Takeo Kanade

Bio: Takeo Kanade is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Motion estimation & Image processing. The author has an hindex of 147, co-authored 799 publications receiving 103237 citations. Previous affiliations of Takeo Kanade include National Institute of Advanced Industrial Science and Technology & Hitachi.

Evaluation of Gabor-wavelet-based facial action unit recognition in image sequences of increasing complexity

Abstract: Previous work suggests that Gabor-wavelet-based methods can achieve high sensitivity and specificity for emotion-specified expressions (e.g., happy, sad) and single action units (AUs) of the Facial Action Coding System (FACS). This paper evaluates a Gabor-wavelet-based method to recognize AUs in image sequences of increasing complexity. A recognition rate of 83% is obtained for three single AUs when image sequences contain homogeneous subjects and are without observable head motion. The accuracy of AU recognition decreases to 32% when the number of AUs increases to nine and the image sequences consist of AU combinations, head motion, and non-homogeneous subjects. For comparison, an average recognition rate of 87.6% is achieved for the geometry-feature-based method. The best recognition is a rate of 92.7% obtained by combining Gabor wavelets and geometry features.

Shape from interreflections

Abstract: An iterative algorithm is presented that simultaneously recovers the actual shape and the actual reflectance from the pseudo estimates. The recovery algorithm works on Lambertian surfaces of arbitrary shape with possibly varying and unknown reflectance. The general behavior of the algorithm and its convergence properties are discussed. Both simulation and experimental results are included to demonstrate the accuracy and stability of the algorithm. >

Automated facial expression recognition based on FACS action units

Abstract: Automated recognition of facial expression is an important addition to computer vision research because of its relevance to the study of psychological phenomena and the development of human-computer interaction (HCI). We developed a computer vision system that automatically recognizes individual action units or action unit combinations in the upper face using hidden Markov models (HMMs). Our approach to facial expression recognition is based an the Facial Action Coding System (FACS), which separates expressions into upper and lower face action. We use three approaches to extract facial expression information: (1) facial feature point tracking; (2) dense flow tracking with principal component analysis (PCA); and (3) high gradient component detection (i.e. furrow detection). The recognition results of the upper face expressions using feature point tracking, dense flow tracking, and high gradient component detection are 85%, 93% and 85%, respectively.

Facial Expression Recognition

Abstract: This chapter introduces recent advances in facial expression analysis and recognition. The first part discusses general structure of AFEA systems. The second part describes the problem space for facial expression analysis. This space includes multiple dimensions: level of description, individual differences in subjects, transitions among expressions, intensity of facial expression, deliberate versus spontaneous expression, head orientation and scene complexity, image acquisition and resolution, reliability of ground truth, databases, and the relation to other facial behaviors or nonfacial behaviors. We note that most work to date has been confined to a relatively restricted region of this space. The last part of this chapter is devoted to a description of more specific approaches and the techniques used in recent advances. They include the techniques for face acquisition, facial data extraction and representation, facial expression recognition, and multimodal expression analysis. The chapter concludes with a discussion assessing the current status, future possibilities, and open questions about automatic facial expression analysis.

Gradient-based learning applied to document recognition

Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Going deeper with convolutions

Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Histograms of oriented gradients for human detection

Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.