FPGA based Streaming Image Processing Processor (SIPPro) architecture to accelerate data intensive applications

Current data-intensive image processing applications push traditional embedded architectures to their limits. FPGA based hardware acceleration is a potential solution but the programmability gap and time consuming HDL design flow is significant. The proposed research approach to develop “FPGA based programmable hardware acceleration platform” that uses, large number of Streaming Image processing Processors (SIPPro) potentially addresses these issues. SIPPro is pipelined in-order soft-core processor architecture with specific optimisations for image processing applications. Each SIPPro core uses 1 DSP48, 2 Block RAMs and 370 slice-registers, making the processor as compact as possible whilst maintaining flexibility and programmability. It is area efficient, scalable and high performance softcore architecture capable of delivering 530 MIPS per core using Xilinx Zynq SoC (ZC7Z020-3). To evaluate the feasibility of the proposed architecture, a Traffic Sign Recognition (TSR) algorithm has been prototyped on a Zedboard with the color and morphology operations accelerated using multiple SIPPros. Simulation and experimental results demonstrate that the processing platform is able to achieve a speedup of 15 and 33 times for color filtering and morphology operations respectively, with a significant reduced design effort and time.

FPGA-based soft-core processors for image processing applications

With security and surveillance, there is an increasing need to process image data efficiently and effectively either at source or in a large data network. Whilst a Field-Programmable Gate Array (FPGA) has been seen as a key technology for enabling this, the design process has been viewed as problematic in terms of the time and effort needed for implementation and verification. The work here proposes a different approach of using optimized FPGA-based soft-core processors which allows the user to exploit the task and data level parallelism to achieve the quality of dedicated FPGA implementations whilst reducing design time. The paper also reports some preliminary
progress on the design flow to program the structure. An implementation for a Histogram of Gradients algorithm is also reported which shows that a performance of 328 fps can be achieved with this design approach, whilst avoiding the long design time, verification and debugging steps associated with conventional FPGA implementations.

Towards An Acoustic Model-Based Poroelastic Imaging Method: I. Theoretical Foundation

The ultrasonic measurement and imaging of tissue elasticity is currently under wide investigation and development as a clinical tool for the assessment of a broad range of diseases, but little account in this field has yet been taken of the fact that soft tissue is porous and contains mobile fluid. The ability to squeeze fluid out of tissue may have implications for conventional elasticity imaging, and may present opportunities for new investigative tools. When a homogeneous, isotropic, fluid-saturated poroelastic material with a linearly elastic solid phase and incompressible solid and fluid constituents is subjected to stress, the behaviour of the induced internal strain field is influenced by three material constants: the Young's modulus (E(s)) and Poisson's ratio (nu(s)) of the solid matrix and the permeability (k) of the solid matrix to the pore fluid. New analytical expressions were derived and used to model the time-dependent behaviour of the strain field inside simulated homogeneous cylindrical samples of such a poroelastic material undergoing sustained unconfined compression. A model-based reconstruction technique was developed to produce images of parameters related to the poroelastic material constants (E(s), nu(s), k) from a comparison of the measured and predicted time-dependent spatially varying radial strain. Tests of the method using simulated noisy strain data showed that it is capable of producing three unique parametric images: an image of the Poisson's ratio of the solid matrix, an image of the axial strain (which was not time-dependent subsequent to the application of the compression) and an image representing the product of the aggregate modulus E(s)(1-nu(s))/(1+nu(s))(1-2nu(s)) of the solid matrix and the permeability of the solid matrix to the pore fluid. The analytical expressions were further used to numerically validate a finite element model and to clarify previous work on poroelastography.

An FPGA Based Coprocessor for GLCM and Haralick Texture Features and Their Application in Prostate Cancer Classification

Grey Level Co-occurrence Matrix (GLCM), one of the best known tool for texture analysis, estimates image properties related to second-order statistics. These image properties commonly known as Haralick texture features can be used for image classification, image segmentation, and remote sensing applications. However, their computations are highly intensive especially for very large images such as medical ones. Therefore, methods to accelerate their computations are highly desired. This paper proposes the use of programmable hardware to accelerate the calculation of GLCM and Haralick texture features. Further, as an example of the speedup offered by programmable logic, a multispectral computer vision system for automatic diagnosis of prostatic cancer has been implemented. The performance is then compared against a microprocessor based solution.

Thresholding of noisy shoeprint images based on pixel context

In a typical shoeprint classification and retrieval system, the first step is to segment meaningful basic shapes and patterns in a noisy shoeprint image. This step has significant influence on shape descriptors and shoeprint indexing in the later stages. In this paper, we extend a recently developed denoising technique proposed by Buades, called non-local mean filtering, to give a more general model. In this model, the expected result of an operation on a pixel can be estimated by performing the same operation on all of its reference pixels in the same image. A working pixel’s reference pixels are those pixels whose neighbourhoods are similar to the working pixel’s neighbourhood. Similarity is based on the correlation between the local neighbourhoods of the working pixel and the reference pixel. We incorporate a special instance of this general case into thresholding a very noisy shoeprint image. Visual and quantitative comparisons with two benchmarking techniques, by Otsu and Kittler, are conducted in the last section, giving evidence of the effectiveness of our method for thresholding noisy shoeprint images.

