Vartika Singh

Real-time Automatic Deceit Detection from Involuntary Facial Expressions

Being the most broadly used tool for deceit measurement, the polygraph is a limited method as it suffers from human operator subjectivity and the fact that target subjects are aware of the measurement, which invites the opportunity to alter their behavior or plan counter-measures in advance. The approach presented in this paper attempts to circumvent these problems by unobtrusively and automatically measuring several prior identified deceit indicators (DIs) based upon involuntary, so-called reliable facial expressions through computer vision analysis of image sequences in real time. Reliable expressions are expressions said by the psychology community to be impossible for a significant percentage of the population to convincingly simulate, without feeling a true inner felt emotion. The strategy is to detect the difference between those expressions which arise from internal emotion, implying verity, and those expressions which are simulated, implying deceit. First, a group of facial action units (AUs) related to the reliable expressions are detected based on distance and texture based features. The DIs then can be measured and finally a decision of deceit or verity will be made accordingly. The performance of this proposed approach is evaluated by its real time implementation for deceit detection.

A Hierarchical Classification Model for Document Categorization

We propose a novel hierarchical classification method for documents categorization in this paper. The approach consists of multiple levels of classification for different hierarchies. Regularized Least Square (RLS)binary classifiers are applied in the middle levels of the hierarchy to classify documents into smaller set of categories and K-nearest-neighbor (KNN) multi-class classifiers are used at the bottom to classify documents into final classes. Experiments on large-scale real world tax documents show that the proposed hierarchical approach outperforms traditional flat classification method.

A Cascade Multiple Classifier System for Document Categorization

A novel cascade multiple classifier system (MCS) for document image classification is presented in the paper. It consists of two different classifiers with different feature sets. The proceeding classifier uses image features, learns physical representation of the document, and outputs a set of candidate class labels for the second classifier. The succeeding classifier is a hierarchical classification model based on textual features. The candidate labels set from the first classifier provides subtrees for the second classifier to search in the hierarchical tree and derive a final classification decision. Hence, it reduces the computational complexity and improves classification accuracy for the second classifier. We test the proposed cascade MCS on a large scale set of tax document classification. The experimental results show improvement of classification performance over individual classifiers.