Author
Takeo Kanade
Other affiliations: National Institute of Advanced Industrial Science and Technology, Hitachi, University of Pittsburgh ...read more
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 published on a yearly basis
Papers
More filters
••
18 Jun 1996TL;DR: A neural network-based face detection system that arbitrates between multiple networks to improve performance over a single network using a bootstrap algorithm, which eliminates the difficult task of manually selecting non-face training examples.
Abstract: We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We use a bootstrap algorithm for training the networks, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting non-face training examples, which must be chosen to span the entire space of non-face images. Comparisons with other state-of-the-art face detection systems are presented; our system has better performance in terms of detection and false-positive rates.
301 citations
•
12 Oct 1995TL;DR: In this article, an apparatus and method of creating a digital library from audio data and video images is presented. But the method is based on the first set of time-stamps and indexing the audio data.
Abstract: An apparatus and method of creating a digital library from audio data and video images. The method includes the steps of transcribing the audio data and marking the transcribed audio data with a first set of time-stamps and indexing the transcribed audio data. The method also includes the steps of digitizing the video data and marking the digitized video data with a second set of time-stamps related to the first set of time-stamps and segmenting the digitized video data into paragraphs according to a set of rules. The steps of storing the indexed audio data and the digitized video data with their respective sets of time-stamps is also provided. The method also includes the step of passing the transcribed audio data through a natural language interpreter before indexing the transcribed audio data. A method and apparatus for searching the digital library is disclosed.
293 citations
••
02 May 1994TL;DR: A paraperspective factorization method that can be applied to a much wider range of motion scenarios, such as image sequences containing significant translational motion toward the camera or across the image, is developed.
Abstract: The factorization method, first developed by Tomasi and Kanade, recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature points to obtain highly redundant feature position information. The method robustly processes the feature trajectory information using singular value decomposition (SVD), taking advantage of the linear algebraic properties of orthographic projection. However, an orthographic formulation limits the range of motions the method can accommodate. Paraperspective projection, first introduced by Ohta, is a projection model that closely approximates perspective projection by modelling several effects not modelled under orthographic projection, while retaining linear algebraic properties. We have developed a paraperspective factorization method that can be applied to a much wider range of motion scenarios, such as image sequences containing significant translational motion toward the camera or across the image. We present the results of several experiments which illustrate the method's performance in a wide range of situations, including an aerial image sequence of terrain taken from a low-altitude airplane.
289 citations
01 Jan 2000
TL;DR: This thesis describes a statistical method for 3D object detection that has developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithms thatCan reliably detect cars over a wide range of viewpoints.
Abstract: In this thesis, we describe a statistical method for 3D object detection. In this method, we decompose the 3D geometry of each object into a small number of viewpoints. For each viewpoint, we construct a decision rule that determines if the object is present at that specific orientation. Each decision rule uses the statistics of both object appearance and “non-object” visual appearance. We represent each set of statistics using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints.
288 citations
••
TL;DR: An automated method of facial display analysis by feature point tracking demonstrated high concurrent validity with manual FACS coding.
Abstract: The face is a rich source of information about human behavior. Available methods for coding facial displays, however, are human-observer dependent, labor intensive, and difficult to standardize. To enable rigorous and efficient quantitative measurement of facial displays, we have developed an automated method of facial display analysis. In this report, we compare the results with this automated system with those of manual FACS (Facial Action Coding System, Ekman & Friesen, 1978a) coding. One hundred university students were videotaped while performing a series of facial displays. The image sequences were coded from videotape by certified FACS coders. Fifteen action units and action unit combinations that occurred a minimum of 25 times were selected for automated analysis. Facial features were automatically tracked in digitized image sequences using a hierarchical algorithm for estimating optical flow. The measurements were normalized for variation in position, orientation, and scale. The image sequences were randomly divided into a training set and a cross-validation set, and discriminant function analyses were conducted on the feature point measurements. In the training set, average agreement with manual FACS coding was 92% or higher for action units in the brow, eye, and mouth regions. In the cross-validation set, average agreement was 91%, 88%, and 81% for action units in the brow, eye, and mouth regions, respectively. Automated face analysis by feature point tracking demonstrated high concurrent validity with manual FACS coding.
287 citations
Cited by
More filters
••
01 Jan 1998TL;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
••
07 Jun 2015TL;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
••
[...]
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
••
20 Jun 2005TL;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
••
23 Jun 2014TL;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