this chapter, most used color spaces in content-based image retrieval techniques are introduced and the process to convert one color space into others is also discussed. A brief description of color descriptors of MPEG-7 standard is also given.

Vipin Tyagi

Chapter 8. Texture Feature

Abstract

Texture is an important visual feature of an image that helps in designing a feature vector for content-based image retrieval. In this chapter, the concept of texture is introduced and a number of texture features are described. Various models of the texture are discussed which can be used in content-based image retrieval. A brief description of MPEG-7 texture descriptors is also provided.

Vipin Tyagi

Chapter 9. Content-Based Image Retrieval Based on Relative Locations of Multiple Regions of Interest Using Selective Regions Matching

Abstract

In this chapter, a technique for content-based image retrieval based on selective matching of regions using region codes is described. All images in the database are uniformly divided into multiple regions, and each region is assigned a 4-bit region code based upon its location relative to the central region. Dominant color and local binary pattern (LBP)-based texture features are extracted from these regions. Feature vectors together with their region codes are stored and indexed in the database. Any two region codes are said to be similar if their logical AND operation is not 0000. During retrieval, feature vectors of regions having region codes similar to the query image region are required for comparison. To reflect the user’s intent in query formulation in a better way, an effective technique for region of interest (ROI) overlapping block selection is also proposed. Region codes are further used to find relative locations of multiple ROIs in query and target images.

Vipin Tyagi

Chapter 10. Content-Based Image Retrieval Based on Location-Independent Regions of Interest

Abstract

In this chapter, a technique of object-based image retrieval to retrieve the images based on location-independent region of interest (ROI) is given. In this technique, instead of extracting the features of the whole query image, features of the objects of interest are extracted using morphological operations. First, background subtraction is performed to reduce the effect of background intensities, then segmentation is performed, and the regions are extracted. To minimize the number of comparisons in image retrieval process, the image is categorized into texture and non-texture regions. Tetrolet transform is used to retrieve the texture features for the texture regions, while moment invariants and edge features are used for non-texture regions.

Vipin Tyagi

Chapter 11. Content-Based Image Retrieval of Texture Images Using Adaptive Tetrolet Transforms

Abstract

In this chapter, a technique for texture image retrieval based on tetrolet transforms is described. Tetrolets provide fine texture information due to its different way of analysis. Tetrominoes are applied at each decomposition level of an image, and best combination of tetrominoes is selected, which better shows the geometry of an image at each level. All three high-pass components of the decomposed image at each level are used as input for feature extraction. A feature vector is created by taking standard deviation in combination with energy at each subband. Retrieval performance of the technique in terms of accuracy is tested on group of texture images taken from benchmark databases Brodatz and VisTex. Experimental results indicate that the method (Raghuwanshi and Tyagi in Digit Signal Proc 48:50–57, 2016) achieves 78.80% retrieval accuracy on group of texture images D1 (taken from Brodatz), 84.41% on group D2 (taken from VisTex), and 77.41% on rotated texture image group D3 (rotated images from Brodatz).

Vipin Tyagi

Chapter 12. Content-Based Image Retrieval Using a Short Run Length Descriptor

Abstract

In this chapter, a content-based image retrieval technique based on a short run length descriptor (SRLD) is described. SRLD can effectively represent image local and global information. It can be viewed as an integrated representation of both color and texture properties. HSV color space is quantized to 72 bins, and SRLD is computed using short run lengths of size 2 and 3 for each color in different orientations. Short run lengths at all orientations are combined to get short run length histogram (SRLH) feature. SRLH can thoroughly describe the spatial correlation between color and texture and has the advantages of both statistical and structural approaches of texture representation. The experimental results are given that show the effectiveness of the proposed descriptor in image retrieval applications.

Vipin Tyagi

Chapter 13. Content-Based Image Retrieval Using Integrated Color, Texture, and Shape Features

Abstract

In this chapter, a content-based image retrieval technique based on the concept of region-based image retrieval has been described. This technique integrates color, texture, and shape features using local binary patterns (LBPs). In this technique, the image is divided into a fixed number of blocks and from each block LBP-based color, texture, and shape features are computed. The color and texture features are extracted using LBP histograms of quantized color image and gray-level images, respectively. Shape features are computed using the binary edge map obtained using Sobel edge detector from each block. All three features are combined to make a single completed binary region descriptor (CBRD) represented in the LBP way. To support region-based retrieval, an effective region code-based scheme is employed. In this technique, the spatial relative locations of objects are also considered to increase the retrieval accuracy.

Vipin Tyagi

Chapter 14. Multistage Content-Based Image Retrieval

Abstract

Traditional image retrieval systems match the input image by searching the whole database repeatedly for various image features. Intermediate results produced for these features are merged using data fusion techniques to produce one common output. In this chapter, an image retrieval technique is described, which retrieves similar color images in three stages. Initially, a fixed number of images are retrieved based on their color feature similarity. The relevance of the retrieved images is further improved by matching their texture and shape features, respectively. This eliminates the need of fusion and normalization techniques, which are commonly used to calculate final similarity scores. This reduces the computation time and increases the overall accuracy of the system. Moreover, in this technique, global and region features are combined to obtain better retrieval accuracy.

Vipin Tyagi

Chapter 15. Research Issues for Next Generation Content-Based Image Retrieval

Abstract

In this chapter, several research issues related to content-based image retrieval are given. Although work has been done in all these areas, but still much work is required to be done to get more effective content-based image retrieval applications.

Vipin Tyagi

Backmatter

Titel: Content-Based Image Retrieval
verfasst von: Dr. Vipin Tyagi
Verlag: Springer Singapore
Electronic ISBN: 978-981-10-6759-4
Print ISBN: 978-981-10-6758-7
DOI: https://doi.org/10.1007/978-981-10-6759-4