scispace - formally typeset
Search or ask a question
Author

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.


Papers
More filters
BookDOI
01 Jan 1977

96 citations

Journal ArticleDOI
TL;DR: Experimental results showed that face tracking combining AAMs and CHMs is more pose robust than that of A AMs in terms of 170% higher tracking rate and the 115% wider pose coverage.
Abstract: The active appearance models (AAMs) provide the detailed descriptive parameters that are useful for various autonomous face analysis problems. However, they are not suitable for robust face tracking across large pose variation for the following reasons. First, they are suitable for tracking the local movements of facial features within a limited pose variation. Second, they use gradient-based optimization techniques for model fitting and the fitting performance is thus very sensitive to initial model parameters. Third, when their fitting is failed, it is difficult to obtain appropriate model parameters to re-initialize them. To alleviate these problems, we propose to combine the active appearance models and the cylinder head models (CHMs), where the global head motion parameters obtained from the CHMs are used as the cues of the AAM parameters for a good fitting or re-initialization. The good AAM parameters for robust face tracking are computed in the following manner. First, we estimate the global motion parameters by the CHM fitting algorithm. Second, we project the previously fitted 2D shape points onto the 3D cylinder surface inversely. Third, we transform the inversely projected shape points by the estimated global motion parameters. Fourth, we project the transformed 3D points onto the input image and computed the AAM parameters from them. Finally, we treat the computed AAM parameters as the initial parameters for the fitting. Experimental results showed that face tracking combining AAMs and CHMs is more pose robust than that of AAMs in terms of 170% higher tracking rate and the 115% wider pose coverage.

95 citations

Proceedings ArticleDOI
09 May 2011
TL;DR: This work reformulates the traditional least squares solution to allow the fast computation of surface normals, and proposes a new approach that obtains the normals by calculating the derivatives of the surface from a spherical range image.
Abstract: The fast and accurate computation of surface normals from a point cloud is a critical step for many 3D robotics and automotive problems, including terrain estimation, mapping, navigation, object segmentation, and object recognition. To obtain the tangent plane to the surface at a point, the traditional approach applies total least squares to its small neighborhood. However, least squares becomes computationally very expensive when applied to the millions of measurements per second that current range sensors can generate. We reformulate the traditional least squares solution to allow the fast computation of surface normals, and propose a new approach that obtains the normals by calculating the derivatives of the surface from a spherical range image. Furthermore, we show that the traditional least squares problem is very sensitive to range noise and must be normalized to obtain accurate results. Experimental results with synthetic and real data demonstrate that our proposed method is not only more efficient by up to two orders of magnitude, but provides better accuracy than the traditional least squares for practical neighborhood sizes.

92 citations

Journal ArticleDOI
TL;DR: A phase contrast microscope image restoration method that produces phase retardation features, which are intrinsic features of phase contrast microscopy, and a semi-supervised learning based algorithm for cell segmentation, which is a fundamental task for various cell behavior analysis are proposed.

92 citations

Book
03 Jan 1992
TL;DR: In this article, the basic shadow problem is extended to shadows cast by polyhedra and curved surfaces, and the analysis of the constraints provided by shadows can be analyzed in a manner analogous to the Basic Shadow Problem.
Abstract: : Given a line drawing from an image with shadow regions identified, the shapes of the shadows can be used to generate constraints on the orientations of the surfaces involved. This paper describes the theory which governs those constraints under orthography. A 'Basic Shadow Problem' is first posed, in which there is a single light source, and a single surface casts a shadow on another (background) surface. There are six parameters to determine: the orientation (2 parameters) for each surface, and the direction of the vector (2 parameters) pointing at the light source. If some set of 3 of these are given in advance, the remaining 3 can then be determined geometrically. The solution method consists of identifying 'illumination surfaces' consisting of illumination vectors, assigning Huffman-Clowes line labels to their edges, and applying the corresponding constraints in gradient space. The analysis is extended to shadows cast by polyhedra and curved surfaces. In both cases, the constraints provided by shadows can be analyzed in a manner analogous to the Basic Shadow Problem. When the shadow falls upon a polyhedron or curved surface, similar techniques apply. The consequences of varying the position and number of light sources are also discussed. Finally, some methods are presented for combining shadow geometry with other gradien space techniques for 3D shape inference. (Author)

91 citations


Cited by
More filters
Journal ArticleDOI
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
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.

42,067 citations

Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
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.

40,257 citations

Journal ArticleDOI

[...]

08 Dec 2001-BMJ
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
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 …

33,785 citations

Proceedings ArticleDOI
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
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.

31,952 citations

Proceedings ArticleDOI
23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
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.

21,729 citations