Abstract: Approaches provide for recognizing and locating text represented in image data. For example, image data that includes representations of text can be obtained. A width-focused recognition engine can be configured to analyze the image data to determine a base-set of words. The base-set of words can be associated with logical structure information that describes a geometric relationship between words in the base-set of words. A set of bounding boxes that includes one or more base words can be determined, as well as a confidence value for each base word. A depth-focused recognition engine can be configured to analyze the image data to determine a focused-set of words, the focused-set of words associated with a set of bounding boxes and confidence values for respective words. A set of merged words can be determined from a set of overlapping bounding boxes that overlap a threshold amount.

Abstract: Tasks such as object classification from image data can take advantage of a deep learning process using convolutional neural networks. These networks can include a convolutional layer followed by an activation layer, or activation unit, among other potential layers. Improved accuracy can be obtained by using a generalized linear unit (GLU) as an activation unit in such a network, where a GLU is linear for both positive and negative inputs, and is defined by a positive slope, a negative slope, and a bias. These parameters can be learned for each channel or a block of channels, and stacking those types of activation units can further improve accuracy.

Abstract: Approaches provide for identifying text represented in image data as well as determining a location or region of the image data that includes the text represented in the image data. For example, a camera of a computing device can be used to capture a live camera view of one or more items. The live camera view can be presented to the user on a display screen of the computing device. An application executing on the computing device or at least in communication with the computing device can analyze the image data of the live camera view to identify text represented in the image data as well as determine locations or regions of the image that include the representations.

Abstract: Tasks such as object classification from image data can take advantage of a deep learning process using convolutional neural networks. These networks can include a convolutional layer followed by an activation layer, or activation unit, among other potential layers. Improved accuracy can be obtained by using a generalized linear unit (GLU) as an activation unit in such a network, where a GLU is linear for both positive and negative inputs, and is defined by a positive slope, a negative slope, and a bias. These parameters can be learned for each channel or a block of channels, and stacking those types of activation units can further improve accuracy.

Abstract: Tasks such as object classification from image data can take advantage of a deep learning process using convolutional neural networks. These networks can include a convolutional layer followed by an activation layer, or activation unit, among other potential layers. Improved accuracy can be obtained by using a generalized linear unit (GLU) as an activation unit in such a network, where a GLU is linear for both positive and negative inputs, and is defined by a positive slope, a negative slope, and a bias. These parameters can be learned for each channel or a block of channels, and stacking those types of activation units can further improve accuracy.