The proceedings contain 157 papers. The topics discussed include: known unknowns: novelty detection in condition monitoring;seeing the invisible and predicting the unexpected;vision-based SLAM in real-time;handwritten...
详细信息
ISBN:
(纸本)9783540728467
The proceedings contain 157 papers. The topics discussed include: known unknowns: novelty detection in condition monitoring;seeing the invisible and predicting the unexpected;vision-based SLAM in real-time;handwritten symbol recognition by a boosted blurred shape model with error correction;Bayesian hyperspectral image segmentation with discriminative class learning;comparison of unsupervised band selection methods for hyperspectral imaging;learning mixture models for gender classification based on facial surface normals;motion segmentation from feature trajectories with missing data;segmentation of rigid motion from non-rigid 2D trajectories;hierarchical eyelid and face tracking;automatic learning of conceptual knowledge in image sequences for human behavior interpretation;a comparative study of local descriptors for object category recognition:SIFT vs HMAX;and moment-based pattern representation using shape and grayscale features.
The proceedings contain 157 papers. The topics discussed include: known unknowns: novelty detection in condition monitoring;seeing the invisible and predicting the unexpected;vision-based SLAM in real-time;handwritten...
详细信息
ISBN:
(纸本)9783540728481
The proceedings contain 157 papers. The topics discussed include: known unknowns: novelty detection in condition monitoring;seeing the invisible and predicting the unexpected;vision-based SLAM in real-time;handwritten symbol recognition by a boosted blurred shape model with error correction;Bayesian hyperspectral image segmentation with discriminative class learning;comparison of unsupervised band selection methods for hyperspectral imaging;learning mixture models for gender classification based on facial surface normals;motion segmentation from feature trajectories with missing data;segmentation of rigid motion from non-rigid 2D trajectories;hierarchical eyelid and face tracking;automatic learning of conceptual knowledge in image sequences for human behavior interpretation;a comparative study of local descriptors for object category recognition:SIFT vs HMAX;and moment-based pattern representation using shape and grayscale features.
This paper describes an experimental study about a robust contour feature (shape-context) for using in action recognition based on continuous hidden Markov models (HMM). We ran different experimental setting using the...
详细信息
image preprocessing stage (also known as iris segmentation) is the first step of the iris recognition process and determines its accuracy. In this paper, we propose a method for iris segmentation. In order to get a ro...
详细信息
This paper presents a new approach to the problem of simultaneous location and segmentation of object in images. The main emphasis is done on the information provided by the contour fragments present in the image. Clu...
详细信息
This paper proposes a new method for simplifying a 2d shape boundary based on its phase congruence and the optimisation of a function criterion. The phase congruence is a dimensionless feature that stands out boundary...
详细信息
In the statistical patternrecognition field the number of samples to train a classifier is usually insufficient. Nevertheless, it has been shown that some learning domains can be divided in a set of related tasks, th...
详细信息
One area of patternrecognition that is receiving a lot of attention recently is handwritten text recognition. Traditionally, handwritten text recognition systems have been modelled by means of HMM models and n-gram l...
详细信息
This paper presents a methodology for the automated detection of impact craters on images of planetary surfaces. This modular approach includes a phase of candidate selection, followed by template matching and finally...
详细信息
ISBN:
(纸本)9783540728467
This paper presents a methodology for the automated detection of impact craters on images of planetary surfaces. This modular approach includes a phase of candidate selection, followed by template matching and finally the analysis of a probability volume that allows for the identification of craters on the image. It is applied to a set of images of the surface of the planet Mars, with results that are very promising, in face of future improvements in the methodology.
This paper presents a non parametric method for classifying interactions between two people as taken from a video camera. A nearest neighbour classifier that uses trajectory matching in feature space is introduced and...
详细信息
ISBN:
(纸本)9783540728481
This paper presents a non parametric method for classifying interactions between two people as taken from a video camera. A nearest neighbour classifier that uses trajectory matching in feature space is introduced and shown to be superior to regular nearest neighbour classification for this problem.
暂无评论