Disclosed are an image processing method and apparatus, a computer device and a storage medium, which relate to the field of artificial Intelligence. The method includes receiving an original image; performing image photographing defect detection and color deviation detection on the original image, the image photographing defect detection determining whether there exists a photographing defect that is irreparable through image processing, the color deviation detection determining whether there exists color cast in the original image; performing color correction on the original image if the original image passes the image photographing defect detection and does not pass the color deviation detection; and generating a target image based on the color-corrected original image.

This disclosure describes systems and methods for training a neural network with a training data set including data items labeled at different granularities. During training, each item within the training data set can be fed through the neural network. For items with labels of a higher granularity, weights of the network can be adjusted based on a comparison between the output of the network and the label of the item. For items with labels of a lower granularity, an output of the network can be fed through a conversion function that convers the output from the higher granularity to the lower granularity. The weights of the network can then be adjusted based on a comparison between the converted output and the label of the item.

This disclosure describes systems and methods for training a neural network with a training data set including data items labeled at different granularities. During training, each item within the training data set can be fed through the neural network. For items with labels of a higher granularity, weights of the network can be adjusted based on a comparison between the output of the network and the label of the item. For items with labels of a lower granularity, an output of the network can be fed through a conversion function that convers the output from the higher granularity to the lower granularity. The weights of the network can then be adjusted based on a comparison between the converted output and the label of the item.

An information processing apparatus extracts colors used for an image, links each color to one of color groups including a first color group and a second color group, displays, in a first region of a UI, a representative color associated with a group, of the color groups, to which extracted color is linked, displays a color palette including one color in a second region of the UI, and replaces a color included in the image and belonging to the color group associated with the selected representative color with a color selected from the color palette. If the color groups include groups to which at least one extracted color is linked, representative colors respectively associated with the groups to which at least one of the extracted colors is linked are displayed in the first region.

An information processing apparatus extracts colors used for an image, links each color to one of color groups including a first color group and a second color group, displays, in a first region of a UI, a representative color associated with a group, of the color groups, to which extracted color is linked, displays a color palette including one color in a second region of the UI, and replaces a color included in the image and belonging to the color group associated with the selected representative color with a color selected from the color palette. If the color groups include groups to which at least one extracted color is linked, representative colors respectively associated with the groups to which at least one of the extracted colors is linked are displayed in the first region.

A method and apparatus may be used for performing a scene-based automatic white balance correction. The method may include obtaining an input image. The method may include obtaining a raw image thumbnail. The method may include obtaining an augmented image thumbnail. The method may include computing a histogram from an image thumbnail. The method may include determining a scene classification. The method may include learning a filter. The filter may be learned from one or several different instances of the raw image thumbnail, the augmented image thumbnail, the scene classification, or any combination thereof. The method may include applying the filter to the histogram to determine white balance correction coefficients and obtain a processed image.

A method and apparatus may be used for performing a scene-based automatic white balance correction. The method may include obtaining an input image. The method may include obtaining a raw image thumbnail. The method may include obtaining an augmented image thumbnail. The method may include computing a histogram from an image thumbnail. The method may include determining a scene classification. The method may include learning a filter. The filter may be learned from one or several different instances of the raw image thumbnail, the augmented image thumbnail, the scene classification, or any combination thereof. The method may include applying the filter to the histogram to determine white balance correction coefficients and obtain a processed image.

Systems and methods for the detection and analysis of road markings and other road objects are described. A method for detection of road markings comprises identifying image data including lane markings associated with a road segment, defining a plurality of subsections for the road segment, identifying boundary recognition observations for the lane markings from the image data corresponding to the at least one of the plurality of subsections for the road segments, calculating one or more clusters for the boundary recognition observations according to color or intensity, and outputting a lane marking indicator indicating the color or the intensity, for the at least one of the plurality of subsections for the road segments, in response to the one or more clusters.

Systems and methods for the detection and analysis of road markings and other road objects are described. A method for detection of road markings comprises identifying image data including lane markings associated with a road segment, defining a plurality of subsections for the road segment, identifying boundary recognition observations for the lane markings from the image data corresponding to the at least one of the plurality of subsections for the road segments, calculating one or more clusters for the boundary recognition observations according to color or intensity, and outputting a lane marking indicator indicating the color or the intensity, for the at least one of the plurality of subsections for the road segments, in response to the one or more clusters.

Image data of a light source comprising a surface is obtained using an optical sensor. The surface includes a color band code comprising an array of color regions at least partially modifying visible light of the light source prior to the light impinging the optical sensor. One or more characteristics of the color band code are determined based on the image data that is obtained. Determining a unique identity of the light source based on the determined one or more characteristics of the color band code is performed, or determining a location within a structure associated with the light source based on the determined one or more characteristics of the color band code is performed.