On the focusing of thermal images

In this paper we present a new thermographic image database, suitable for the analysis of automatic focusing measures. This database contains the images of 10 scenes, each of which is represented once for each of 96 different focus positions. Using this database, we evaluate the usefulness of five focus measures with the goal of determining the optimal focus position. Experimental results reveal that the accurate automatic detection of optimal focus position can be achieved with a low computational burden. We also present an acquisition tool for obtaining thermal images. To the best of our knowledge, this is the first study on the automatic focusing of thermal images.     

Dynamic learning from multiple examples for semantic object segmentation and search

We present a novel “dynamic learning” approach for an intelligent image database system to automatically improve object segmentation and labeling without user intervention, as new examples become available, for object-based indexing. The proposed approach is an extension of our earlier work on “learning by example,” which addressed labeling of similar objects in a set of database images based on a single example. The proposed dynamic learning procedure utilizes multiple example object templates to improve the accuracy of existing object segmentations and labels. Multiple example templates may be images of the same object from different viewing angles, or images of related objects. This paper also introduces a new shape similarity metric called normalized area of symmetric differences (NASD), which has desired properties for use in the proposed “dynamic learning” scheme, and is more robust against boundary noise that results from automatic image segmentation. Performance of the dynamic learning procedures has been demonstrated by experimental results.     

Image-Based Tree Variations

The automatic generation of realistic vegetation closely reproducing the appearance of specific plant species is still a challenging topic in computer graphics. In this paper, we present a new approach to generate new tree models from a small collection of frontal RGBA images of trees. The new models are represented either as single billboards (suitable for still image generation in areas such as architecture rendering) or as billboard clouds (providing parallax effects in interactive applications). Key ingredients of our method include the synthesis of new contours through convex combinations of exemplar countours, the automatic segmentation into crown/trunk classes and the transfer of RGBA colour from the exemplar images to the synthetic target. We also describe a fully automatic approach to convert a single tree image into a billboard cloud by extracting superpixels and distributing them inside a silhouette-defined 3D volume. Our algorithm allows for the automatic generation of an arbitrary number of tree variations from minimal input, and thus provides a fast solution to add vegetation variety in outdoor scenes.     

3D Face Recognition Using Simulated Annealing and the Surface Interpenetration Measure

This paper presents a novel automatic framework to perform 3D face recognition. The proposed method uses a Simulated Annealing-based approach (SA) for range image registration with the Surface Interpenetration Measure (SIM), as similarity measure, in order to match two face images. The authentication score is obtained by combining the SIM values corresponding to the matching of four different face regions: circular and elliptical areas around the nose, forehead, and the entire face region. Then, a modified SA approach is proposed taking advantage of invariant face regions to better handle facial expressions. Comprehensive experiments were performed on the FRGC v2 database, the largest available database of 3D face images composed of 4,007 images with different facial expressions. The experiments simulated both verification and identification systems and the results compared to those reported by state-of-the-art works. By using all of the images in the database, a verification rate of 96.5 percent was achieved at a False Acceptance Rate (FAR) of 0.1 percent. In the identification scenario, a rank-one accuracy of 98.4 percent was achieved. To the best of our knowledge, this is the highest rank-one score ever achieved for the FRGC v2 database when compared to results published in the literature.     

Meeting the challenge of fifty years of logic

In this article, we tell a story of good fortune. The good fortune concerns the discovery of a systematic approach to compress 50 years of excellent research in logic into a single day's use of an automated reasoning program. The discovery resulted from a colleague's experiment with a new representation and a new use of the weighting strategy. The experiment focused on an attempt—which I knew would fail—to prove one of the benchmark theorems that had eluded us for years. Fortunately, I was wrong; my colleague's attempt was successful, and a proof was found. The proof led to proving in one day 13 theorems, theorems that resulted from 50 years of excellent research in logic. We present these theorems as intriguing problems to test the power of a reasoning program or to evaluate the effectiveness of a new idea. In addition to the challenge problems, we discuss a possible approach to finding short proofs and the results achieved with it.This work was supported by the Applied Mathematical Sciences subprogram of the Office of Energy Research, U.S. Department of Energy, under Contract W-31-109-Eng-38.     

