This paper discusses the influence of the word lip reading by change of the frame rate. The proposed method applies active appearance model to extract the face and several lip regions. Then, our method calculates trajectory feature and applies DP matching. We set the target words as the Japanese 25 words, and took 250 utterance scenes per a speaker from ten Japanese men. Though many of research...

Scene classification has received much attention in the recent past. How images can be efficiently classified becomes an important research topic. Most of the stateof-the-art solutions assumed that scene classes are mutually exclusive. But, different human beings have different perceptions, and different people tend to respond inconsistently even to the same scene images. Hence, a scene image m...

This work contributes to detection and tracking of walking or running humans in surveillance video sequences. We propose a 2D model-based approach to the whole body tracking in a video sequence captured from a single camera view. An extended six-link biped human model is employed. We assume that a static camera observes the scene horizontally or obliquely. Persons can be seen from a continuum o...

This paper describes our work to allow players in a virtual world to pose questions without relying on textual input. Our approach is to create enhanced virtual photographs by annotating them with semantic information from the 3D environment’s scene graph. The player can then use these annotated photos to interact with inhabitants of the world through automatically generated queries that are gu...

In this paper, we present a novel exemplar-based technique for the interpolation between two textures that combines patch-based and statistical approaches. Motivated by the notion of texture as a largely local phenomenon, we warp and blend small image neighborhoods prior to patch-based texture synthesis. In addition, interpolating and enforcing characteristic image statistics faithfully handles...

One of the first criteria that a user uses in deciding to use and consume a photograph is whether it is in focus or not. We have developed an effective and efficient algorithm to detect out-offocus photographs. In this paper, we describe an algorithm that automatically determines if the captured photograph is out-offocus through image analysis. It uses several global figure-ofmerits which are c...

Aim To do a literature survey of Computational Auditory Scene Analysis and look for features or techniques t hat can be used for purposes such as discriminating a particular sound (speech in this case) from all the other sounds.

Humans read content from images. However, images have not only content, but also a notion of style. Some pictorial styles differ noticeably and can be distinguished without careful inspection of the picture. This paper analyzes the style that can be noticeable at a pre-attentive level, using image statistics. Since the way images are decoded in the human visual system is related to the structur...

The problem of overlapping harmonics is particularly acute in musical sound separation and has not been addressed adequately. We propose a monaural system based on binary time-frequency masking with an emphasis on robust decisions in timefrequency regions, where harmonics from different sources overlap. Our computational auditory scene analysis system exploits the observation that sounds from t...

v