Embodiments include methods, systems and computer program products method for generating one or more new glyphs by combining one or more available radicals. The computer-implemented method includes receiving, using a processor, a glyph determined to be unavailable for a character representation within text. The processor identifies one or more structures and radicals associated with the unavailable glyph for the character. The processor further searches for a replacement glyph or portions thereof from a group of available glyphs. The processor combines the replacement glyph or portions thereof to form a new glyph. The processor further replaces the unavailable glyph with the new glyph. The processor further displays the new glyph in the text at a location associated with the unavailable glyph.

Disclosed are methods for handwriting recognition. In some aspects, an image representing a page of a sample document is analyzed to identify a region having indications of handwriting. The region is analyzed to determine frequencies of a plurality of geometric features within the region. The frequencies may be compared to profiles or histograms of known language types, to determine if there are similarities between the frequencies in the sample document relative to those of the known language types. In some aspects, machine learning may be used to characterize the document as a particular language type based on the frequencies of the geometric features.

A method and a system are described for performing optical character recognition on an image including a plurality of printed characters. The method includes defining one or more opcodes and direction pointers associated with the plurality of printed characters of a language and a font type, wherein each of the one or more opcodes has an associated unique opcode characterization value. The method includes creating a binary tree comprising a plurality of nodes, wherein each node of the plurality of nodes is assigned the unique opcode characterization value. The method includes retrieving a set of operations associated with the unique opcode characterization value assigned to each of the plurality of nodes. The method includes navigating the binary tree from a root node to a leaf node based on the set of operations, the first pointer value, and the second pointer value until the leaf node is reached.

Apparatus for recognition of handwritten Chinese characters contains a bus, an input means connecting to the bus for receiving input imagery data created from a handwritten Chinese character, a Cellular Neural Networks or Cellular Nonlinear Networks (CNN) based integrated circuit operatively connecting to the bus for extracting features out of the input imagery data using pre-trained filter coefficients of a plurality of order convolutional layers stored therein, a memory connecting the bus, the memory being configured for storing weight coefficients of fully-connected (FC) layers, a processing unit connecting to the bus for performing computations of FC layers to classify the extracted features from the CNN based integrated circuit to a particular Chinese character in a predefined Chinese character set, and a display unit connecting to the bus for displaying the particular Chinese character. Greater than 95% recognition accuracy is achieved using multiple bi-valued 33 filter kernels as pre-trained filter coefficients.

A method of generating a text line classifier including generating text line samples by use of a present terminal system font reservoir. The method also includes extracting features from the text line samples and pre-stored marked-up samples. The method further includes training models by use of the extracted features to generate a text line classifier for recognizing text regions. With the system font reservoir being utilized for generating text line samples, the generated text line classifiers can target different scenes or different requirements for text region recognition with a high degree of applicability and wide application in addition to ease of implementation. Together with the combinational use of the marked up samples for extracting features from the text line samples, the generated text line classifiers provide for enhanced classification efficiency and accuracy.

A vehicle imaging system may include a first circuit board, and the system may also include an additional circuit board. The circuit boards may hold components for capturing images of vehicles as well as components for analyzing images of vehicles that have been captured. The analyzing may include performing optical character recognition on portions on images to identify characters in the images. A housing may enclose the circuit boards. The vehicle imaging system may be a license plate recognition system, a DOT number reader system, a hazardous material placard reader system, or a container code reader system, for example.

A method for applying a graphic effect in an electronic device. The method includes identifying a stroke constituting a character based on an input sensed through a display of the electronic device, displaying the identified stroke through the display, identifying a language corresponding to the identified stroke, and identifying a variation value for a graphic effect of the displayed stroke based on a complexity of the identified language.

Methods and systems for testing base text direction (BTD) include comparing one or more images from an end-user system to a respective reference image associated with a respective text test case. Each of the one or more images includes respective text test case information. It is determined whether the end-user system produces BTD errors based on the comparison in accordance with one or more BTD error rules.

According to one embodiment, an information processing device includes a storage device and a processor connected to the storage device. The processor is configured to perform a process for displaying an image and information related to a size of a recognition target, and recognize a recognition target from the image. The information related to the size of the recognition target includes visual information of the recognition target.

Methods and systems for testing base text direction (BTD) include receiving one or more images captured by an end-user system. Each of the one or more images displays respective text test case information. Each of the one or more images is compared to a respective reference image associated with a respective text test case. It is determined whether the end-user system produces BTD errors based on the comparison in accordance with one or more BTD error rules.