An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

Disclosed are systems, computer-readable mediums, and methods for determining that text contains Chinese, Japanese, or Korean characters. One method includes determining a language hypothesis for each text fragment in a plurality of text fragments identified from connected components in a document image. The method further includes selecting a first subset of text fragments from the plurality of text fragments based on ratings for the language hypothesis of each text fragment in the plurality of text fragments. The method further includes verifying, by a processor, the language hypothesis of one or more text fragments in the first subset of text fragments based on optical character recognition of the one or more text fragments. The method further includes determining, by the processor, that Chinese, Japanese, or Korean (CJK) characters are present in the document image based on the verification of the language hypothesis of each of the one or more text fragments.

A method to determine image similarities. The method may include obtaining a first image and a second image and determining a discrete transform difference between a first discrete transform of the first image and a second discrete transform of the second image. The method may also include determining multiple first intensity vectors for the first image and determining multiple second intensity vectors for the second image. The method may also include determining an intensity vector difference between the multiple first intensity vectors and the multiple second intensity vectors and determining a color difference between a first color histogram of the first image and a second color histogram of the second image. The method may also include determining a similarity between the first image and the second image based on the discrete transform difference, the intensity vector difference, and the color difference.

According to one embodiment, a computer-implemented method includes: capturing an image of a document using a camera of a mobile device; performing optical character recognition (OCR) on the image of the document; extracting an identifier of the document from the image based at least in part on the OCR; comparing the identifier with content from one or more reference data sources, wherein the content from the one or more reference data sources comprises global address information; and determining whether the identifier is valid based at least in part on the comparison. The method may optionally include normalizing the extracted identifier, retrieving additional geographic information, correcting OCR errors, etc. based on comparing extracted information with reference content. Corresponding systems and computer program products are also disclosed.

An intelligent scoring method and system for a text objective question, the method comprising: acquiring an answer image of a text objective question (101); segmenting the answer image to obtain one or more segmentation results of an answer string to be identified (102); determining whether any of the segmentation results has the same number of characters as the standard answer (103); if no, the answer is determined to be wrong (106); otherwise, calculating identification confidence of the segmentation result having the same number of words as the standard answer, and/or calculating the identification confidence of respective characters in the segmentation result having the same number of words as the standard answer (104); determining whether the answer is correct according to the calculated identification confidence (105). The method can automatically score text objective questions, thus reducing consumption of human resource, and improving scoring efficiency and accuracy.

An image pickup device transmits to a server a transmission sample including a detection image detected by a first detection section from a transmitting/receiving section under the control of a transmission sample control section. The server performs detection processing that requires more resources than those of the first detection section on the detection image transmitted by a second detection section from the image pickup device, and determines whether or not the detection image in question is spurious, based on a second detection score which is thereby obtained. A transmission frequency deciding section generates transmission frequency control information such as to raise the transmission frequency by an image pickup device that has a high frequency of spurious detection; a transmitting/receiving section transmits the transmission frequency control information to the image pickup device.

An apparatus includes a first acquisition unit configured to acquire main object information specifying a main object in generation of a layout image, a second acquisition unit configured to acquire object correlation information specifying an object having a correlation with the main object, an extraction unit configured to extract at least one image including the main object and at least one image including the object having the correlation with the main object from a plurality of images based on the acquired main object information and the acquired object correlation information acquired, and a generation unit configured to generate, using a layout template, a layout image in which the at least one image extracted by the extraction unit and including the main object and the at least one image extracted by the extraction unit and including the object having the correlation with the main object are laid out therein.

An exemplary lens arrangement can be provided that includes a plurality of lenses configured to provide a field of view (FOV) of between about 9 mm×6 mm to about 15 mm×12 mm, a resolution at at least one edge of the lenses of between about 40 lp/mm to about 100 lp/mm, and a distortion between about 0.1% to about 1%.

A method including training predictor machine learning models (MLMs) using a first data set. The trained predictor MLMs are trained to predict classifications of data items in the first data set. The method also includes training confidence MLMs using second classifications, output by the trained predictor MLMs. The method also includes generating an aggregated ranked list of classes based on third classifications output by the trained predictor MLMs and second confidences output by the trained confidence MLMs. The method also includes training an ensemble confidence MLM using the aggregated ranked list of classes to generate a trained ensemble confidence MLM. The trained ensemble confidence MLM is trained to predict a corresponding selected classification for each corresponding data item in a training data set containing second data items similar to the first data items.

An image detection apparatus includes: a display outputting an image; a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: detect, by using a neural network, an additional information area in a first image output on the display; obtain style information of the additional information area from the additional information area; and detect, in a second image output on the display, an additional information area having style information different from the style information by using a model that has learned an additional information area having new style information generated based on the style information.