In sequence labeling, using higher order features leads to high inference complexity. A lot of studies have been conducted to address this problem. In this paper, we propose a new exact decoding algorithm under the assumption that weights of all higher order features are non-negative. In the worst case, the time complexity of our algorithm is quadratic on the number of higher order features. Comparing with existing algorithms, our method is more efficient and easier to implement. We evaluate our method on two sequence labeling tasks: Optical Character Recognition and Chinese part-of-speech tagging. Our experimental results demonstrate that adding higher order features significantly improves the performance while requiring only 30% additional inference time.

In this paper, we tackle the problem of online semi-supervised learning (SSL). When data arrive in a stream, the dual problems of computation and data storage arise for any SSL method. We propose a fast approximate online SSL algorithm that solves for the harmonic solution on an approximate graph. We show, both empirically and theoretically, that good behavior can be achieved by collapsing nearby points into a set of local "representative points" that minimize distortion. Moreover, we regularize the harmonic solution to achieve better stability properties. We apply our algorithm to face recognition and optical character recognition applications to show that we can take advantage of the manifold structure to outperform the previous methods. Unlike previous heuristic approaches, we show that our method yields provable performance bounds.

Character segmentation is one of the most important decision processes for optical character recognition (OCR). Isolating individual alphabetic characters in the script image is often significant enough to make a decisive contribution towards the success rate of the overall system. An OCR system may be designed to work for either of online and off-line purposes. Online OCR systems collect input data by recording the order of strokes made by the write on an electronic bit-pad, and off-line OCR systems do the same by recording the pixel by pixel digital image of the entire writing with a digital scanner. OCR has a wide field of application covering handwritten document transcription, automatic mail address recognition, machine processing of bankchecks, faxes etc. Off-line OCR of hand written words has long been an active area research. Some important contributions so far made in this field involve analysis of English texts [1], [2], [3], [5], Chinese script [6] and Arabic characters [9]. With this background of research, the present work considers Bengali script for developing suitable techniques for off-line OCR with it.

A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analog neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognize characters deformed by random noise, rotation, scaling, and shifting. Introduction: Analog neural network hardware has many advantages over its digital and software counterparts.

Crowdsourcing systems, in which tasks are electronically distributed to numerous ``information piece-workers'', have emerged as an effective paradigm for human-powered solving of large scale problems in domains such as image classification, data entry, optical character recognition, recommendation, and proofreading. Because these low-paid workers can be unreliable, nearly all crowdsourcers must devise schemes to increase confidence in their answers, typically by assigning each task multiple times and combining the answers in some way such as majority voting. In this paper, we consider a general model of such rowdsourcing tasks, and pose the problem of minimizing the total price (i.e., number of task assignments) that must be paid to achieve a target overall reliability. We give new algorithms for deciding which tasks to assign to which workers and for inferring correct answers from the workers’ answers. We show that our algorithm significantly outperforms majority voting and, in fact, are asymptotically optimal through comparison to an oracle that knows the reliability of every worker.

Existing crowdsourcing markets are often inaccessible to workers living at the bottom of the economic pyramid. We present MobileWorks, a mobile phone-based crowdsourcing platform intended to provide employment to developing world users. MobileWorks provides human optical character recognition (OCR) tasks that can be completed by workers on low-end mobile phones through a web browser. To address the limited screen resolution available on low-end phones, MobileWorks divides documents into many small pieces and sends each piece to a different worker. An initial pilot study with 10 users over a two month period revealed that it is feasible to do basic OCR tasks using a simple mobile web-based application. We find that workers using MobileWorks average 120 tasks per hour at an accuracy rate of 99% using a multiple entry solution. In addition, users had a positive experience with MobileWorks: all study participants would recommend MobileWorks to friends and family.

We describe a framework for rapidly prototyping applications which require intelligent visual processing, but for which reliable algorithms do not yet exist, or for which engineering those algorithms is too costly. The framework, CrowdSight, leverages the power of crowdsourcing to offload intelligent processing to humans, and enables new applications to be built quickly and cheaply, affording system builders the opportunity to validate a concept before committing significant time or capital. Our service accepts requests from users either via email or simple mobile applications, and handles all the communication with a backend human computation platform. We build redundant requests and data aggregation into the system freeing the user from managing these requirements. We validate our framework by building several test applications and verifying that prototypes can be built more easily and quickly than would be the case without the framework.

Human computation is a new and evolving research area that centers around harnessing human intelligence to solve computational problems that are beyond the scope of existing Artificial Intelligence (AI) algorithms. With the growth of the Web, human computation systems can now leverage the abilities of an unprecedented number of people via the Web to perform complex computation. There are various genres of human computation applications that exist today. Games with a purpose (e.g., the ESP Game) specifically target online gamers who generate useful data (e.g., image tags) while playing an enjoyable game. Crowdsourcing marketplaces (e.g., Amazon Mechanical Turk) are human computation systems that coordinate workers to perform tasks in exchange for monetary rewards.

This paper defines the notion of analogical dissimilarity between four objects, with a special focus on objects structured as sequences. Firstly, it studies the case where the four objects have a null analogical dissimilarity, i.e. are in analogical proportion. Secondly, when one of these objects is unknown, it gives algorithms to compute it. Thirdly, it tackles the problem of defining analogical dissimilarity, which is a measure of how far four objects are from being in analogical proportion. In particular, when objects are sequences, it gives a definition and an algorithm based on an optimal alignment of the four sequences. It gives also learning algorithms, i.e. methods to find the triple of objects in a learning sample which has the least analogical dissimilarity with a given object. Two practical experiments are described: the first is a classification problem on benchmarks of binary and nominal data, the second shows how the generation of sequences by solving analogical equations enables a handwritten character recognition system to rapidly be adapted to a new writer.

We present a study which is concerned with word recognition rates for heavily degraded documents. We compare human with machine reading capabilities in a series of experiments, which explores the interaction of word/non-word recognition, word frequency and legality of non-words with degradation level. We also study the influence of character segmentation, and compare human performance with that of our artificial neural network model for reading. We found that the proposed computer model uses word context as efficiently as humans, but performs slightly worse on the pure character recognition task. 1 Introduction Optical Character Recognition (OCR) of machine-print document images ·has matured considerably during the last decade. Recognition rates as high as 99.5% have been reported on good quality documents. However, for lower image resolutions (200 Dpl and below), noisy images, images with blur or skew, the recognition rate declines considerably. In bad quality documents, character segmentation is as big a problem as the actual character recognition.