We present a compiler that takes high level signal and image processing algorithms described in MATLAB and generates an optimized hardware for an FPGA with external memory. We propose a precision analysis algorithm to determine the minimum number of bits required by an integer variable and a combined precision and error analysis algorithm to infer the minimum number of bits required by a floating point variable. Our results show that on an average, our algorithms generate hardware requiring a factor of 5 less FPGA resources in terms of the Configurable Logic Blocks (CLBs) consumed as compared to the hardware generated without these optimizations. We show that our analysis results in the reduction in the size of lookup tables for functions like sin, cos, sqrt, exp etc. Our precision analysis also enables us to pack various array elements into a single memory location to reduce the number of external memory accesses. We show that such a technique improves the performance of the generated hardware by an average of 35%.

Abstract—We present a system to recognize underwater plankton images from the shadow image particle profiling evaluation recorder (SIPPER). The challenge of the SIPPER image set is that many images do not have clear contours. To address that, shape features that do not heavily depend on contour information were developed. A soft margin support vector machine (SVM) was used as the classifier. We developed a way to assign probability after multiclass SVM classification. Our approach achieved approximately 90 % accuracy on a collection of plankton images. On another larger image set containing manually unidentifiable particles, it also provided 75.6 % overall accuracy. The proposed approach was statistically significantly more accurate on the two data sets than a C4.5 decision tree and a cascade correlation neural network. The single SVM significantly outperformed ensembles of decision trees created by bagging and random forests on the smaller data set and was slightly better on the other data set. The 15-feature subset produced by our feature selection approach provided slightly better accuracy than using all 29 features. Our probability model gave us a reasonable rejection curve on the larger data set. Index Terms—Feature selection, learning, plankton recognition, probabilistic output, support vector machine (SVM). I.

Several libraries dedicated to mathematical morphology exist. But they lack genericity, that is to say, the ability for operators to accept input of di#erent natures ---2D binary images, graphs enclosing floating values, etc. We describe solutions which are integrated in Olena, a library providing morphological operators. We demonstrate with some examples that translating mathematical formulas and algorithms into source code is made easy and safe with Olena. Moreover, experimental results show that no extra costs at run-time are induced.

Chip fabrication technology continues to plunge deeper into submicron levels requiring hardware designers to utilize everincreasing amounts of logic and shorten design time. Toward that end, high-level languages such as C/C++ are becoming popular for hardware description and synthesis in order to more quickly leverage complex algorithms. Similarly, as logic density increases due to technology, power dissipation becomes a progressively more important metric of hardware design. PACT HDL, a C to HDL compiler, merges automated hardware synthesis of high-level algorithms with power and performance optimizations and targets arbitrary hardware architectures, particularly in a System on a Chip (SoC) setting that incorporates reprogrammable and application-specific hardware. PACT HDL is intended for applications well suited to custom hardware implementation such as image and signal processing codes. By making the compiler modular and flexible, optimizations may be executed in any order and at different levels in the compilation process. PACT HDL generates industry standard HDL codes, such as RTL Verilog and VHDL, which may be synthesized and profiled for power using commercial tools. This is the first paper on the PACT compiler project in a series. The compiler framework and introductory optimizations are presented. Later papers will focus on these and other optimizations in detail.

Abstract – This paper discusses a hybrid system for detecting masses in mammographic images. The proposed approach analyses the mammograms in three major steps. First a global segmentation method is applied to find the regions of interest. This step uses texture features, decision trees and a multiresolution Markov Random Field model. The second stage works on the output of the previous algorithm. Here a combination of three different local segmentation methods is used, and then some relevant features are extracted. Some of them refer to the shape of the object, others are simple texture parameters. Based on these features the final decision is made.

This thesis is available for Library use on the understanding that it is copyright material and that no quotation from this thesis may be published without proper acknowledgement. I certify that all material in this thesis which is not my own work has been identified and that no material has previously been submitted and approved for the award of this degree by this or any other university.

Abstract. A swap instruction, which exchanges a value in memory with a value of a register, is available on many architectures. The primary application of a swap instruction has been for process synchronization. As an experiment we wished to see how often a swap instruction can be used to coalesce loads and stores to improve the performance of a variety of applications. The results show that both the number of accesses to the memory system (data cache) and the number of executed instructions are reduced. 1 INTRODUCTION An instruction that exchanges a value in memory with a value in a register has been used on a variety of machines. The primary purpose for these swap instructions is to provide an atomic operation for reading from and writing to memory, which has been used to construct mutual-exclusion mechanisms in software for process synchronization. In fact, there are other forms of hardware instructions that have been used to support mutual exclusion, which include the classic test-and-set instruction. We thought it would be interesting to see if a swap instruction could be exploited in a more conventional manner. In this paper we show that a swap instruction can also be used by a low-level codeimproving transformation to coalesce loads and stores into a single instruction, which results in a reduction of memory references and executed instructions.

We present a system to recognize underwater plankton images from the Shadow Image Particle Profiling Evaluation Recorder. As some images do not have clear contours, we develop several features that do not heavily depend on the contour information. A soft margin support vector machine (SVM) was used as the classifier. We developed a new way to assign probability after multi-class SVM classification. Our approach achieved approximately 90% accuracy on a collection of images with minimal noise. On another image set containing manually unidentifiable particles, it also provides promising results. Also, our approach is more accurate on the two data sets than a C4.5 decision tree and a cascade correlation neural network at the 95% confidence level.

1.1 Optical Coherence Tomography In optical coherence tomography �OCT�, cross-sectional images are created by measuring near-infrared light backreflected from tissue. 1,2 Typical in vivo OCT systems have a

A computer system for the determination of the tension strength of a stay-rope has been elaborated. The tension strength in stayropes of towers needs to be calculated to approve its verticality and to verify the safety of its exploitation. Traditionally, this was done by means of time consuming methods such as an analog close-range photogrammetry or by means of the theodolite. I present a new approach to this task. The presented technology uses digital images and the computer in order to speed up the elaboration time. It uses the Kodak DCS 760 camera and a laptop as tools. As pictures are taken by a free-orientated, non-metric camera, an appropriate approach to camera orientation should be adopted. I suggest doing this by means of a projective planar transformation, which requires at least four control points. The shape of a freely dangling rope is determined by its tension strength. The catenary equation is used for modeling the shape of the rope. The line following algorithms have been developed for semiautomatic line measurement with sub-pixel accuracy (three points should be placed on the screen by the operator before algorithms can start). As a result, the positions of thousands of points are determined. It gives a more reliable shape of the rope and allows more reliable statistical estimation and evaluation of the results. Catenary parameters are calculated by means of the Least Square Method. As an example, the system was tested on a test field and the results were compared to traditional methods. The obtained results seem to be promising. A fully operable system is now ready to be used. Similar systems, based on line following algorithms but designed for different tasks, such as the determination of fabric chimney rectilinearity, may also be elaborated.