Automatic authentication of color laser print-outs using machine identification codes

Authentication of documents can be done by detecting the printing device used to generate the print-out. Many manufacturers of color laser printers and copiers designed their devices in a way to integrate a unique tracking pattern in each print-out. This pattern is used to identify the exact device the print-out originates from. In this paper, we present an important extension of our previous work for (a) detecting the class of printer that was used to generate a print-out, namely automatic methods for (b) comparing two base patterns from two different print-outs to verify if two print-outs come from the same printer and for (c) automatic decoding of the base pattern to extract the serial number and, if available, the time and the date the document was printed. Finally, we present (d) the first public dataset on tracking patterns (also called machine identification codes) containing 1,264 images from 132 different printers. Evaluation on this dataset resulted in accuracies of up to 93.0 % for detecting the printer class. Comparison and decoding of the tracking patterns achieved accuracies of 91.3 and 98.3 %, respectively.     

An approach to computer-supported cartooning

An approach to computer-supported cartooning is described that aims at optimizing the image-related working process by introducing computer-support in the drawing and painting stages of traditional cartoon production, in particular, allowing automatic coloring of a sequence of digitized images. This is achieved by using a shape-matching algorithm to evaluate the similarity of image regions and by performing an optimum region assignment to identify the corresponding ones and propagate the color information through the image sequence. In order to maintain the use of traditional drawing tools, the first step in the proposed system architecture is the processing of scanned animators' drawings to enhance their quality and extract meaningful information. Two different system modules allow either manual coloring of images or computer-assisted automatic painting of an image sequence. Additional modules allow the construction of a vector representation for the images, the generation of in-betweens, and the composing of each cartoon frame. The first stages of the system's architecture — image preprocessing, painting and vectorization — are presented. Special emphasis is placed on the fundamental ideas behind the computer-assisted painting and vectorization steps. The competitiveness of the approach, which requires no special hardware or high-performance workstation, is shown.     

Self organizing natural scene image retrieval

In this work we describe a new statistically-based methodology to organize and retrieve images of natural scenes by combining feature extraction, automatic clustering, automatic indexing and classification techniques. Our proposal belongs to the content-based image retrieval (CBIR) category. Our goal is to retrieve images from an image database by their content. The methodology combines randomly extracted points for feature extraction. The describing features are the mean, the standard deviation and the homogeneity (from the co-occurrence matrix) of a sub-image extracted from the three color channels (HSI). A K-means algorithm and a 1-NN classifier are used to build an indexed database. Three databases of images of natural scenes are used during the training and testing processes. One of the advantages of our proposal is that the images are not labeled manually for their retrieval. The performance of our framework is shown through several experimental results, including a comparison with several classifiers and comparison with related works, achieving up to 100% good recognition. Additionally, our proposal includes scene retrieval.     

Segmentation of the left ventricle in cardiac cine MRI using a shape-constrained snake model

Segmentation of the left ventricle (LV) is a hot topic in cardiac magnetic resonance (MR) images analysis. In this paper, we present an automatic LV myocardial boundary segmentation method using the parametric active contour model (or snake model). By convolving the gradient map of an image, a fast external force named gradient vector convolution (GVC) is presented for the snake model. A circle-based energy is incorporated into the GVC snake model to extract the endocardium. With this prior constraint, the snake contour can conquer the unexpected local minimum stemming from artifacts and papillary muscle, etc. After the endocardium is detected, the original edge map around and within the endocardium is directly set to zero. This modified edge map is used to generate a new GVC force filed, which automatically pushes the snake contour directly to the epicardium by employing the endocardium result as initialization. Meanwhile, a novel shape-similarity based energy is proposed to prevent the snake contour from being strapped in faulty edges and to preserve weak boundaries. Both qualitative and quantitative evaluations on our dataset and the publicly available database (e.g. MICCAI 2009) demonstrate the good performance of our algorithm.     

