Heikki Kälviäinen

Invariance properties of Gabor filter-based features-overview and applications

For almost three decades the use of features based on Gabor filters has been promoted for their useful properties in image processing. The most important properties are related to invariance to illumination, rotation, scale, and translation. These properties are based on the fact that they are all parameters of Gabor filters themselves. This is especially useful in feature extraction, where Gabor filters have succeeded in many applications, from texture analysis to iris and face recognition. This study provides an overview of Gabor filters in image processing, a short literature survey of the most significant results, and establishes invariance properties and restrictions to the use of Gabor filters in feature extraction. Results are demonstrated by application examples.

Simple Gabor feature space for invariant object recognition

Invariant object recognition is one of the most challenging problems in computer vision. The authors propose a simple Gabor feature space, which has been successfully applied to applications, e.g., in invariant face detection to extract facial features in demanding environments. In the proposed feature space, illumination, rotation, scale, and translation invariant recognition of objects can be realized within a reasonable amount of computation. In this study, fundamental properties of Gabor features, construction of the simple feature space, and invariant search operations in the feature space are discussed in more detail.

Probabilistic and Non-Probabilistic Hough Transforms: Overview and Comparisons

Abstract A new and efficient version of the Hough transform for curve detection, the Randomized Hough Transform (RHT), has been recently suggested. The RHT selects n pixels from an edge image by random sampling to solve n parameters of a curve and then accumulates only one cell in a parameter space. In this paper, the RHT is related to other recent developments of the Hough transform. Hough transform methods are divided into two categories: probabilistic and non-probabilistic methods. An overview of these variants is given. Some novel extensions of the RHT are proposed to improve the RHT for complex and noisy images. These new versions of the RHT, called the Dynamic RHT, and the Window RHT with its variants, use local information of the edge image. They apply the RHT process to a limited neighbourhood of edge pixels. Tests in line detection with synthetic and real-world images demonstrate the high speed and low memory usage of the new extensions, as compared both to the basic RHT and other versions of the Hough transform.

The DIARETDB1 diabetic retinopathy database and evaluation protocol

Automatic diagnosis of diabetic retinopathy from digital fundus images has been an active research topic in the medical image processing community. The research interest is justified by the excellent potential for new products in the medical industry and significant reductions in health care costs. However, the maturity of proposed algorithms cannot be judged due to the lack of commonly accepted and representative image database with a verified ground truth and strict evaluation protocol. In this study, an evaluation methodology is proposed and an image database with ground truth is described. The database is publicly available for benchmarking diagnosis algorithms. With the proposed database and protocol, it is possible to compare different algorithms, and correspondingly, analyse their maturity for technology transfer from the research laboratories to the medical practice.

Feature-based affine-invariant localization of faces

We present a novel method for localizing faces in person identification scenarios. Such scenarios involve high resolution images of frontal faces. The proposed algorithm does not require color, copes well in cluttered backgrounds, and accurately localizes faces including eye centers. An extensive analysis and a performance evaluation on the XM2VTS database and on the realistic BioID and BANCA face databases is presented. We show that the algorithm has precision superior to reference methods.

Feature representation and discrimination based on Gaussian mixture model probability densities-Practices and algorithms

Highly active hydrofining catalysts are prepared by ion exchanging a silica-alumina hydrogel with an ammoniacal solution of a cobalt and/or nickel compound, and thereafter compositing the undried product with an alumina hydrogel and a molybdenum component, followed by drying and calcining. The resulting catalysts are particularly active for the denitrogenation of mineral oil feedstocks.

Diagnosis tool for motor condition monitoring

In the modern industrial environment there is increasing demand for automatic condition monitoring. With reliable condition monitoring, faults such as mechanical motor failures could be identified in their early stages and further damage to the system could be prevented. Successful monitoring is a complex and application-specific problem, but a generic tool would be useful in preliminary analysis of new signals and in verification of known theories. A generic condition diagnosis tool is introduced in this paper. The tool is based on discriminative energy functions which reveal discriminative frequency-domain regions where failures can be identified. The tool was applied to induction motor bearing fault detection and succeeded in finding characteristic frequencies which allow accurate detection of bearing faults.

Randomized or probabilistic Hough transform: unified performance evaluation

Abstract Rapid computation of the Hough transform is necessary in very many computer vision applications. One of the major approaches for fast Hough transform computation is based on the use of a small random sample of the data set rather than the full set. Two different algorithms within this family are the randomized Hough transform (RHT) and the probabilistic Hough transform (PHT). There have been contradictory views on the relative merits and drawbacks of the RHT and the PHT. In this paper, a unified theoretical framework for analyzing the RHT and the PHT is established. The performance of the two algorithms is characterized both theoretically and experimentally. Clear guidelines for selecting the algorithm that is most suitable for a given application are provided. We show that, when considering the basic algorithms, the RHT is better suited for the analysis of high quality low noise edge images, while for the analysis of noisy low quality images the PHT should be selected.

Compression of multispectral remote sensing images using clustering and spectral reduction

Image compression has been one of the main research topics in the field of image processing for a long time. The research usually focuses on compressing images that are visible to humans. The images being compressed are usually gray-level images or RGB color images. Recent advances in technology, however, enable the authors to make the detailed processing of spectral features in the images. Therefore, the compression of images with many spectral channels, called multispectral images, is required. Many methods used in traditional lossy image compression can be reused also in the compression of multispectral images. In this paper, a new combination of clustering spectra, manipulating spectral vectors, and encoding and decoding for multispectral images is presented. In the manipulation of the spectral vectors PCA, ICA, and wavelets are used. The approach is based on extracting relevant spectral information. Furthermore, some quantitative quality measures for multispectral images are presented.

Color features for quality control in ceramic tile industry

We study visual quality control in the ceramics industry. In tile manufacturing, it is important that in each set of tiles, every single tile looks similar. Currently, the estimation is usually done by human vision. Our goal is to design a machine vision system that can estimate the sufficient similarity, or same appearance, to the human eye. Our main approach is to use accurate spectral representation of color, and com- pare spectral features to the RGB color features. A laboratory system for color measurements is built. Experimentations with five classes of brown tiles are presented and discussed. In addition to the k-nearest neighbor (k-NN) classifier, a neural network called the self-organizing map (SOM) is used to provide understanding of the spectral features. Every single spectrum in each tile of a training set is used as input to a 2-D SOM. The SOM is analyzed to understand how spectra are clustered. As a result, tiles are classified using a trained 2-D SOM. It is also of interest to know whether the order of spectral colors can be determined. In our approach, all spectra are clustered in a 1-D SOM, and each pixel (spectrum) is presented by pseudocolors according to the trained nodes. Finally, the results are compared to experiments with human vision.