Image transformation tasks such as cropping, text addition etc. are common across industries. Each industry has different business context and demands the image transformations be performed aligned to the business context. This disclosure relates to a system and method for an adaptive image transformation for a given context and maintaining aesthetic sense of the transformed image. Herein, the system is configurable and adaptive to any business context or domain. The system learns the context from available domain samples and creates an automated workflow of context-aware transformation tasks that maintains both the content and aesthetics demands of the context. Further, a saliency map is extracted for the identified RoI to append a text to the RoI based on the extracted saliency map, the calculated similarity metric for various content and aesthetic factors and various preferences of the user.

Systems and methods are disclosed for aligning a two-dimensional (2D) design image to a 2D projection image of a three-dimensional (3D) design model. One method comprises receiving a 2D design document, the 2D design document comprising a 2D design image, and receiving a 3D design file comprising a 3D design model, the 3D design model comprising one or more design elements. The method further comprises generating a 2D projection image based on the 3D design model, the 2D projection image comprising a representation of at least a portion of the one or more design elements, generating a projection barcode based on the 2D projection image, and generating a drawing barcode based on the 2D design image. The method further comprises aligning the 2D projection image and the 2D design image by comparing the projection barcode and the drawing barcode.

An apparatus comprising a memory and one or more processing circuits is provided. The memory stores a blend table having blend weights. The processing circuits, for partitions of the blend table: determine whether a subset of the pixels associated with the partition includes pixels associated with seamlines defined in a three-dimensional surface representation of the scene. If none of the subset of the pixels are associated with the seamlines, the processing circuits populate a region of the virtual image corresponding to the partition with pixel values from an image captured by one of the plurality of image capture devices. If one or more of the subsets of the pixels is associated with the seamlines, the processing circuits populate the region of the virtual image associated with the partition with blended pixel values from two or more images captured by two or more of the plurality of image capture devices.

Methods, systems, and articles of manufacture to improve image recognition searching are disclosed. In some embodiments, a first document image of a known object is used to generate one or more other document images of the same object by applying one or more techniques for synthetically generating images. The synthetically generated images correspond to different variations in conditions under which a potential query image might be captured. Extracted features from an initial image of a known object and features extracted from the one or more synthetically generated images are stored, along with their locations, as part of a common model of the known object. In other embodiments, image recognition search effectiveness is improved by transforming the location of features of multiple images of a same known object into a common coordinate system. This can enhance the accuracy of certain aspects of existing image search/recognition techniques including, for example, geometric verification.

An image photographing method is provided, including: based on a photographing instruction, selecting at least one focus in a quadrangular image, and photographing at least one initial image based on the at least one focus, where the quadrangular image includes a first pair of opposite sides and a second pair of opposite sides, an included angle between the opposite sides of the first pair of opposite sides is less than that of the second pair of opposite sides, a first side is a shorter side of the first pair of opposite sides, the at least one focus includes a first focus, and the first focus is in the quadrangular image and in a partial region including the first side; adjusting a quadrangular image to a rectangular image; and obtaining a final image and outputting the final image.

A method and apparatus are provided for generating enhanced digital imagery from digital input images (7) exhibiting differences other than or in excess of differences in projection. By applying a plurality of image transformations (10) to frequency normalised (8) versions of the input images, and generating measures of image similarity (11) therefrom, an optimum image transformation (12) can be determined that can be applied to the digital input images such that they are substantially matched. Digital input images of physical objects or environments to which the method is applied can then be used in image fusion, ortho-rectification or change detection applications, in order to monitor the physical object or environment.

According to one embodiment, an information processing apparatus includes a memory and a processor. The memory stores a background image that does not include a detection target, a detection target image that is an image of the detection target, and label information that indicates the detection target of the detection target image. The processor performs trapezoid correction on the background image, generates a composite image by superimposing the detection target image on the background image subjected to the trapezoid correction, and generates learning data based on the composite image and the label information.

An electronic apparatus and a method of controlling the electronic apparatus are provided. The electronic apparatus includes a display configured to display an image, and a controller electrically connected to the display. The controller is configured to control the display to display a region of the image, using a first reproducing method, identify either one or both of a first event in which a control signal is externally received and a second event occurring based on a result of analyzing a feature of the region of the image, and change the first reproducing method to a second reproducing method, based on either one or both of the first event and the second event being identified.

Systems and methods for use in training a convolutional neural network (CNN) for image and video transformations. The CNN is trained by adding noise to training data set images, transforming both the noisy image and the source image, and then determining the difference between the transformed noisy image and the transformed source image. The CNN is further trained by using an object classifier network and noting the node activation levels within that classifier network when transformed images (from the CNN) are classified. By iteratively adjusting the CNN to minimize a combined loss function that includes the differences between the node activation levels for the transformed references images and when transformed source are classified and the differences between the transformed noisy image and the transformed source image, the artistic style being transferred is maintained in the transformed images.

Provided are methods and devices of picture processing and user interface display. The method includes: determining at least one picture in user interface data corresponding to a user interface; storing the at least one picture to an external storage device in an electronic device; and generating an index identifier based on a storage location of the at least one image picture in the external storage device, where the index identifier is used by the electronic device to read the at least one picture in the external storage device indexed by the index identifier for displaying the user interface. The present disclosure provides a guarantee for further improving the display effect of a user interface, saves the memory space of an MCU to a large extent, and improves the user experience.