Abstract Human postures or gestures which essentially are static orientations of the body usually symbolizing a motive are put to use for bridging the gap between novice and expert users. Both the users are at the same natural level and capability to interact. To achieve an interaction between the machine and its human operator various techniques are suggested in the text.... Human postures or gestures which essentially are static orientations of the body usually symbolizing a motive are put to use for bridging the gap between novice and expert users. Both the users are at the same natural level and capability to interact. To achieve an interaction between the machine and its human operator various techniques are suggested in the text. Their implementations though not cheap are also available in the market. Our research and implementation revolves around the use of an ordinary inexpensive camera to acquire live video and hence segment the human forearm locations using various filters. A database containing nearly 2000 images was created for this purpose. Furthermore a neural network for the purpose of pattern recognition among segmented images was trained. All the experimental results are gathered through testing on a live application in an interactive scenario. Read More Read Less

Abstract Pattern with time period is more valuable because it can better describe objective knowledge. Previous studies on periodic patterns from market basket data focus on patterns without considering the items with their purchased quantities. But in real-life transactions, an item could be purchased multiple times in a transaction and different items may have different quantity in the transactions. To solve this problem, we... Pattern with time period is more valuable because it can better describe objective knowledge. Previous studies on periodic patterns from market basket data focus on patterns without considering the items with their purchased quantities. But in real-life transactions, an item could be purchased multiple times in a transaction and different items may have different quantity in the transactions. To solve this problem, we incorporate the concept of transaction frequency (TF) and database frequency (DF) of an item in a time interval. Our algorithm works in two phases. In first phase we mined locally frequent item sets along with the set of intervals and their database frequency range and second phase mines the two types of periodic patterns (cyclic and acyclic) from the list of intervals. Experimental results are provided to validate the study. Read More Read Less

Abstract This work looks into the problem of detecting the presence of motorcyclist safety helmet on single images of city roads. The degree of adjustment of a new image to the previously trained Active Appearance Model (AAM) acts as the decision criterion for detection. This adjustment is measured by differences between AAM shape and appearance parameter vectors, which become the feature vectors for four... This work looks into the problem of detecting the presence of motorcyclist safety helmet on single images of city roads. The degree of adjustment of a new image to the previously trained Active Appearance Model (AAM) acts as the decision criterion for detection. This adjustment is measured by differences between AAM shape and appearance parameter vectors, which become the feature vectors for four different classifiers. Results show that this approach is feasible and may be recommended. Read More Read Less