The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Gender recognition from face images is an important application in the fields of security, retail advertising and marketing. We propose a novel descriptor based on COSFIRE filters for gender recognition. A COSFIRE filter is trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest. We demonstrate the effectiveness of...
Classifiers have known to be used in various fields of applications. However, the main problem usually found recently is about applying a classifier to large datasets. Thus, the process of reducing size of the training set becomes necessary especially to accelerate the processing time of the classifier. Concerning the problem, this paper proposes a new method which can reduce size of the training...
This paper presents a fast approach to represent and recognize human actions. For representation, a feature vector is constructed from spatiotemporal data of silhouettes based on appearance and motion. For classification, a new Radial Basis Function Network (RBF), called Time Delay Input Radial Basis Function Network is proposed by introducing time delay units to the RBF in a novel approach. The proposed...
We present a real-world robotic agent that is capable of transferring grasping strategies across objects that share similar parts. The agent transfers grasps across objects by identifying, from examples provided by a teacher, parts by which objects are often grasped in a similar fashion. It then uses these parts to identify grasping points onto novel objects. We focus our report on the definition...
When humans perceive incomplete or ambiguous informations, they tend to instantaneously resolve them by creating meaningful completions. In psychological terms, this generative aspect of perception is called reification. In this paper, we present an approach to model reification by means of perceptual grouping. This technique plays an important role in human-robot interaction scenarios, because it...
This work aims to identify abnormal behaviors from the analysis of humans or vehicles' trajectories. A set of normal trajectories' prototypes is extracted by means of a novel unsupervised learning technique: the scene is adaptively partitioned into zones by using the distribution of the training set and each trajectory is represented as a sequence of symbols by taking into account positional information...
Automatic sketch recognition is used to enhance human-computer interaction by allowing a natural/free form of interaction. It is a challenging problem due to the variability in hand drawings, the variation in the order of strokes, and the similarity of symbol classes. Since sketch recognition requires real time processing, the speed of the classifier is important. Another important issue is how to...
This paper proposes a novel graph-based method for representing a human's shape during the performance of an action. Despite their strong representational power, graphs are computationally cumbersome for pattern analysis. One way of circumventing this problem is that of transforming the graphs into a vector space by means of graph embedding. Such an embedding can be conveniently obtained by way of...
One-class classification is an important problem with applications in several different areas such as outlier detection and machine monitoring. In this paper we propose a novel method for one-class classification which also implements prototype reduction. The main feature of the proposed method is to analyze every limit of all the feature dimensions to find the true border which describes the normal...
Shape and motion are two most distinct cues observed from human actions. Traditionally, K-Nearest Neighbor (K-NN) classifier is used to compute crisp votes from multiple cues separately. The votes are then combined using linear weighting scheme. Usually, the weights are determined in a brute-force or trial-and-error manner. In this study, we propose a new classification framework based on sum-rule...
This paper presents a text query-based method for keyword spotting from online Chinese handwritten documents. The similarity between a text word and handwriting is obtained by combining the character similiarity scores given by a character classifier. To overcome the ambiguity of character segmentation, multiple candidates of character patterns are generated by over-segmentation, and sequences of...
Handwriting-gesture recognition has been widely implemented in handwriting input application. Usually, gestures are used to conduct edit operations or be set as short-cut of an application. In this paper, we compare several handwriting-gesture recognition methods, and address their different user cases. These methods include pixel-matching method, rule based method and discriminant-function based...
A supervised nonlinear classification approach is proposed in this paper. It can classify data in original feature space without concerning kernel transformation to map data into linear high dimension space, Belonging degree measure used in this approach is more rational than some conventional distance measures such as Euclidean distance, Under ERM principle, union of hyper ellipsoids and hyper planes...
Recognizing human actions in video sequences is frequently based on analyzing the shape of the human silhouette as the main feature. In this paper we introduce a method for recognizing different actions by comparing signatures of similarities to pre-defined shape prototypes. In training, we build a vocabulary of shape prototypes by clustering a training set of human silhouettes and calculate prototype...
Self-Organization Map (SOM) offers an effective visualization capability for analyzing high-dimensional data. Nevertheless, most SOM models lack a robust solution to appropriately manipulate both numeric and categorical data. To solve the foregoing problem, Generalized SOM (GenSOM) was proposed to handle distance measurement of mixed-type data via distance hierarchy. Whereas GenSOM constrains projection...
Learning models for recognizing objects with few or no training examples is important, due to the intrinsic long-tailed distribution of objects in the real world. In this paper, we propose an approach to use comparative object similarity. The key insight is that: given a set of object categories which are similar and a set of categories which are dissimilar, a good object model should respond more...
This work presents the classification of different types of consumptions of water in a house (sinks, showers, washing machines etc.). This classification takes into account the measured flow and the duration of the flow at a particular point in the water distribution network. The classifier uses the FCM and Gustafson-Kessel algorithms. The data set is called AGUA and it corresponds to real data gathered...
In this paper, we proposed an automatic lung segmentation method. We designed a ROI based method to estimate a proper initial lung boundary for ASM deformation by deriving the translation and the scaling parameters from the lung ROI. An adaptive ASM, using k-means clustering and silhouette-based cluster validation technique, was proposed to adapt to the lung shape change so that the lung shape variation...
Practical applications of online handwritten character recognition demand robust and highly accurate recognition along with low memory requirements. The Active-DTW classifier proposed by Sridhar et al.combines the advantages of generative and discriminative classifiers to address the similarity of between-class samples, while taking into account the variability of writing styles within the same character...
We propose a new method for handwritten word-spotting which does not require prior training or gathering examples for querying. More precisely, a model is trained ldquoon the flyrdquo with images rendered from the searched words in one or multiple computer fonts. To reduce the mismatch between the typed-text prototypes and the candidate handwritten images, we make use of: (i) local gradient histogram(LGH)...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.