Parallel implementation of Gray Level Co-occurrence Matrices and Haralick texture features on cell architecture

Authors:
Asadollah Shahbahrami;Tuan Anh Pham;Koen Bertels
Affiliations:
Department of Computer Engineering, Faculty of Engineering, University of Guilan, Rasht, Iran;Computer Engineering Laboratory, Faculty of EEMCS, Delft University of Technology, Delft, The Netherlands 2628 CD;Computer Engineering Laboratory, Faculty of EEMCS, Delft University of Technology, Delft, The Netherlands 2628 CD
Venue:
The Journal of Supercomputing
Year:
2012

Citing 13
Cited 2

A transfer network for the Arbitrary Rotation of Digitised Images

The Computer Journal
An FPGA-Based Architecture for Real Time Image Feature Extraction

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
An FPGA Based Coprocessor for GLCM and Haralick Texture Features and their Application in Prostate Cancer Classification

Analog Integrated Circuits and Signal Processing
FPGA architecture for fast parallel computation of co-occurrence matrices

Microprocessors & Microsystems
Texture Measures for Automatic Classification of Pulmonary Disease

IEEE Transactions on Computers
Cell broadband engine architecture and its first implementation: a performance view

IBM Journal of Research and Development
Study of content-based image retrieval using parallel computing technique

CHINA HPC '07 Proceedings of the 2007 Asian technology information program's (ATIP's) 3rd workshop on High performance computing in China: solution approaches to impediments for high performance computing
Color Spatial Feature Extraction for Image Indexing - A Case Study on the Cell B. E. Processor

CISP '08 Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 2 - Volume 02
FPGA-based System for Real-Time Video Texture Analysis

Journal of Signal Processing Systems
Scalar Processing Overhead on SIMD-Only Architectures

ASAP '09 Proceedings of the 2009 20th IEEE International Conference on Application-specific Systems, Architectures and Processors
Parallel Implementation of Good Feature Extraction for Tracking on the Cell Processor with OpenCV Interface

IIH-MSP '09 Proceedings of the 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing
A scalable and embedded FPGA architecture for efficient computation of grey level co-occurrence matrices and Haralick textures features

Microprocessors & Microsystems
Dedicated hardware for real-time computation of second-order statistical features for high resolution images

ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems

Accelerating satellite image based large-scale settlement detection with GPU

Proceedings of the 1st ACM SIGSPATIAL International Workshop on Analytics for Big Geospatial Data
High performance implementation of texture features extraction algorithms using FPGA architecture

Journal of Real-Time Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Texture features extraction algorithms are key functions in various image processing applications such as medical images, remote sensing, and content-based image retrieval. The most common way to extract texture features is the use of Gray Level Co-occurrence Matrices (GLCMs). The GLCM contains the second-order statistical information of spatial relationship of the pixels of an image. Haralick texture features are extracted using these GLCMs. However, the GLCMs and Haralick texture features extraction algorithms are computationally intensive. In this paper, we apply different parallel techniques such as task- and data-level parallelism to exploit available parallelism of those applications on the Cell multi-core processor. Experimental results have shown that our parallel implementations using 16 Synergistic Processor Elements significantly reduce the computational times of the GLCMs and texture features extraction algorithms by a factor of 10脳 over non-parallel optimized implementations for different image sizes from 128脳128 to 1024脳1024.