A method and apparatus for processing image data is provided. The method includes the steps of employing a main processing network for classifying one or more features of the image data, employing a monitor processing network for determining one or more confusing classifications of the image data, and spawning a specialist processing network to process image data associated with the one or more confusing classifications.

A system and method of identifying objects is provided. In one aspect, the system and method includes a hand-held device with a display, camera and processor. As the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. The processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. The display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.

A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

One variation of a method includes: accessing a handwriting sample comprising a set of user glyphs handwritten by a user; for each character in a set of characters, identifying a subset of user glyphs corresponding to the character in the handwriting sample, characterizing variability of a set of spatial features across the subset of user glyphs, and storing variability of the set of spatial features across the subset of user glyphs in a character container corresponding to the character; and compiling the set of character containers into a handwriting model for the user. The method further includes: accessing a text string comprising a combination of characters in the set of characters; for each instance of each character in the text string, inserting a set of variability parameters into the handwriting model to generate a synthetic glyph representing the character; and assembling the set of synthetic glyphs into a print file.

The present invention relates to a computer-implemented method and a system for testing the output of a neural network (1) having a plurality of layers (11), which detects or classifies objects. The method comprises the step (S1) of reading at least one result from at least one first layer (11) and the confidence value thereof, which is generated in the first layer (11) of a neural network (1), and the step (S2) of checking a plausibility of the result by taking into consideration the confidence value thereof so as to conclude whether the object detection by the neural network (1) is correct or false. The step (S2) of checking comprises comparing the confidence value for the result with a predefined threshold value. In the event that it is concluded in the checking step (S2) that the object detection is false, output of the object falsely detected by the neural network is prevented.

Generally, a system and method for an automatic detection of referee's decisions during a ball-game match are provided. The method may include receiving a plurality of images of a ball-game field generated during the ball-game match; determining, based on predetermined ball-game rules, a first subset of images of the plurality of images representing a first event that is suspected as a specified rule-based event; determining, based on the predetermine ball-game rules, a second subset of images of the plurality of images that represents a second event, wherein the second event is subsequent to the specified rule-based event according to the predetermined ball-game rules; and analyzing, based on the predetermined ball-game rules, the images of the second subset and further determining, based on the analysis thereof, a referee's decision concerning whether the first even is the specified rule-based event.

An electronic device and a controlling method thereof are provided. A controlling method of an electronic device according to the disclosure includes: performing first learning for a neural network model for acquiring a video sequence including a talking head of a random user based on a plurality of learning video sequences including talking heads of a plurality of users, performing second learning for fine-tuning the neural network model based on at least one image including a talking head of a first user different from the plurality of users and first landmark information included in the at least one image, and acquiring a first video sequence including the talking head of the first user based on the at least one image and pre-stored second landmark information using the neural network model for which the first learning and the second learning were performed.

Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.

Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.