A document evaluation apparatus includes: a document data acquisition unit that acquires document data including at least text objects; a preliminary processing unit that performs a preliminary process on the document data acquired by the document data acquisition unit; an information volume evaluation unit that evaluates an amount of information in the document data based on the preliminarily processed document data; a character evaluation unit that evaluates the legibility of text based on the preliminarily processed document data; and a color evaluation unit that evaluates the relationships among adjacent colors in the document data based on the preliminarily processed document data.

Aspects and implementations provide for techniques of fast and efficient recognition of texts in electronic documents. The disclosed techniques include, for example, accessing a description of a symbol in a page description file for a document and identifying, responsive to a character code failure, the symbol using a vectorized drawing instruction for the symbol. The character code failure includes an absence of a character code in the description of the symbol or a bad character code in the symbol description of the symbol. The techniques further include identifying a text of the document using the identified symbol.

A method of training a text quality assessment model, a method of determining text quality, an electronic device, and a storage medium are provided. The method of training the text quality assessment model includes: determining a first text satisfying a condition of being a negative sample and a second text satisfying a condition of being a positive sample from a plurality of texts based on indicators for the texts; for any text of the first text and the second text, adding a label to the text based on the condition satisfied by the text, wherein the label indicates a category of the text, and the category includes a low-quality category for the negative sample and a non-low-quality category for the positive sample; and constituting a training set by the first text having a label and the second text having a label, to train the text quality assessment model.

Systems and methods for automatic enrollment and identity verification based upon processing a captured image of a document are disclosed herein. Various embodiments enable, for example, a user to enroll in a particular service by taking a photograph of a particular document (e.g., his driver license) with a mobile device. One or more algorithms can then extract relevant data from the captured image. The extracted data (e.g., the person's name, gender, date of birth, height, weight, etc.) can then be used to automatically populate various fields of an enrollment application, thereby reducing the amount of information that the user has to manually input into his mobile device in order to complete the enrollment process. In some embodiments, a set of internal and/or external checks can be run against the data to ensure that the data is valid, has been read correctly, and is consistent with other data.

A first character string obtainment unit according to one or more embodiments may obtain a first character string in response to an input character string that has been input. A similar character extraction unit extracts similar characters having similar shapes as characters in the first character string. A second character string generation unit generates one or more second character strings in which some or all of the characters in the first character string are replaced with similar characters extracted by the similar character extraction unit. Then, a conversion candidate output unit outputs the first character string and the second character strings as conversion candidates for the input character string.

Systems and methods for deep learning model development for data extraction using a feedback loop. A system generates an interactive graphical user interface (GUI) on one or more user devices for displaying a document with data extracted from the document by a data extraction model together with a user interaction tool allowing the user to correct the extracted data. The system receives, via the interactive GUI, correction information for the extracted data and monitoring performance characteristics of the extraction model in real-time based on the user correction information. The system automatically updates and trains the extraction model using the correction information responsive to detecting that the performance characteristics meet a predetermined performance reduction condition.

An image processing apparatus that is capable of restoring a degraded image with high accuracy The image processing apparatus acquires image data including an image of character information and identifies a character type of the character information. A learned model adapted to the identified character type is acquired from a plurality of learned models subjected to machine learning using images for learning, which are associated with a plurality of character type conditions, respectively, and correct answer images associated therewith. The image of character information is input to the acquired learned model to restore the image of character information.

Detection of textual phrases in a non-horizontal orientation at a scene is a critical problem. This disclosure relates to a processor implemented method to detect a text from multimedia content captured at a scene. An input original image is processed by a trained model to obtain an individual character with a bounding box on the original image. The original image is positioned by a gradient to obtain a rotated image if a number of detected characters is not equal to a number of expected characters on the original image. At least one missing character bounding box on the original image and on the rotated image are estimated to construct a horizontal text image if the number of detected characters is not equal to the number of expected characters on the rotated image. At least one missing character in the estimated bounding box is detected by at least one text returned from an optical character reader.

An apparatus includes a memory and a processor. The memory stores a dictionary and a machine learning algorithm trained to classify text. The processor receives an image of a page, converts the image into a set of text, and identifies a plurality of tokens within the text. Each token includes one or more contiguous characters that are both preceded and followed by whitespace within the text. The processor identifies invalid tokens by removing tokens of the plurality of tokens that correspond to words of the dictionary. The processor calculates, based on a ratio of a total number of valid tokens to a total number of tokens, a score. In response to determining that the score is greater than a threshold, the processor applies the machine learning algorithm to classify the text into a category and stores the image and/or text in a database according to the category.

Imaging devices, systems, and methods for capturing and processing images for vision applications in a non-fixed environment are described herein. An example system includes: an imaging assembly, an aiming assembly, and one or more imaging processors configured to: (a) receive a first image; (b) analyze at least a portion of the first image to determine a first focus value; (c) configure a focus parameter of the imaging assembly based on the first focus value; (d) receive a subsequent image; (e) determine a blurriness value for at least a portion of the subsequent image; (f) responsive to the blurriness value being less than a predetermined threshold value, transmit the subsequent image to a decode module; and (g) responsive to the blurriness value exceeding the predetermined threshold value: determine a subsequent focus value; (ii) configure the focus parameter based on the subsequent focus value; and (iii) repeat (d) through (g).