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.

A physical approach to color image understanding

Abstract: In this paper, we present an approach to color image understanding that can be used to segment and analyze surfaces with color variations due to highlights and shading. The work is based on a theory—the Dichromatic Reflection Model—which describes the color of the reflected light as a mixture of light from surface reflection (highlights) and body reflection (object color). In the past, we have shown how the dichromatic theory can be used to separate a color image into two intrinsic reflection images: an image of just the highlights, and the original image with the highlights removed. At that time, the algorithm could only be applied to hand-segmented images. This paper shows how the same reflection model can be used to include color image segmentation into the image analysis. The result is a color image understanding system, capable of generating physical descriptions of the reflection processes occurring in the scene. Such descriptions include the intrinsic reflection images, an image segmentation, and symbolic information about the object and highlight colors. This line of research can lead to physicsbased image understanding methods that are both more reliable and more useful than traditional methods.

Video OCR for digital news archive

Abstract: Video OCR is a technique that can greatly help to locate topics of interest in a large digital news video archive via the automatic extraction and reading of captions and annotations. News captions generally provide vital search information about the video being presented, the names of people and places or descriptions of objects. In this paper, two difficult problems of character recognition for videos are addressed: low resolution characters and extremely complex backgrounds. We apply an interpolation filter, multi-frame integration and a combination of four filters to solve these problems. Segmenting characters is done by a recognition-based segmentation method and intermediate character recognition results are used to improve the segmentation. The overall recognition results are good enough for use in news indexing. Performing video OCR on news video and combining its results with other video understanding techniques will improve the overall understanding of the news video content.

Determining shape and reflectance of hybrid surfaces by photometric sampling

Abstract: A method is presented for determining the shapes of hybrid surfaces without prior knowledge of the relative strengths of the Lambertian and specular components of reflection. The object surface is illuminated using extended light sources and is viewed from a single direction. Surface illumination using extended sources makes it possible to ensure the detection of both Lambertian and specular reflections. Uniformly distributed source directions are used to obtain an image sequence of the object. This method of obtaining photometric measurements is called photometric sampling. An extraction algorithm uses the set of image intensity values measured at each surface point to compute orientation as well as relative strengths of the Lambertian and specular reflection components. The simultaneous recovery of shape and reflectance parameters enables the method to adapt to variations in reflectance properties from one scene point to another. Experiments were conducted on Lambertian surfaces, specular surfaces, and hybrid surfaces. >

A System for Video Surveillance and Monitoring CMU VSAM Final Report

Abstract: : Under the three-year Video Surveillance and Monitoring (VSAM) project, the Robotics Institute at Carnegie Mellon University (CMU) and the Sarnoff Corporation have developed a system for autonomous Video Surveillance and Monitoring. The technical approach uses multiple, cooperative video sensors to provide continuous coverage of people and vehicles in a cluttered environment. This final report presents an overview of the system, and of the technical accomplishments that have been achieved. Details can be found in a set of previously published papers that together comprise Appendix A.

Panoptic Studio: A Massively Multiview System for Social Interaction Capture

Abstract: We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the integration of perceptual analyses over a large variety of view points. We present a modularized system designed around this principle, consisting of integrated structural, hardware, and software innovations. The system takes, as input, 480 synchronized video streams of multiple people engaged in social activities, and produces, as output, the labeled time-varying 3D structure of anatomical landmarks on individuals in the space. Our algorithm is designed to fuse the “weak” perceptual processes in the large number of views by progressively generating skeletal proposals from low-level appearance cues, and a framework for temporal refinement is also presented by associating body parts to reconstructed dense 3D trajectory stream. Our system and method are the first in reconstructing full body motion of more than five people engaged in social interactions without using markers. We also empirically demonstrate the impact of the number of views in achieving this goal.

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.