The authors describe a general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces. The method handles the full six degrees of freedom and is based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point. The ICP algorithm always converges monotonically to the nearest local minimum of a mean-square distance metric, and the rate of convergence is rapid during the first few iterations. Therefore, given an adequate set of initial rotations and translations for a particular class of objects with a certain level of 'shape complexity', one can globally minimize the mean-square distance metric over all six degrees of freedom by testing each initial registration. One important application of this method is to register sensed data from unfixtured rigid objects with an ideal geometric model, prior to shape inspection. Experimental results show the capabilities of the registration algorithm on point sets, curves, and surfaces. >

A method for registration of 3-D shapes

Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overview of pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.

/pdf/data-clustering-a-review-4c452f5cab.pdf

Data clustering: a review

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

We describe a technique for image encoding in which local operators of many scales but identical shape serve as the basis functions. The representation differs from established techniques in that the code elements are localized in spatial frequency as well as in space. Pixel-to-pixel correlations are first removed by subtracting a lowpass filtered copy of the image from the image itself. The result is a net data compression since the difference, or error, image has low variance and entropy, and the low-pass filtered image may represented at reduced sample density. Further data compression is achieved by quantizing the difference image. These steps are then repeated to compress the low-pass image. Iteration of the process at appropriately expanded scales generates a pyramid data structure. The encoding process is equivalent to sampling the image with Laplacian operators of many scales. Thus, the code tends to enhance salient image features. A further advantage of the present code is that it is well suited for many image analysis tasks as well as for image compression. Fast algorithms are described for coding and decoding.

/pdf/the-laplacian-pyramid-as-a-compact-image-code-3pr3qcg6c5.pdf

The Laplacian Pyramid as a Compact Image Code

A theory of edge detection is presented. The analysis proceeds in two parts. (1) Intensity changes, which occur in a natural image over a wide range of scales, are detected separately at different scales. An appropriate filter for this purpose at a given scale is found to be the second derivative of a Gaussian, and it is shown that, provided some simple conditions are satisfied, these primary filters need not be orientation-dependent. Thus, intensity changes at a given scale are best detected by finding the zero values of delta 2G(x,y)*I(x,y) for image I, where G(x,y) is a two-dimensional Gaussian distribution and delta 2 is the Laplacian. The intensity changes thus discovered in each of the channels are then represented by oriented primitives called zero-crossing segments, and evidence is given that this representation is complete. (2) Intensity changes in images arise from surface discontinuities or from reflectance or illumination boundaries, and these all have the property that they are spatially. Because of this, the zero-crossing segments from the different channels are not independent, and rules are deduced for combining them into a description of the image. This description is called the raw primal sketch. The theory explains several basic psychophysical findings, and the operation of forming oriented zero-crossing segments from the output of centre-surround delta 2G filters acting on the image forms the basis for a physiological model of simple cells (see Marr & Ullman 1979).

http://www.hms.harvard.edu/bss/neuro/bornlab/qmbc/beta/day4/marr-hildreth-edge-prsl1980.pdf

Theory of Edge Detection

: We have developed an integrated framework for the efficient synthesis of realistic images of three dimensional terrain with man-made objects and natural clutter. We have shown how many phenomenological aspects of the placement of road networks, tree clusters, populated areas, buildings, etc., can be captured in a computationally-efficient pseudorandom image-generation framework. We generate the underlying terrain with a fast Fourier based procedure. This procedure is seeded with a pseudorandom sequence, so a small number of parameters can characterize a distinctive class of terrain. Within each class, arbitrarily many scenes can be synthesized. We have used procedural definitions for objects; targets or clutter are represented by different models depending on range. For example, at a great distance trees may look like simple cones. But, as the viewpoint nears a tree, finer details will become visible. Procedural definitions also eliminate the need to explicitly store boundary representations for every object placed in the scene. A single procedural definition for an object, such as a tree, can be used at render time by a Z-buffer algorithm to create as many instances as are necessary, with each instance being unique since it uses a unique pseudorandom seed.... Automatic target recognition, Image synthesis, Computer modeling, Z-buffer.

Efficient Generation of Synthetic Terrain Imagery for Automatic Target Recognition

We propose a framework for the automatic one-shot segmentation of synthetic images generated by a StyleGAN. Our framework is based on the observation that the multi-scale hidden features in the GAN generator hold useful semantic information that can be utilized for automatic on-the-fly segmentation of the generated images. Using these features, our framework learns to segment synthetic images using a self-supervised contrastive clustering algorithm that projects the hidden features into a compact space for per-pixel classification. This novel contrastive learner is based on using a pixel-wise swapped prediction loss for image segmentation that leads to faster learning of the feature vectors for one-shot segmentation. We have tested our implementation on a number of standard benchmarks to yield a segmentation performance that not only outperforms the semi-supervised baseline methods by an average wIoU margin of 1.02% but also improves the inference speeds by a factor of 4.5. Finally, we also show the results of using the proposed one-shot learner in implementing BagGAN, a framework for producing annotated synthetic baggage X-ray scans for threat detection. This framework was trained and tested on the PIDRay baggage benchmark to yield a performance comparable to its baseline segmenter based on manual annotations.

Self-Supervised One-Shot Learning for Automatic Segmentation of StyleGAN Images

2. Signal Processing Fundamentals

This dissertation advances the state-of-the-art in information retrieval (IR) based approaches to automatic bug localization in software. In an IR-based approach, one first creates a search engine using a probabilistic or a deterministic model for the files in a software library. Subsequently, a bug report is treated as a query to the search engine for retrieving the files relevant to the bug. With regard to the new work presented, we first demonstrate the importance of taking version histories of the files into account for achieving significant improvements in the precision with which the files related to a bug are located. This is motivated by the realization that the files that have not changed in a long time are likely to have ``stabilized" and are therefore less likely to contain bugs. Subsequently, we look at the difficulties created by the fact that developers frequently use abbreviations and concatenations that are not likely to be familiar to someone trying to locate the files related to a bug. We show how an initial query can be automatically reformulated to include the relevant actual terms in the files by an analysis of the files retrieved in response to the original query for terms that are proximal to the original query terms. The last part of this dissertation generalizes our term-proximity based work by using Markov Random Fields (MRF) to model the inter-term dependencies in a query vis-a-vis the files. Our MRF work redresses one of the major defects of the most commonly used modeling approaches in IR, which is the loss of all inter-term relationships in the documents.

/pdf/source-code-retrieval-from-large-software-libraries-for-7y6gtb8zkq.pdf

Avinash C. Kak

Papers

Efficient Generation of Synthetic Terrain Imagery for Automatic Target Recognition

Self-Supervised One-Shot Learning for Automatic Segmentation of StyleGAN Images

2. Signal Processing Fundamentals

Source code retrieval from large software libraries for automatic bug localization

Correction to "The transient behavior of high-field dipole domains in transferred electron devices"