An Evaluation of Color-Spatial Retrieval Techniques for Large Image Databases

In a color-spatial retrieval technique, the color information is integrated with the knowledge of the colors' spatial distribution to facilitate content-based image retrieval. Several techniques have been proposed in the literature, but these works have been developed independently without much comparison. In this paper, we present an experimental evaluation of three color-spatial retrieval techniques—the signature-based technique, the partition-based algorithm and the cluster-based method. We implemented these techniques and compare them on their retrieval effectiveness and retrieval efficiency. The experimental study is performed on an image database consisting of 12,000 images. With the proliferation of image retrieval mechanisms and the lack of extensive performance study, the experimental results can serve as guidelines in selecting a suitable technique and designing a new technique.     

Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction

We present a method—termed Helmholtz stereopsis—for reconstructing the geometry of objects from a collection of images. Unlike existing methods for surface reconstruction (e.g., stereo vision, structure from motion, photometric stereopsis), Helmholtz stereopsis makes no assumptions about the nature of the bidirectional reflectance distribution functions (BRDFs) of objects. This new method of multinocular stereopsis exploits Helmholtz reciprocity by choosing pairs of light source and camera positions that guarantee that the ratio of the emitted radiance to the incident irradiance is the same for corresponding points in the two images. The method provides direct estimates of both depth and surface normals, and consequently weds the advantages of both conventional stereopsis and photometric stereopsis. Results from our implementation lend empirical support to our technique.     

Building a user-centered semantic hierarchy in image databases

Recent development in the field of digital media technology has resulted in the generation of a huge number of images. Consequently, content-based image retrieval has emerged as an important area in multimedia computing. Research in human perception of image content suggests that the semantic cues play an important role in image retrieval. In this paper, we present a new paradigm to establish the semantics in image databases based on multi-user relevance feedback. Relevance feedback mechanism is one way to incorporate the users’ perception during image retrieval. By treating each feedback as a weak classifier and combining them together, we are able to capture the categories in the users’ mind and build a user-centered semantic hierarchy in the database to support semantic browsing and searching. We present an image retrieval system based on a city-landscape image database comprising of 3,009 images. We also compare our approach with other typical methods to organize an image database. Superior results have been achieved by the proposed framework.     

Frankenrigs: building character rigs from multiple sources

We present a new rigging and skinning method which uses a database of partial rigs extracted from a set of source characters. Given a target mesh and a set of joint locations, our system can automatically scan through the database to find the best-fitting body parts, tailor them to match the target mesh, and transfer their skinning information onto the new character. For the cases where our automatic procedure fails, we provide an intuitive set of tools to fix the problems. When used fully automatically, the system can generate results of much higher quality than a standard smooth bind, and with some user interaction, it can create rigs approaching the quality of artist-created manual rigs in a small fraction of the time.     

A Self-Tuning Evolutionary Algorithm Applied to an Inverse Partial Differential Equation

Evolutionary algorithms (EAs) are becoming increasingly popular tools for solving complex search problems. Their popularity in various problem domains has led to the introduction and development of numerous variants of two standard EA operators—crossover and mutation. Unfortunately, there are few if any effective guidelines for choosing which operators will be most effective in a given problem. In this paper, a self-tuning EA is introduced that employs several crossover and mutation operators simultaneously. The probability of using a given operator changes during the course of an evolutionary run whereby the most effective operators are selected based on which part of the search space is currently being explored. The self-tuning EA is used to solve an inverse partial differential equation—considered to be one of the more difficult problems in the realm of engineering mathematics. Results indicate that for the particular inverse partial differential equation considered, the self-tuning EA provides an effective solution methodology.     