Fast model based feature matching technique applied to airport lighting

The use of image processing techniques to assess the performance of airport landing lighting using images of it collected from an aircraft-mounted camera is documented. In order to assess the performance of the lighting, it is necessary to uniquely identify each luminaire within an image and then track the luminaires through the entire sequence and store the relevant information for each luminaire, that is, the total number of pixels that each luminaire covers and the total grey level of these pixels. This pixel grey level can then be used for performance assessment. The authors propose a robust model-based (MB) featurematching technique by which the performance is assessed. The development of this matching technique is the key to the automated performance assessment of airport lighting. The MB matching technique utilises projective geometry in addition to accurate template of the 3D model of a landing-lighting system. The template is projected onto the image data and an optimum match found, using nonlinear least-squares optimisation. The MB matching software is compared with standard feature extraction and tracking techniques known within the community, these being the Kanade–Lucus–Tomasi (KLT) and scaleinvariant feature transform (SIFT) techniques. The new MB matching technique compares favourably with the SIFT and KLT feature-tracking alternatives. As such, it provides a solid foundation to achieve the central aim of this research which is to automatically assess the performance of airport lighting.

High-performance 3D median filter architecture for medical image despeckling

A high-sample rate 3D median filtering processor architecture is proposed, based on a novel 3D median filtering algorithm, that can reduce the computing complexity in comparison with the traditional bubble sorting algorithm. A 3 x 3 x 3 filter processor is implemented in VHDL, and the simulation verifies that the processor can process a 128 x 128 x 96 MRI image in 0.03 seconds while running at 50 MHz.

A novel shrinkage technique based on the normal inverse Gaussian density model

This paper proposes a novel image denoising technique based on the normal inverse Gaussian (NIG) density model using an extended non-negative sparse coding (NNSC) algorithm proposed by us. This algorithm can converge to feature basis vectors, which behave in the locality and orientation in spatial and frequency domain. Here, we demonstrate that the NIG density provides a very good fitness to the non-negative sparse data. In the denoising process, by exploiting a NIG-based maximum a posteriori estimator (MAP) of an image corrupted by additive Gaussian noise, the noise can be reduced successfully. This shrinkage technique, also referred to as the NNSC shrinkage technique, is self-adaptive to the statistical properties of image data. This denoising method is evaluated by values of the normalized signal to noise rate (SNR). Experimental results show that the NNSC shrinkage approach is indeed efficient and effective in denoising. Otherwise, we also compare the effectiveness of the NNSC shrinkage method with methods of standard sparse coding shrinkage, wavelet-based shrinkage and the Wiener filter. The simulation results show that our method outperforms the three kinds of denoising approaches mentioned above.

Robust face recognition using posterior union model based neural networks

Face recognition with unknown, partial distortion and occlusion is a practical problem, and has a wide range of applications, including security and multimedia information retrieval. The authors present a new approach to face recognition subject to unknown, partial distortion and occlusion. The new approach is based on a probabilistic decision-based neural network, enhanced by a statistical method called the posterior union model (PUM). PUM is an approach for ignoring severely mismatched local features and focusing the recognition mainly on the reliable local features. It thereby improves the robustness while assuming no prior information about the corruption. We call the new approach the posterior union decision-based neural network (PUDBNN). The new PUDBNN model has been evaluated on three face image databases (XM2VTS, AT&T and AR) using testing images subjected to various types of simulated and realistic partial distortion and occlusion. The new system has been compared to other approaches and has demonstrated improved performance.

Palmprint Recognition Based on Subspace Analysis of Gabor Filter Bank

This paper introduces a new technique for palmprint recognition based on Fisher Linear Discriminant Analysis (FLDA) and Gabor filter bank. This method involves convolving a palmprint image with a bank of Gabor filters at different scales and rotations for robust palmprint features extraction. Once these features are extracted, FLDA is applied for dimensionality reduction and class separability. Since the palmprint features are derived from the principal lines, wrinkles and texture along the palm area. One should carefully consider this fact when selecting the appropriate palm region for the feature extraction process in order to enhance recognition accuracy. To address this problem, an improved region of interest (ROI) extraction algorithm is introduced. This algorithm allows for an efficient extraction of the whole palm area by ignoring all the undesirable parts, such as the fingers and background. Experiments have shown that the proposed method yields attractive performances as evidenced by an Equal Error Rate (EER) of 0.03%.