Recognition of Dynamic Texture Patterns Using CHLAC Features

Kobayashi, Takumi; Higuchi, Tetsuya; Miyajima, Tsuneharu; Otsu, Nobuyuki

doi:10.1109/bliss.2009.31

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the support of line drawing algorithms [12,13] is helpful to handle image processing. For more comprehensive feature extraction, utilization of dynamic texture patterns was studied in [14].…”

Section: Related Workmentioning

confidence: 99%

A Novel Image Identifier Generation Method Using Luminance and Location

Park

Whangbo

Kim

2016

Wireless Pers Commun

View full text Add to dashboard Cite

It has been more than 40 years since the first digital imaging sensor was invented. For the last four decades, image acquisition functionality has continuously been improved, in terms of quality, size and cost. Consequently the digital imaging techniques started to be utilized in the digital camera industry and various component applications as well. According to the trend of the current applications of digital imaging, images are being produced not only by the conventional mechanism, such as regular camera, but also by the applications with digital image acquisition functionality, who aim to better understand the circumstances using an analysis of images. As a consequence of this trend, the amount of images created by diverse image related devices is immeasurably huge. Moreover the utilization of such voluminous amount of images demands a management system that can support information management operations, such as search, contents duplication and modification detection. These operations can be efficiently and effectively processed when the image related operations are performed by the usage of distinctive values, not by the image processing operations which require much more processing time. In order to meet the satisfaction of the requirement, we have been studied approaches that can utilize the line segments and the luminance areas. However, those approaches are disadvantage in the case of that an image contains the relatively large regions with sparse & Taeg Keun Whangbo edges or stationary luminance. In order to resolve such circumstances, in this paper, we present a more improved approach, in the perspective of cost and requirement satisfaction. The proposed method mainly exploits luminance areas and pixel location, so that the produced image identifiers could satisfy one-to-one relationship between images and identifiers. With experimental evaluations, we demonstrate that our approach is most favorable considering cost-effectiveness and efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Image Identifier Generation Method Using Luminance and Location

Park

Whangbo

Kim

2016

Wireless Pers Commun

View full text Add to dashboard Cite

show abstract

Low-cost image indexing for massive database

Park

2014

Multimed Tools Appl

View full text Add to dashboard Cite

Texture recognition by using a non-linear kernel

Al-Daoud

Al-Hanandeh

Abdallah

et al. 2013

IJCAT

View full text Add to dashboard Cite

This study proposes the use of features combination and a non-linear kernel to improve the classification rate of texture recognition. The feature vector concatenates three different sets of feature: the first set is extracted using grey-level cooccurrence matrix, the second set is collected from three different radii of local binary patterns, and the third set is generated using Gabor wavelet features. Gabor features are the mean, the standard deviation, and the skew of each scaling and orientation parameter. The aim of the new kernel is to incorporate the power of the kernel methods with the optimal balance derived from the features. To verify the effectiveness of the proposed method, numerous techniques are tested using the three data sets, which consist of various orientations, configurations and lighting conditions.

show abstract

Recognition of Dynamic Texture Patterns Using CHLAC Features

Cited by 3 publications

References 8 publications

A Novel Image Identifier Generation Method Using Luminance and Location

A Novel Image Identifier Generation Method Using Luminance and Location

Low-cost image indexing for massive database

Texture recognition by using a non-linear kernel

Contact Info

Product

Resources

About