Learned Fitting of Spatially Varying BRDFs

The use of spatially varying reflectance models (SVBRDF) is the state of the art in physically based rendering and the ultimate goal is to acquire them from real world samples. Recently several promising deep learning approaches have emerged that create such models from a few uncalibrated photos, after being trained on synthetic SVBRDF datasets. While the achieved results are already very impressive, the reconstruction accuracy that is achieved by these approaches is still far from that of specialized devices. On the other hand, fitting SVBRDF parameter maps to the gibabytes of calibrated HDR images per material acquired by state of the art high quality material scanners takes on the order of several hours for realistic spatial resolutions. In this paper, we present a first deep learning approach that is capable of producing SVBRDF parameter maps more than two orders of magnitude faster than state of the art approaches, while still providing results of equal quality and generalizing to new materials unseen during the training. This is made possible by training our network on a large‐scale database of material scans that we have gathered with a commercially available SVBRDF scanner. In particular, we train a convolutional neural network to map calibrated input images to the 13 parameter maps of an anisotropic Ward BRDF, modified to account for Fresnel reflections, and evaluate the results by comparing the measured images against re‐renderings from our SVBRDF predictions. The novel approach is extensively validated on real world data taken from our material database, which we make publicly available under https://cg.cs.uni‐bonn.de/svbrdfs/ .     

A Statistical Approach to Texture Classification from Single Images

We investigate texture classification from single images obtained under unknown viewpoint and illumination. A statistical approach is developed where textures are modelled by the joint probability distribution of filter responses. This distribution is represented by the frequency histogram of filter response cluster centres (textons). Recognition proceeds from single, uncalibrated images and the novelty here is that rotationally invariant filters are used and the filter response space is low dimensional.Classification performance is compared with the filter banks and methods of Leung and Malik [IJCV, 2001], Schmid [CVPR, 2001] and Cula and Dana [IJCV, 2004] and it is demonstrated that superior performance is achieved here. Classification results are presented for all 61 materials in the Columbia-Utrecht texture database.We also discuss the effects of various parameters on our classification algorithm—such as the choice of filter bank and rotational invariance, the size of the texton dictionary as well as the number of training images used. Finally, we present a method of reliably measuring relative orientation co-occurrence statistics in a rotationally invariant manner, and discuss whether incorporating such information can enhance the classifiers performance.     

An integrated automatic test data generation system

The Godzilla automatic test data generator is an integrated collection of tools that implements a relatively new test data generation method—constraint-based testing—that is based on mutation analysis. Constraint-based testing integrates mutation analysis with several other testing techniques, including statement coverage, branch coverage, domain perturbation, and symbolic evaluation. Because Godzilla uses a rule-based approach to generate test data, it is easily extendible to allow new testing techniques to be integrated into the current system. This article describes the system that has been built to implement constraint-based testing. Godzilla's design emphasizes orthogonality and modularity, allowing relatively easy extensions. Godzilla's internal structure and algorithms are described with emphasis on internal structures of the system and the engineering problems that were solved during the implementation.Parts of this research were supported by Contract F30602-85-C-0255 through Rome Air Development Center while the author was a graduate student at the Georgia Institute of Technology.     

Automated building extraction from IKONOS images in suburban areas

The article addresses automatic building extraction from IKONOS images in suburban areas. In the proposed approach, we used a stereo pair of IKONOS images. Automatic photogrammetric methods of image matching were used to generate a digital surface model (DSM) and a digital elevation model. In further processing, single-image methods were used. The orthophotos of individual bands were created. The initial building mask was generated from the calculated normalized DSM (nDSM). The calculated normalized difference vegetation index and the road data extracted from the existing topographical database were used to remove vegetation and traffic surfaces. The mask was further improved with our own combination of methods based on non-linear diffusion filtering, unsupervised classification, colour segmentation and region growing. The final mask was vectorized using the Hough transform. Compared with a reference building database, 83.2% of the buildings in the test area were detected using the proposed approach with a quality percentage (how likely a building pixel produced by an automatic approach is correct) of 49.46.