Color and texture descriptors

Manjunath, B.S.; Ohm, Jens-Rainer; Vasudevan, Varun; Yamada, Akio

doi:10.1109/76.927424

Cited by 1,449 publications

(809 citation statements)

References 11 publications

Supporting

Mentioning

768

Contrasting

Unclassified

Order By: Relevance

“…compact color moments, color coherence vector and color correlograms [5]. In the MPEG-7 standard, the color descriptors consist of a number of histogram descriptors, such as dominant color descriptor, color layout descriptor (CLD) and scalable color descriptor (SCD) [6]. Texture features provide an important information of the smoothness, coarseness and regularity of many real-world objects such as fruit, skin, clouds, trees, bricks and fabric, etc.…”

Section: Related Workmentioning

confidence: 99%

“…However, the performance of these texture descriptors, such as EHD [6], Gabor feature [3,6,10,40], etc., will be reduced when processing natural images. Gabor filter is widely used to extract texture features for image retrieval, because frequency and orientation representations of Gabor filter are similar to those of the human visual system, and it has been found to be particularly appropriate for texture representation and discrimination [40].…”

Section: Color Quantization Levelsmentioning

confidence: 99%

See 1 more Smart Citation

Image retrieval based on micro-structure descriptor

Liu

Zhang

et al. 2011

Pattern Recognition

298

203

View full text Add to dashboard Cite

a b s t r a c tThis paper presents a simple yet efficient image retrieval approach by proposing a new image feature detector and descriptor, namely the micro-structure descriptor (MSD). The micro-structures are defined based on an edge orientation similarity, and the MSD is built based on the underlying colors in microstructures with similar edge orientation. With micro-structures serving as a bridge, the MSD extracts features by simulating human early visual processing and it effectively integrates color, texture, shape and color layout information as a whole for image retrieval. The proposed MSD algorithm has high indexing performance and low dimensionality. Specifically, it has only 72 dimensions for full color images, and hence it is very efficient for image retrieval. The proposed method is extensively tested on Corel datasets with 15,000 natural images. The results demonstrate that it is much more efficient and effective than representative feature descriptors, such as Gabor features and multi-textons histogram, for image retrieval.Crown

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Color Quantization Levelsmentioning

confidence: 99%

Image retrieval based on micro-structure descriptor

Liu

Zhang

et al. 2011

Pattern Recognition

298

203

View full text Add to dashboard Cite

show abstract

“…The descriptors that were chosen for use by the employed highlevel classifier are the Dominant Color [7], Edge Histogram [7] and Contour Shape descriptors [2]; subsets of these descriptors are used for classification. These were chosen due to their conciseness and discriminative power.…”

Section: Mpeg-7 Low-level Descriptorsmentioning

confidence: 99%

A region-based approach to conceptual image classification

Papadopoulos

Mezaris

Kompatsiaris³

et al. 2005

IEE International Conference on Visual Information Engineering (VIE 2005)

View full text Add to dashboard Cite

Classifying images into a set of semantic categories that are meaningful to humans has proved to be a challenging and attractive problem in the field of content-based retrieval. Addressing this problem is typically based on the initial extraction of low-level features for the images and the subsequent application of a pattern recognition technique, to divide the feature space in a number of subspaces corresponding to the semantic categories. An extension to this framework is presented in this paper, aiming at the improvement of the efficiency of image classification systems. This is based on the introduction of an unsupervised still image segmentation algorithm to the process and its combination with MPEG-7 low-level descriptors and a Bayes classifier. Experimental results using different pairs of classes and corresponding data sets demonstrate the efficiency of the proposed approach.

show abstract

“…In this paper, we adopt the bag-of-features MPEG-7 [1,2,3,4,13,14,22,23,24] defined by the MPEG organization, which consists of color description (i.e., two color descriptors), texture description (i.e., two texture descriptors), and shape description (i.e., one shape descriptor). Among them, the descriptors relevant to image characteristics are as follows and the numbers of their features are shown in Table 1 To extract CLD features, an image on the RGB color space is partitioned into 8*8=64 blocks first; then, the average color of each block is calculated and converted into YCbCr color; next, each Y, Cb, Cr color space is transformed by 8x8 DCT, so that three sets of 64 DCT coefficients are obtained; finally, a zigzag scanning is performed with these three sets of 64 DCT coefficients, and CLD features are extracted with the specified length 12 (i.e., 6 coefficients from Y, 3 coefficients from Cb, and 3 coefficients from Cr).…”

Section: Feature Extractionmentioning

confidence: 99%

Content-Based Image Retrieval System for Real Images

Huang¹,

Chen²

EPiC Series in Computing

View full text Add to dashboard Cite

With the rapid progress of network technologies and multimedia data, information retrieval techniques gradually become content-based, and not text-based yet. In this paper, we propose a content-based image retrieval system to query similar images in a real image database. First, we employ segmentation and main object detection to separate the main object from an image. Then, we extract MPEG-7 features from the object and select relevant features using the SAHS algorithm. Next, two approaches "one-againstall" and "one-against-one" are proposed to build the classifiers based on SVM. To further reduce indexing complexity, K-means clustering is used to generate MPEG-7 signatures. Thus, we combine the classes predicted by the classifiers and the results based on the MPEG-7 signatures, and find out the similar images to a query image. Finally, the experimental results show that our method is feasible in image searching from the real image database and more effective than the other methods.

show abstract

Color and texture descriptors

Cited by 1,449 publications

References 11 publications

Image retrieval based on micro-structure descriptor

Image retrieval based on micro-structure descriptor

A region-based approach to conceptual image classification

Content-Based Image Retrieval System for Real Images

Contact Info

Product

Resources

About