Kalle Karu

A real-time matching system for large fingerprint databases

With the current rapid growth in multimedia technology, there is an imminent need for efficient techniques to search and query large image databases. Because of their unique and peculiar needs, image databases cannot be treated in a similar fashion to other types of digital libraries. The contextual dependencies present in images, and the complex nature of two-dimensional image data make the representation issues more difficult for image databases. An invariant representation of an image is still an open research issue. For these reasons, it is difficult to find a universal content-based retrieval technique. Current approaches based on shape, texture, and color for indexing image databases have met with limited success. Further, these techniques have not been adequately tested in the presence of noise and distortions. A given application domain offers stronger constraints for improving the retrieval performance. Fingerprint databases are characterized by their large size as well as noisy and distorted query images. Distortions are very common in fingerprint images due to elasticity of the skin. In this paper, a method of indexing large fingerprint image databases is presented. The approach integrates a number of domain-specific high-level features such as pattern class and ridge density at higher levels of the search. At the lowest level, it incorporates elastic structural feature-based matching for indexing the database. With a multilevel indexing approach, we have been able to reduce the search space. The search engine has also been implemented on Splash 2-a field programmable gate array (FPGA)-based array processor to obtain near-ASIC level speed of matching. Our approach has been tested on a locally collected test data and on NIST-9, a large fingerprint database available in the public domain.

Locating text in complex color images

Abstract There is a substantial interest in retrieving images from a large database using the textual information contained in the images. An algorithm which will automatically locate the textual regions in the input image will facilitate this task; the optical character recognizer can then be applied to only those regions of the image which contain text. We present two methods for automatically locating text in complex color images. The first method segments the image into connected components with uniform color, and uses several heuristics (size, alignment, proximity) to select the components which are likely to contain character(s) belonging to the text. The second method computes the local spatial variation in the gray-scale image, and locates text in regions with high variance. A combination of the two approaches is shown to be more effective than the individual methods. The proposed methods have been used to locate text in compact disc (CD) and book cover images, as well as in the images of traffic scenes captured by a video camera. Initial results are encouraging and suggest that these algorithms can be used in image retrieval applications.

Learning texture discrimination masks

A neural network texture classification method is proposed in this paper. The approach is introduced as a generalization of the multichannel filtering method. Instead of using a general filter bank, a neural network is trained to find a minimal set of specific filters, so that both the feature extraction and classification tasks are performed by the same unified network. The authors compute the error rates for different network parameters, and show the convergence speed of training and node pruning algorithms. The proposed method is demonstrated in several texture classification experiments. It is successfully applied in the tasks of locating barcodes in the images and segmenting a printed page into text, graphics, and background. Compared with the traditional multichannel filtering method, the neural network approach allows one to perform the same texture classification or segmentation task more efficiently. Extensions of the method, as well as its limitations, are discussed in the paper.

Is there any texture in the image

Abstract Texture analysis methods have been used in various image processing tasks, such as image segmentation, recognition, shape analysis, texture synthesis and image compression. When applying any of these methods, we assume that the input image has some textural characteristics. This paper addresses the problem of deciding whether an image has texture; in other words, whether texture-based methods are suitable for processing the image. We define a texture to have a spatially uniform distribution of local gray-value variations. A fast algorithm for detecting regions that have texture according to this definition is presented. The performance of the method is demonstrated on several synthetic and natural images.

The cd -index of fans and posets

The number of flags in a complete fan, or more generally in an Eulerian poset, is encoded in the cd-index. We prove the non-negativity of the cd-index for complete fans, regular CW -spheres and Gorenstein* posets.

Some non-finitely generated Cox rings

We give a large family of weighted projective planes, blown up at a smooth point, that do not have finitely generated Cox rings. We then use the method of Castravet and Tevelev to prove that the moduli space of stable n-pointed genus zero curves does not have a finitely generated Cox ring if n is at least 13.

Toric residue mirror conjecture for Calabi-Yau complete intersections

We generalize the toric residue mirror conjecture of Batyrev and Materov to not necessarily reflexive polytopes. Using this generalization we prove the toric residue mirror conjecture for Calabi-Yau complete intersections in Gorenstein toric Fano varieties.

Texture Analysis: Representation and Matching

Texture has found many applications in computer vision. Examples where texture analysis methods are being used include: (i) classifying images and browsing images based on their texture; (ii) segmenting an input image into regions of homogeneous texture; (iii) extracting surface shape information from ‘texture gradient’; and (iv) synthesizing textures that resemble natural images for various computer graphics applications. Image texture is characterized by the gray value or color ‘pattern’ in a neighborhood surrounding the pixel. Different methods of texture analysis capture this gray-level pattern by extracting textural features in a localized input region. Practical texture-based image processing methods define texture in a manner that is most appropriate for achieving a given goal and ignore the issue whether the input image really contains any texture. This paper describes attempts to learn ‘optimal’ texture discrimination masks using neural networks.

Automatic filter design for texture discrimination

Multichannel filtering has been shown by many researchers to provide good features for texture segmentation and classification. In this paper the authors exploit neural networks to construct optimal filters and to combine the outputs of these filters for the classification of known textures. The authors use the neural network training together with node pruning, so that both the classification error and the number of filters or, equivalently, the number of features, are minimized. The performance of the neural network classifier is demonstrated an several experiments involving classification of natural textures. The authors study the effects of using different sized filters with different network configurations. The authors show that the number of filters, and, therefore, the processing time, can be greatly reduced while preserving the classification accuracy, using the proposed scheme compared to using a general set of filters (e.g., Gabor filters).

Bivariant algebraic cobordism

We associate a bivariant theory to any suitable oriented Borel-Moore homology theory on the category of algebraic schemes or the category of algebraic G-schemes. Applying this to the theory of algebraic cobordism yields operational cobordism rings and operational G-equivariant cobordism rings associated to all schemes in these categories. In the case of toric varieties, the operational T-equivariant cobordism ring may be described as the ring of piecewise graded power series on the fan with coefficients in the Lazard ring.