Eric B. Hinkle

Radon and Projection Transform-Based Computer Vision

This book is a description of the applicability of projection transforms to computer vision and image processing. It deals with architecture implementations for real-time processing and, in particular, presents novel algorithms suitable for VLSI implementations. The architecture ideas unleash the power of the Radon transform for technological applications of the machine vision.

Image analysis methods for solder ball inspection in integrated circuit manufacturing

Machine vision methods are presented for the analysis of solder balls in integrated circuits. The algorithms are founded on counter fitting using a multiparameter Hough transform and on polynomial-classifier-based pattern recognition. The first method is used to show the complexity of the inspection problem, especially in the presence of high-precision requirements. In this connection, it is shown that subpixel accuracy is not obtainable even under the assumption of a perfect camera system which determines the resolution necessary for the measurement of a given maximum-volume distortion. The second method is carried out by computing a large number of features on the original image after individual solder balls are segmented by a projection technique. This approach can be considered as a control-free image segmentation paradigm, since it does not rely on properly sequencing several image-analysis modules. Further experimentation with a large pool of defective solder balls is necessary to confirm the applicability of these machine vision algorithms to a real-world manufacturing inspection systems. A general image-segmentation architecture is proposed, which enables the computation of the necessary low-level image features as well as pixel classification at video-rate speed. >

P 3 E: New life for projection—based image processing

Abstract This paper deals with a novel architecture that makes real-time projection-based image processing a reality. The design is founded on raster-mode processing, which is exploited in a powerful and flexible pipeline. This architecture, dubbed “P 3 E” (Parallel Pipeline Projection Engine), supports a large variety of image processing and image analysis applications. In the present paper, we concern ourselves with several image processing tasks, such as discrete approximations of the Radon and inverse Radon transform, among other projection operators; CT reconstructions; 2-D convolutions; rotations and translations; etc. However, there is also an extensive list of key image analysis algorithms that are supported by P 3 E, thus making it a profound and versatile tool for projection-based computer vision. Recently, several image analysis operators were mapped onto this architecture to solve some important automated inspection problems. We have yet to apply P 3 E to many other unexplored image processing and image analysis tasks. Examples of these are object recognition, motion parameter computations, approximation of the Fourier transform on polar rasters, etc.

Computing projections of digital images in image processing pipeline architectures

This paper deals with the problem of computing projections of digital images. The novelty of our contribution is that we present algorithms which are suitable for implementation in general purpose image processing and image analysis pipeline architectures. No random access of the image memory is necessary. We propose some new pipeline configurations which achieve a remarkable degree of parallelism in the computation of projection data and, in fact, of many other geometrical descriptors of digital images. Fast computation of projections of digital images is not only important for extracting geometrical information from images, it also makes possible performing a large number of operations on images in Radon space, thereby reducing two-dimensional problems to a series of one-dimensional problems.

A Rule-Based System for Verifying Engineering Specifications in Industrial Visual Inspection Applications

An important step in automatic visual inspection is verifying whether a part is good or bad, by comparing a list of inspection specifications to a list of extracted and measured defects. Our goal is to provide a general, flexible, and efficient solution to this problem. We present a solution following a rule-based approach for the case of specs for visual inspection of disk heads. However, due to the generality of our approach (within the realm of visual inspection), it is easily extendible to verification of specs in other visual inspection applications. While flexibility comes naturally with the rule-based approach, efficiency is still an issue. Therefore, we implemented two techniques to increase the efficiency of our system: one at the rule level, and one at the rule-matching level. We describe our implementation and show experimental results from applying our approach in an experimental system for automatic visual disk head inspection.

Fast image segmentation for some machine vision applications

This paper describes the use of an image contrast measure for producing binary segmentations of images in a certain class of applications. This method is well-suited for fast pipeline implementations, because the contrast measure uses only two local features in the image. To eliminate segmentation noise, we post-process the segmentations using binary morphological operations. This method has been applied to three different microelectronics inspection problems, with consistently good results, and experimental results from each of these applications are presented here. Also, we discuss this technique in terms of the theory of polynomial classifiers.

On the computation and use of projections of digital images in general purpose image processing pipeline architectures

This paper deals with the problem of computing, projections of digital images. The novelty of our contribution is that we present algorithms which are suitable for implementation in general purpose image processing and image analysis pipeline architectures. Also, we propose some new pipeline configurations which achieve a remarkable degree of parallelism in the computation of projection data and in fact, of many other geometrical descriptors of digital images. In particular, random access memories and other dedicated hardware devices are not needed in our algorithms. The effectiveness of our approach and feasibility of the proposed architectures are demonstrated by running our algorithms in commercially available short-pipelines for image processing and analysis. Examples are shown of the use of projection data for machine vision applications.

Projections Along General Contours

The powerful CIG in Fig. 3.1 can also be used to generate ramps which are not linear, along with other more sophisticated patterns. For example, the operation \(\sqrt {{c_1}{{(i - {i_1})}^2} + {c_2}{{(j - {j_1})}^2}} \) , where c1, c2, il, and jl are constants, is suitable for generating elliptical ramps, and is specifically useful for drawing circular multi-tone masks (see Sects. 5.4 and 5.5). Another example is the operation \(c\sqrt {ij} \) , where c is a constant, which yields hyperbolic ramps.2 In this case, it is necessary that the CIG be capable of taking integer products between the image coordinates.

Model and Computation of Digital Projections

The parallel projection of a function f(x,y)for a given angle θ is given by: