Jacek Czyz

A particle filter for joint detection and tracking of color objects

Color is a powerful feature for tracking deformable objects in image sequences with complex backgrounds. The color particle filter has proven to be an efficient, simple and robust tracking algorithm. In this paper, we present a hybrid valued sequential state estimation algorithm, and its particle filter-based implementation, that extends the standard color particle filter in two ways. First, target detection and deletion are embedded in the particle filter without relying on an external track initialization and cancellation algorithm. Second, the algorithm is able to track multiple objects sharing the same color description while keeping the attractive properties of the original color particle filter. The performance of the proposed filter are evaluated qualitatively on various real-world video sequences with appearing and disappearing targets.

Face verification competition on the XM2VTS database

In the year 2000 a competition was organised to collect face verification results on an identical, publicly available data set using a standard evaluation protocol. The database used was the Xm2vts database along with the Lausanne protocol [14]. Four different institutions submitted results on the database which were subsequently published in [13]. Three years later, a second contest using the same dataset and protocol was organised as part of AVBPA 2003. This time round seven seperate institutions submitted results to the competition. This paper presents the results of the competition and shows that verification results on this protocol have increased in performance by a factor of 3.

A robust soft hash algorithm for digital image signature

Watermarking is largely used for copyright protection and fast search of images in databases. Another method for securely identifying images is to use hash functions. Digital signature standard, used in cryptosystem to dispute authentication documents, is based on hash functions. A digital signature is a bit stream dependent on key and content of document. For each document, the digital signature algorithm provides a unique output bit stream. In order to be efficient in images, the digital signature should be different if and only if the image content, and not the input bit stream, is different. Our new method is a one-way function for images. Using the radon transform and principal component analysis, we extract characteristics robust against geometrical transformation (rotation and scaling) and image processing attacks (compression, filtering, blurring).

Decision fusion for face authentication

In this paper we study two aspects of decision fusion for enhancing face authentication. First, sequential fusion of scores obtained on successive video frames of a users face is used to reduce the error rate. Secondly, the opinions of several face authentication algorithms are combined so that the combined decision is more accurate than the best algorithm alone. The experiments performed on a realistic database demonstrate that the fully automatic multi-frame - multi-experts system proposed in this work allows a significant improvement over the static single-expert system.

Face Authentication Competition on the BANCA Database

This paper details the results of a face verification competition [2] held in conjunction with the First International Conference on Biometric Authentication. The contest was held on the publically available BANCA database [1] according to a defined protocol [6]. Six different verification algorithms from 4 academic and commercial institutions submitted results. Also, a standard set of face recognition software from the internet [3] was used to provide a baseline performance measure.

A color-based particle filter for joint detection and tracking of multiple objects

Recent works have shown that the particle filter using color as observation feature is a powerful technique for tracking deformable objects in image sequences with complex backgrounds. This paper presents a hybrid valued sequential state estimation algorithm, and its particle filter-based solution, that extends the standard color particle filter in two ways. Firstly, track initialization is embedded in the particle filter without relying on an external target detection algorithm. Secondly, the algorithm is able to track multiple objects sharing the same color description. We evaluate the performance of the proposed filter on various real-world video sequences with appearing and disappearing targets.

Multiple classifier combination for face-based identity verification

When combining outputs from multiple classifiers, many combination rules are available. Although easy to implement, fixed combination rules are optimal only in restrictive conditions. We discuss and evaluate their performance when the optimality conditions are not fulfilled. Fixed combination rules are then compared with trainable combination rules on real data in the context of face-based identity verification. The face images are classified by combining the outputs of five different face verification experts. It is demonstrated that a reduction in the error rates of up to 50% over the best single expert is achieved on the XM2VTS database, using either fixed or trainable combination rules

A modular multi-camera framework for team sports tracking

This article presents a modular architecture for multicamera tracking in the context of sports broadcasting. For each video stream, a geometrical module continuously performs the image-to-model homography estimation. A local-feature based tracking module tracks the players in each view. A supervisor module collects, associates and fuses the data provided by the tracking modules. The originality of the proposed system is three-fold. First, it allows to localize the targets on the ground with rotating and zooming cameras; second, it does not use background modeling techniques; and third, the local tracking can cope with severe occlusions. We present experimental results on raw TV-camera footage of a soccer game.

Combining face verification experts

We study the combination of face verification algorithms in order to improve the verification performance. Although the different face experts that we consider provide their output scores on the basis of the same image, they are complementary to each other and their combination, using a simple sum rule, outperforms the best individual expert. Our experiments were conducted on the standard XM2VTS face database.

Object Detection in Video via Particle Filters

We propose an object detection method using particle filters. Our approach estimates the probability of object presence in the current image given the history of observations up to current time. To do so, object presence is modelled by a two-state Markov chain, and the problem is translated into sequential Bayesian estimation which can be solved by particle filters. The observation density, required by the particle filter is based on selected discriminative Haar-like features that were introduced by Viola and Jones (2004) for object detection in static images. We illustrate the approach on the problem of face detection. Experiments on real video sequences show the feasbility of the approach