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

We present an approach to motion planning for humanoid robots that aims to ensure reliable execution by augmenting the planning process to reason about the robot's ability to successfully perceive its environment during operation. By efficiently simulating the robot's perception system during search, our planner utilizes a perceptive capability metric that quantifies the 'sensability' of the environment in each state given the task to be accomplished. We have applied our method to the problem of planning robust autonomous grasping motions and walking sequences as performed by an HRP-2 humanoid. A fast GPU-accelerated 3D tracker is used for perception, with a grasp planner and footstep planner incorporating reasoning about the robot's perceptive capability. Experimental results show that considering information about the predicted perceptive capability ensures that sensing remains operational throughout the grasping or walking sequence and yields higher task success rates than perception-unaware planning.

Motion planning using predicted perceptive capability

To run off-premise private cloud, consumer needs budget for public cloud data-out charge. This amount of expenditure can be considerable for data-intensive organization. Deploying web cache can prevent consumer from duplicated data loading out of their private cloud up to some extent. In present existence, however, there is no cache replacement strategy designed specifically for cloud computing. Devising a cache replacement strategy to truly suit cloud computing paradigm requires ground-breaking design perspective. This paper presents a novel cloud cache replacement policy that optimizes cloud data-out charge, the overall responsiveness of data loadings and the scalability of cloud infrastructure. The measurements demonstrate that the proposed policy achieves superior cost-saving, delay-saving and byte-hit ratios against the other well-known web cache replacement policies.

Advances in Grid and Pervasive Computing

This paper presents the capturability analysis of a three-dimensional guidance law that provides a desired angular acceleration of the heading angle to a pursuer. The relative rotational motion between a pursuer and an evader is represented by an equation similar to the equation of motion for a spherical pendulum with a disturbance. A set of sufficient conditions for successful pursuit are derived, and it is proved that the conditions are satisfied by suitably choosing the gain parameters of the guidance law. For sufficiently large gains, a pursuer controlled by the guidance law catches a maneuvering evader while achieving motion camouflage.

Capturability analysis of a three-dimensional guidance law with angular acceleration input

: This research includes perception for road following and cross-country navigation, path planning, and tools for building integrated mobile robot systems. Main accomplishments, software components, publications, and personnel are reviewed. Detailed technical descriptions of the key component of the research are provided.

http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA352124&Location=U2&doc=GetTRDoc.pdf

Unmanned Ground Vehicle System Perception for Outdoor Navigation.

This paper proposes a method of automated individualization of eye region model. The eye region model has been proposed in past research that parameterizes both the structure and the motion of the eye region. Without any prior knowledge, one can never determine a given appearance of eye region to be either neutral to any expression, i.e., the inherent structure of the eye region, or the result of motion by a facial expression. The past method manually individualized the model with respect to the structure parameters in the initial frame and tracks the motion parameters automatically across the rest of the image sequence, assuming the initial frame contains only neutral faces. Under the same assumption, we automatically determine the structure parameters for the given eye region image. We train active appearance models (AAMs) for parameterizing the variance of individuality. The system projects a given eye region image onto the low dimensional subspace spanned by the AAM and retrieves the structure parameters of the nearest training sample and initializes the eye region model using them. The AAMs are trained in the subregions, i.e., the upper eyelid region, the palpebral fissure (the eye aperture) region, and the lower eyelid region, respectively. It enables each AAM to effectively represent fine structures. Experimental results show the proposed method gives as nice initialization as manual labor and allows comparative tracking results for a comprehensive set of eye motions.

/pdf/automated-individualization-of-deformable-eye-region-model-2rdzwm8mtw.pdf

Takeo Kanade

Papers

Motion planning using predicted perceptive capability

Advances in Grid and Pervasive Computing

Capturability analysis of a three-dimensional guidance law with angular acceleration input

Unmanned Ground Vehicle System Perception for Outdoor Navigation.

Automated Individualization of Deformable Eye Region Model and Its Application to Eye Motion Analysis