Christopher Middendorff's research while affiliated with University of Notre Dame and other places

Publications (8)

Article
The ear has gained popularity as a biometric feature due to the robustness of the shape over time and across emotional expression. Popular methods of ear biometrics analyze the ear as a whole, leaving these methods vulnerable to error due to occlusion. Many researchers explore ear recognition using an ensemble, but none present a method for designi...
Conference Paper
Due to its semi-rigid shape and robustness against change over time, the ear has become an increasingly pop- ular biometric feature. It has been shown that combining individual biometric methods into multi-biometric systems improves recognition. What features should be used, how they should be captured, what algorithms should be used, and how they...
Article
Full-text available
In this paper, we discuss a simple extension to the standard particle swarm optimization algorithm, inspired by genetic algorithms that allow swarms to cope better with dynamically changing fitness evaluations for a given parameter space. We demonstrate the utility of the extension in an application system for dynamical facial feature detection and...
Conference Paper
Full-text available
DIARC, a distributed integrated affect, reflection, cognition architecture for robots, provides many features that are criti- cal to successful natural human-robot interaction. As such, DIARC is an ideal platform for experimentation in HRI. In this paper we describe the architecture and and its implemen- tation in ADE, paying particular attention t...
Article
Full-text available
We present an architecture for complex affective robots for human-robot interaction. After describing our ra-tionale for using affect as a means of "architectural in-tegration", we give a quick conceptual example of how affect can play an organizational role in a complex agent and then describe our proposed affective architecture, its functionality...
Conference Paper
Full-text available
We present an architecture for complex affective robots for human-robot interaction. After describing our ra- tionale for using affect as a means of "architectural in- tegration", we give a quick conceptual example of how affect can play an organizational role in a complex agent and then describe our proposed affective architecture, its functionali...

Citations

... In the modern e-world, biometrics has great potentials because of their high accuracy and convenience to use. Researchers and scientists have systematically investigated the use of a number of biometric characteristics like fingerprint [2][3][4][5], face [6], iris [7,8], palmprint [9,10], hand geometry [11], hand vein [12], finger knuckle-print [13,14], voice [15], and ear [16] in the development of computing techniques. The use of applications like automatic personal authentication systems in day-today life results in reliable and effective security control. ...
... The architecture of choice for the implementation of the goal representation and inference mechanisms above was the Distributed Integrated Affective Reflective Cognitive (DIARC) architecture because it already provides explicit goal representations for agent and infrastructure goals. a) Agent goals: DIARC facilitates HRI by integrating high-level natural language understanding [3], [2], [5] with lower level perceptual and action processing (e.g., vision [1], [15], [12], navigation, behavior coordination [16]). DIARC's integrated NLP (natural language processing) component can take natural language directives and convert them into logical representations of the commands. ...
... Among many non-verbal and involuntary channels through which humans express themselves, facial expressions hold paramount importance. Studies such as [31], [32] have shown that Human-Machine Affective Interaction has been proving considerable results in learning and responding towards affective stimuli in natural and uncontrolled environments. If such learning agents are trained congruously, the performance of the recommendation systems can greatly be improved. ...
... On a dataset of 18 subjects of profile face and ear, the recognition rate was 94.44%. Middendorff and Bowyer [6] used PCA/ICP for face/ear, manually annotating feature landmarks. On a 411 subject dataset they were able to achieve a best fusion rate of 97.8%. ...
... Some researchers proposed frameworks that recognize human activity analyzing 2D scene with a pattern matching techniques (e.g., [15], [16]). Scheutz et al. [17] implemented a cognitive behavior recognition system for receptionist and waiter robots that recognizes and generates affective behavior . Brand et al. [18] utilized coupled HMMs to recognize two-handed activities. ...
... In addition, while Williams et al. [4] used iRobot Create, we used Turtlebot. Furthermore, while Williams et al. [4] utilized the robot control architecture (Distributed Integrated Affect, Reflection, and Cognition (DIARC)) [22] to generate the robot's utterances, our study developed the WOZ interface with a human expert (majoring in Korean linguistics) by selecting pre-recorded audio files as the robot's utterances. The possibility that these differences subtly influenced the results cannot be completely excluded. ...
... The integration of multiple biometrics sources face and ear are discussed. The use of combined face and ear data, and found that even a simple fusion technique yields improved performance over either the face or ear alone [7]. The literature studies reviewed in Tables 1 claim that multi-biometrics improve over an individual biometric system. ...