Publications of Henri Bouma

The selected research categories, references to publications, abstracts and full-text articles summarize the research activities of Henri Bouma.


  • Featured publications
  • Publications by year

Featured publications

Re-identificationFast and accurate person re-identification...2018
Behaviour recognitionFlexible human-definable automatic behavior analysis... 2018
Behaviour recognitionLong-term behavior understanding... 2016
Deep learningInteractive detection of incrementally learned concepts...2015
Deep learningIncremental concept learning with few training examples...2015
ThreatAutomatic detection of suspicious behavior of pickpockets...2014
ThreatInstantaneous threat detection...2014
Endoscopic 3DImproved depth perception with three-dimensional auxiliary display...2014
Tracking and
Real-time tracking and fast retrieval of persons...2013

Publications by year


Automatic Detection of Pulmonary Embolism in CTA Images

Pulmonary embolism (PE) is a common lifethreatening disorder for which an early diagnosis is desirable. We propose a new system for the automatic detection of PE in contrast-enhanced CT images. The system consists of candidate detection, feature computation and classification. Candidate detection focusses on the inclusion of PE - even complete occlusions - and the exclusion of false detections, such as tissue and parenchymal diseases. Feature computation does not only focus on the intensity, shape and size of an embolus, but also on locations and the shape of the pulmonary vascular tree. Several classifiers have been tested and the results show that the performance is optimized by using a bagged tree classifier with two features based on the shape of a blood vessel and the distance to the vessel boundary. The system was trained on 38 CT data sets. Evaluation on 19 other data sets showed that the system generalizes well. The sensitivity of our system on the evaluation data is 63% at 4.9 false positives per data set, which allowed the radiologist to improve the number of detected PE by 22%.

Unbiased vessel-diameter quantification based on the FWHM criterion

The full-width at half-max (FWHM) criterion is often used for both manual and automatic quantification of the vessel diameter in medical images. The FWHM criterion is easy to understand and it can be implemented with low computational cost. However, it is well known that the FWHM criterion can give an over- and underestimation of the vessel diameter. In this paper, we propose a simple and original method to create an unbiased estimation of the vessel diameter based on the FWHM criterion and we compared the robustness to noise of several edge detectors. The quantitative results of our experiments show that the proposed method is more accurate and precise than other (more complex) edge detectors, even for small vessels.

Fast and Accurate Gaussian Derivatives based on B-Splines

Gaussian derivatives are often used as differential operators to analyze the structure in images. In this paper, we will analyze the accuracy and computational cost of the most common implementations for differentiation and interpolation of Gaussian-blurred multi-dimensional data. We show that - for the computation of multiple Gaussian derivatives - the method based on B-splines obtains a higher accuracy than the truncated Gaussian at equal computational cost.

Correction for the Dislocation of Curved Surfaces caused by the PSF in 2D and 3D CT Images

Conventional edge-detection methods suffer from the dislocation of curved surfaces due to the PSF. We propose a new method that uses the isophote curvature to circumvent this. It is accurate for objects with locally constant curvature, even for small objects (like blood vessels) and in the presence of noise.

A reconfigurable function array architecture for 3G and 4G wireless terminals

Advace in low-power hand-held multimedia systems requires exploration of novel system architectures. In conventional computer architectures, an increase in processing power also implies an increase in energy consumption. In a mobile system this results in a shorter operating-time. Limiting the generality of an architecture can improve its energy efficiency. However, application specific architectures have a number of drawbacks and are too restricted. Therefore, an application domain specific architecture is proposed. As part of an application domain specific architecture for the digital signal-processing domain, the Field Programmable Function Array (FPFA) was conceived. The FPFA is a reconfigurable device with a datapath that can be configured to implement a number of DSP algorithms energy efficiently. The flexibility in the FPFA results in a data-path that requires many control signals. To reduce the vast amount of control signals, the FPFA control-path uses a combination of configuration registers and vertical microprogramming.

Copyright (c) 2007/2008/2009 SPIE. The papers were published in Proc. SPIE, vols. 6512, 7114 and is made available as an electronic reprint with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.

Copyright (c) 2007 Springer-Verlag. The author may publish his/her contribution on his/her personal web page provided that he/she creates a link to the LNCS homepage and that it is clearly pointed out that the copyright for this contribution is held by Springer.

Copyright (c) 2005/2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Copyrights (c) 2002 Delson Group Inc.