Timo Ojala

A comparative study of texture measures with classification based on featured distributions

This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently. For classification a method based on Kullback discrimination of sample and prototype distributions is used. The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented

Performance evaluation of texture measures with classification based on Kullback discrimination of distributions

This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches. For classification a method based on Kullback discrimination of sample and prototype distributions is used. The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented.

Outex - new framework for empirical evaluation of texture analysis algorithms

This paper presents the current status of a new initiative aimed at developing a versatile framework and image database for empirical evaluation of texture analysis algorithms. The proposed Outex framework contains a large collection of surface textures captured under different conditions, which facilitates construction of a wide range of texture analysis problems. The problems are encapsulated into test suites, for which baseline results obtained with algorithms from literature are provided. The rich functionality of the framework is demonstrated with examples in texture classification, segmentation and retrieval. The framework has a web site for public dissemination of the database and comparative results obtained by research groups world wide.

Unsupervised texture segmentation using feature distributions

Abstract This paper presents an unsupervised texture segmentation method, which uses distributions of local binary patterns and pattern contrasts for measuring the similarity of adjacent image regions during the segmentation process. Nonparametric log-likelihood test, the G statistic, is engaged as a pseudo-metric for comparing feature distributions. A region-based algorithm is developed for coarse image segmentation and a pixelwise classification scheme for improving localization of region boundaries. The performance of the method is evaluated with various types of test images.

Bluetooth and WAP push based location-aware mobile advertising system

Advertising on mobile devices has large potential due to the very personal and intimate nature of the devices and high targeting possibilities. We introduce a novel B-MAD system for delivering permission-based location-aware mobile advertisements to mobile phones using Bluetooth positioning and Wireless Application Protocol (WAP) Push. We present a thorough quantitative evaluation of the system in a laboratory environment and qualitative user evaluation in form of a field trial in the real environment of use. Experimental results show that the system provides a viable solution for realizing permission-based mobile advertising.

Rotation-invariant texture classification using feature distributions

Abstract A distribution-based classification approach and a set of recently developed texture measures are applied to rotation-invariant texture classification. The performance is compared to that obtained with the well-known circular-symmetric autoregressive random field (CSAR) model approach. A difficult classification problem of 15 different Brodatz textures and seven rotation angles is used in experiments. The results show much better performance for our approach than for the CSAR features. A detailed analysis of the confusion matrices and the rotation angles of misclassified samples produces several interesting observations about the classification problem and the features used in this study.

Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns

This paper presents a theoretically very simple yet efficient approach for gray scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The proposed approach is very robust in terms of gray scale variations, since the operators are by definition invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity, as the operators can be realized with a few operations in a small neighborhood and a lookup table. Excellent experimental results obtained in two true problems of rotation invariance, where the classifier is trained at one particular rotation angle and tested with samples from other rotation angles, demonstrate that good discrimination can be achieved with the statistics of simple rotation invariant local binary patterns. These operators characterize the spatial configuration of local image texture and the performance can be further improved by combining them with rotation invariant variance measures that characterize the contrast of local image texture. The joint distributions of these orthogonal measures are shown to be very powerful tools for rotation invariant texture analysis.

A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification

This paper presents generalizations to the gray scale and rotation invariant texture classification method based on local binary patterns that we have recently introduced. We derive a generalized presentation that allows for realizing a gray scale and rotation invariant LBP operator for any quantization of the angular space and for any spatial resolution, and present a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray scale variations, since the operator is by definition invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity, as the operator can be realized with a few operations in a small neighborhood and a lookup table. Excellent experimental results obtained in a true problem of rotation invariance, where the classifier is trained at one particular rotation angle and tested with samples from other rotation angles, demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns. These operators characterize the spatial configuration of local image texture and the performance can be further improved by combining them with rotation invariant variance measures that characterize the contrast of local image texture. The joint distributions of these orthogonal measures are shown to be very powerful tools for rotation invariant texture analysis.

Multipurpose Interactive Public Displays in the Wild: Three Years Later

Extended research on interactive public displays deployed in a city center reveals differences between the publics stated information needs and their actual information behavior and highlights effects that an artificial environment cannot duplicate.

UBI-Hotspot 1.0: Large-Scale Long-Term Deployment of Interactive Public Displays in a City Center

We present the design, implementation, deployment and evaluation of novel urban computing infrastructure called ‘UBI-hotspot’. It is effectively a large interactive public display embedded with other computing resources. We have deployed a network of UBI-hotspots around downtown Oulu, Finland, to establish a public laboratory for conducting experimental ubiquitous computing research in authentic urban setting with diverse real users and with sufficient scale and time span. We focus on the first version of the UBI-hotspot which offers a wide range of services via different interaction modalities. We analyze the usage and user acceptance of the UBI-hotspots from qualitative and quantitative data collected over a period of eight months. Our first observations show that this type of infrastructure may be a useful addition to the urban space.