A system is presented that classiies objects in raw images using statistical pattern recognition and spatial indexing. The system is given a training set containing samples of feature vectors of objects that may be found in the images. This method of classiication was applied to automatic interpretation of oor plans. A number of data structures are suggested for storing the training set. Of the...

In this paper, we propose a new rejection criterion applicable specifically to limited-training speech recognition systems such as Speaker-Dependent (SD) recognition systems. The new criterion uses confidence measures as well as speakerspecific out-of-vocabulary (OOV) models. The OOV models are created from the same training data that is available to create the in-vocabulary (IV) word models. W...

Emotion recognition ability (ERA) predicts more successful interpersonal interactions. However, it remains unknown whether ERA training can affect behaviors and improve social outcomes in such Here, 83 dyads of same-gender students completed either a self-administered 45 min based on audio-visual clips 14 different emotions, or control about cloud types. All then engaged face-to-face employee-r...

This paper presents a novel face recognition approach which uses only partial information in the recognition stage. The algorithm is based on an extension of the classical PCA and is called Partial PCA (P2CA). The PCA is a combined 2D-3D scheme which requires 3D face data in the training process but can process 2D pictures in the recognition stage. The strategy has been proven to be very robust...

High level features such as phone and word n-grams have been shown to be effective for speaker recognition, particularly when used along side traditional acoustic speaker recognition techniques. The applicability of these high-level recognition systems is impeded by the large training data requirements needed to build robust and stable speaker models. This paper describes an extension to an exi...