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.

Gradient-based learning applied to document recognition

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.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

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 …

I and i

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.

/pdf/histograms-of-oriented-gradients-for-human-detection-3nteinziuq.pdf

Histograms of oriented gradients for human detection

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.

/pdf/rich-feature-hierarchies-for-accurate-object-detection-and-22fvjlggyg.pdf

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

End of year report for parallel vision algorithm design and implementation : January 15, 1987-January 14, 1988

We present an approach to navigation planning for humanoid robots that aims to ensure reliable execution by augmenting the planning process to reason about the robotpsilas ability to successfully perceive its environment during operation. By efficiently simulating the robotpsilas perception system during search, our planner generates a metric, the so-called perceptive capability, that quantifies the dasiasensabilitypsila of the environment in each state given the task to be accomplished. We have applied our method to the problem of planning robust autonomous walking sequences as performed by an HRP-2 humanoid. A fast GPU-accelerated 3D tracker is used for perception, with a footstep planner incorporating reasoning about the robotpsilas perceptive capability. When combined with a controller capable of adaptively adjusting the height of swing leg trajectories, HRP-2 is able to navigate around obstacles and climb stairs in dynamically changing environments. Reasoning about the future perceptive capability ensures that sensing remains operational throughout the walking sequence and yields higher task success rates than perception-unaware planning.

Humanoid navigation planning using future perceptive capability

Information Security and Cryptology - ICISC 2008

In this paper we present an algorithm to correct 3D reconstruction errors of 3D ultrasound catheter caused by ultrasound image thickness We also provide a method to quickly measure ultrasound image plane's thickness With thickness correction registration accuracy of navigation system using 3D ultrasound catheters can be improved by 20%

/pdf/image-thickness-correction-for-navigation-with-3d-intra-tgh9enj07m.pdf

Image Thickness Correction for Navigation with 3D Intra-cardiac Ultrasound Catheter

This paper evaluates the dynamic and kinematic properties of a prismatic mechanism and shows its capabilities in performing home manipulation tasks when integrated into a robotic arm. Our design is motivated from the observation that human hand motions often follow a linear trajectory when manipulating everyday objects. We present the mechanical design for a light-weight, energy-efficient robot named PRISM that emphasizes translational motion. By simulating the dynamics equations and comparing the structure of commonly used anthropomorphic arms and our proposed arm, we verify that translational motion is more energy efficient with PRISM, and the robot can maneuver itself in narrower places. Through simulation experiments using state of the art manipulation planning algorithms, we analyze the success rates of PRISM and an anthropomorphic robot arm in performing basic tasks. The simulation experiments center on pick-and-place tasks in cluttered kitchen scenes. We show a real-world prototype of PRISM and perform several manipulation experiments with it.

Takeo Kanade

Papers

End of year report for parallel vision algorithm design and implementation : January 15, 1987-January 14, 1988

Humanoid navigation planning using future perceptive capability

Information Security and Cryptology - ICISC 2008

Image Thickness Correction for Navigation with 3D Intra-cardiac Ultrasound Catheter

Analysis of task feasibility for a home robot using prismatic joints