A system capable of determining which recognition algorithms should be applied to regions of interest within digital representations is presented. A preprocessing module utilizes one or more feature identification algorithms to determine regions of interest based on feature density. The preprocessing modules leverages the feature density signature for each region to determine which of a plurality of diverse recognition modules should operate on the region of interest. A specific embodiment that focuses on structured documents is also presented. Further, the disclosed approach can be enhanced by addition of an object classifier that classifies types of objects found in the regions of interest.

The present disclosure relates to an image processing method and apparatus, an electronic device and a storage medium. The method includes performing feature extraction on an image to be processed to obtain a first feature map of the image to be processed and performing weight prediction on the first feature map to obtain a weight feature map of the first feature map. The weight feature map includes weight values of feature points in the first feature map. The method further includes performing feature value adjustment on the feature points in the first feature map based on the weight feature map to obtain a second feature map and determining a processing result of the image to be processed according to the second feature map. Embodiments of the present disclosure may improve the image processing accuracy.

The present disclosure relates to an image processing method and apparatus, an electronic device and a storage medium. The method includes performing feature extraction on an image to be processed to obtain a first feature map of the image to be processed and performing weight prediction on the first feature map to obtain a weight feature map of the first feature map. The weight feature map includes weight values of feature points in the first feature map. The method further includes performing feature value adjustment on the feature points in the first feature map based on the weight feature map to obtain a second feature map and determining a processing result of the image to be processed according to the second feature map. Embodiments of the present disclosure may improve the image processing accuracy.

An apparatus and method configured to parameterise an image indicating friction skin ridges, the apparatus comprising means for: obtaining a first biometric parameter indicative of a group characteristic of a plurality of the friction ridges; obtaining a second biometric parameter indicative of one or more individual characteristics of one or more individual friction ridges of the plurality of friction ridges; and determining a third biometric parameter dependent on the first biometric parameter and dependent on the second biometric parameter. The first biometric parameter comprises a circular variance field indicative of variation of directions of the plurality of friction ridges. There is also provided a matching apparatus and method.

A method and system for detecting the presence or absence of a target or desired object within a three-dimensional (3D) image. The 3D image is processed to extract one or more 3D feature representations, each of which is then dimensionally reduced into one or more two-dimensional (2D) feature representations. An object detection process is then performed on the 2D features map(s) to generate information about at least the presence or absence of an object within the 2D feature representations, and thereby the overall 3D image.

A method and system for detecting the presence or absence of a target or desired object within a three-dimensional (3D) image. The 3D image is processed to extract one or more 3D feature representations, each of which is then dimensionally reduced into one or more two-dimensional (2D) feature representations. An object detection process is then performed on the 2D features map(s) to generate information about at least the presence or absence of an object within the 2D feature representations, and thereby the overall 3D image.

Technologies for guiding an agricultural vehicle through crop rows using a camera and signal processing to locate the crop row or centers of the crop row. The signal processing uses a filter to filter data from images captured by the camera and locates the row or the centers based on the filtered data. The filter is generated based on a signal processing transform and an initial image of the crop row captured by the camera. The filter is applied to subsequent images of the crop row captured by the camera. In some embodiments, the camera includes one lens. For example, monocular computer vision is used in some embodiments. Also, in some embodiments, a central processing unit generates the filter based on the transform and the initial image of the crop row and applies the generated filter to the subsequent images of the row.

Images of optical codes are mapped to an overview image to localize optical codes within a space. By localizing optical codes, information about locations of various products can be ascertained. One or more techniques can be used to map the images of optical codes to the overview image. The overview image can be a composite image formed by stitching together several images.

The present invention discloses a scene recognition method, a training method and a device based on pyramid attention, belonging to the field of computer vision. The method includes: pyramid layering a color feature map and a depth feature map respectively, calculating the corresponding attention map of each layer; taking the output of the attention of the last layer as the output; taking the attention output of the last layer as the final feature map, for the remaining layers, adding the result after upsampling of the final feature map of an upper layer to the attention output of this layer as the final feature map of this layer; scaling the attention map and the final feature map, using the average of two new attention maps as the final attention map, mapping the largest k position in the final attention map to the final feature map of this layer.

The present invention discloses a scene recognition method, a training method and a device based on pyramid attention, belonging to the field of computer vision. The method includes: pyramid layering a color feature map and a depth feature map respectively, calculating the corresponding attention map of each layer; taking the output of the attention of the last layer as the output; taking the attention output of the last layer as the final feature map, for the remaining layers, adding the result after upsampling of the final feature map of an upper layer to the attention output of this layer as the final feature map of this layer; scaling the attention map and the final feature map, using the average of two new attention maps as the final attention map, mapping the largest k position in the final attention map to the final feature map of this layer.