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

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.

/pdf/rapid-object-detection-using-a-boosted-cascade-of-simple-4crej3dxmd.pdf

Rapid object detection using a boosted cascade of simple features

The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection.

This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.

/pdf/the-pascal-visual-object-classes-voc-challenge-ugvl0p2h51.pdf

The Pascal Visual Object Classes (VOC) Challenge

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn.

Fast R-CNN

The present invention relates generally to automatically processing electronic documents. In one aspect, features and/or properties of words are identified from a set of training documents to aid in extracting information from documents to be processed. The features and/or properties relate to text of the words, position of the words and the relationship to other words. A classifier is developed to express these features and/or properties. During information extraction, documents are processed and analyzed based on the classifier and information is extracted based on correspondence of the documents and the features/properties expressed by the classifier.

Processing an electronic document for information extraction

Multiagent control systems for robots are considered. A robot is described that is based on treating the existing behavioral agents as simply an enhanced effector command language and designing a higher-level control structure that switches them on and off. It is shown how supervisory control can be added to such a reactive multiagent system. >

Cooperative control of a semi-autonomous mobile robot

In recent work, conditional Markov chain models (CMM) have been used to extract information from semi-structured text (one example is the Conditional Random Field [10]). Applications range from finding the author and title in research papers to finding the phone number and street address in a web page. The CMM framework combines a priori knowledge encoded as features with a set of labeled training data to learn an efficient extraction process. We will show that similar problems can be solved more effectively by learning a discriminative context free grammar from training data. The grammar has several distinct advantages: long range, even global, constraints can be used to disambiguate entity labels; training data is used more efficiently; and a set of new more powerful features can be introduced. The grammar based approach also results in semantic information (encoded in the form of a parse tree) which could be used for IR applications like question answering. The specific problem we consider is of extracting personal contact, or address, information from unstructured sources such as documents and emails. While linear-chain CMMs perform reasonably well on this task, we show that a statistical parsing approach results in a 50% reduction in error rate. This system also has the advantage of being interactive, similar to the system described in [9]. In cases where there are multiple errors, a single user correction can be propagated to correct multiple errors automatically. Using a discriminatively trained grammar, 93.71% of all tokens are labeled correctly (compared to 88.43% for a CMM) and 72.87% of records have all tokens labeled correctly (compared to 45.29% for the CMM).

Learning to extract information from semi-structured text using a discriminative context free grammar

The problem of recognizing mathematical expressions differs significantly from the recognition of standard prose. While in prose significant constraints can be put on the interpretation of a character by the characters immediately preceding and following it, few such simple constraints are present in a mathematical expression. In order to make the problem tractable, effective methods of recognizing mathematical expressions will need to put intelligent constraints on the possible interpretations. The authors present preliminary results on a system for the recognition of both handwritten and typeset mathematical expressions. While previous systems perform character recognition out of context, the current system maintains ambiguity of the characters until context can be used to disambiguate the interpretation. In addition, the system limits the number of potentially valid interpretations by decomposing the expressions into a sequence of compatible convex regions. The system uses A-star to search for the best possible interpretation of an expression. We provide a new lower bound estimate on the cost to goal that improves performance significantly.

/pdf/ambiguity-and-constraint-in-mathematical-expression-2sqrjkefk7.pdf

Ambiguity and constraint in mathematical expression recognition

No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is necessary. Both amount to a prior over the space of possible density functions. By far the most common approach is to assume that the density has a parametric form.

By contrast we derive a differential learning rule called EMMA that optimizes entropy by way of kernel density estimation. Entropy and its derivative can then be calculated by sampling from this density estimate. The resulting parameter update rule is surprisingly simple and efficient.

We will show how EMMA can be used to detect and correct corruption in magnetic resonance images (MRI). This application is beyond the scope of existing parametric entropy models.

/pdf/empirical-entropy-manipulation-for-real-world-problems-4d51hwevzf.pdf

Paul A. Viola

Papers

Processing an electronic document for information extraction

Cooperative control of a semi-autonomous mobile robot

Learning to extract information from semi-structured text using a discriminative context free grammar

Ambiguity and constraint in mathematical expression recognition

Empirical Entropy Manipulation for Real-World Problems