Optical character 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.

Abstract: This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters) or gray-level subimages of each individual character The feature extraction methods are discussed in terms of invariance properties, reconstructability and expected distortions and variability of the characters The problem of choosing the appropriate feature extraction method for a given application is also discussed When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application

Abstract: The Tesseract OCR engine, as was the HP Research Prototype in the UNLV Fourth Annual Test of OCR Accuracy, is described in a comprehensive overview. Emphasis is placed on aspects that are novel or at least unusual in an OCR engine, including in particular the line finding, features/classification methods, and the adaptive classifier.

Abstract: CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) are widespread security measures on the World Wide Web that prevent automated programs from abusing online services. They do so by asking humans to perform a task that computers cannot yet perform, such as deciphering distorted characters. Our research explored whether such human effort can be channeled into a useful purpose: helping to digitize old printed material by asking users to decipher scanned words from books that computerized optical character recognition failed to recognize. We showed that this method can transcribe text with a word accuracy exceeding 99%, matching the guarantee of professional human transcribers. Our apparatus is deployed in more than 40,000 Web sites and has transcribed over 440 million words.

Abstract: A manual entry interactive paper and electronic document handling and process system uses a pen-like instrument (PI) with a writing point for making written entries upon a physical document and sensing the three-dimensional forces exerted on the writing tip as well as the motion associated with the act of writing. The PI is also equipped with a CCD array for reading pre-printed bar codes used for identifying document pages and other application defined areas on the page, as well as for providing optical character recognition data. A communication link between the PI and an associated base unit transfers the transducer data from the PI. The base unit includes a programmable processor, a display, and a communication link receiver. The processor includes programs for written character and word recognition, memory for storage of an electronic version of the physical document and any hand-written additions to the document. The display unit displays the corresponding electronic version of the physical document on a CRT or LCD as a means of feedback to the user and for use by authorized electronic agents.