Search results for "Pattern Recognition"
showing 10 items of 2301 documents
Colour image segmentation and labeling through multiedit-condensing
1992
Abstract A new method is proposed for detecting and locating objects of interest within a colour scene under very strong variabilities in lighting conditions, object shape and pigmentation. The method is based on Nearest Neighbour classification and Multiedit-Condensing techniques and is applied to implement the vision subsystem of a robotic citric harvesting device. Experiments and results are reported showing the effectiveness of the method and illustrating its appropriateness to the proposed task.
Prototype selection for the nearest neighbour rule through proximity graphs
1997
Abstract In this paper, the Gabriel and Relative Neighbourhood graphs are used to select a suitable subset of prototypes for the Nearest Neighbour rule. Experiments and results are reported showing the effectiveness of the method and comparing its performance to those obtained by classical techniques.
"Indexing structures for approximate string matching
2003
In this paper we give the first, to our knowledge, structures and corresponding algorithms for approximate indexing, by considering the Hamming distance, having the following properties. i) Their size is linear times a polylog of the size of the text on average. ii) For each pattern x, the time spent by our algorithms for finding the list occ(x) of all occurrences of a pattern x in the text, up to a certain distance, is proportional on average to |x| + |occ(x)|, under an additional but realistic hypothesis.
Lesion of areas 17/18/19: effects on the cat's performance in a binary detection task
1988
The ability of two cats to discriminate between two geometrical outline patterns in the presence of superimposed Gaussian visual noise — i.e. in a binary detection task — was tested before and after bilateral removal of cortical areas 17, 18 and 19. The detection probability PD was measured as a function of the signal-to-noise ratio. After a lesion of areas 17, 18 and 19 both cats were unable to carry out the discrimination tasks. Their detection performance dropped to chance level, but after an extensive phase of retraining (3 months) they regained the ability to discriminate visual patterns. It was thus possible to obtain detection curves and to determine a measure of a performance which …
Using Redundant Visual Information From Different Dimensions for Attentional Selection
2012
The present study investigated the use of redundant information for attentional selection of a visual object. Each display contained two overlapping objects, and participants had to report the color of the occluding object. A baseline condition did not require object selection because the objects were identical. A single-cue condition required object selection based on spatial arrangement (i.e., occlusion) because the objects had the same shape. A double-cue condition afforded object selection by occlusion and shape because the objects consistently differed in shape. Behavioral results showed that the redundant shape cue facilitated attentional selection, although participants were never s…
Short article: Does the brain regularize digits and letters to the same extent?
2009
The cognitive system does not just act as a mirror from the sensory input; instead, it tends to normalize this information. Given that letter processing seems to be much more specialized than digit processing in the cortex, we examined whether the regularization process occurs differently from digits to letters than from letters to digits: We employed a masked priming same/different experiment (e.g., probe, VESZED; prime, V35Z3D; and target, VESZED). When embedded in letter strings, digits that resemble letters (e.g., 3 and 5 in V35Z3D-VESZED) tend to be encoded in a letter-like manner, whereas when embedded in digit strings, letters that resemble digits (e.g., E and S in 9ES7E2–935732) te…
The effect of texture on face identification and configural information processing
2014
Shape and texture are an integral part of face identity. In the present study, the importance of face texture for face identification and detection of configural manipulation (i.e., spatial relation among facial features) was examined by comparing grayscale face photographs (i.e., real faces) and line drawings of the same faces. Whereas real faces provide information about texture and shape of faces, line drawings are lacking texture cues. A change-detection task and a forced-choice identification task were used with both stimuli categories. Within the change detection task, participants had to decide whether the size of the eyes of two sequentially presented faces had changed or not. After…
V11. Functional hierarchy within an overall network for visual motion processing and ocular-motor control at rest
2015
Introduction Visual motion processing on one hand and ocular motor functions on the other are rarely studied together in vivo in humans. The interrelation of these functional networks is rather unclear, even though their functional dependence seems obvious. In several fMRI studies the essential nodes of both networks could be localized using voluntary optokinetic ('look') nystagmus (OKN) in the horizontal plane incorporating visual motion tracking (Dieterich et al., 2009). Here, functional connectivity (FC) between these nodes representing both networks was studies using resting-state FC. Methods Resting-state fMRI data of 200 healthy adults (age 44.1±17.9; 79 male) were included in the cro…
Incremental Generalized Discriminative Common Vectors for Image Classification.
2015
Subspace-based methods have become popular due to their ability to appropriately represent complex data in such a way that both dimensionality is reduced and discriminativeness is enhanced. Several recent works have concentrated on the discriminative common vector (DCV) method and other closely related algorithms also based on the concept of null space. In this paper, we present a generalized incremental formulation of the DCV methods, which allows the update of a given model by considering the addition of new examples even from unseen classes. Having efficient incremental formulations of well-behaved batch algorithms allows us to conveniently adapt previously trained classifiers without th…
Approximated overlap error for the evaluation of feature descriptors on 3D scenes
2013
This paper presents a new framework to evaluate feature descriptors on 3D datasets. The proposed method employs the approximated overlap error in order to conform with the reference planar evaluation case of the Oxford dataset based on the overlap error. The method takes into account not only the keypoint centre but also the feature shape and it does not require complex data setups, depth maps or an accurate camera calibration. Only a ground-truth fundamental matrix should be computed, so that the dataset can be freely extended by adding further images. The proposed approach is robust to false positives occurring in the evaluation process, which do not introduce any relevant changes in the …