5 results about "Source image" patented technology

The invention relates to the technical field of image processing and discloses an image fusion method and a device, and the method comprises the following steps: inputting source images to be fused; respectively carrying out block division treatment on all the source images, and generating block-shaped image matrixes which correspond to the source images; calculating a fusion coefficient matrix of all the block-shaped images in all the source images, carrying out interpolation treatment on the fusion coefficient matrix of all the block-shaped images through the cubic convolution interpolation method, and obtaining the fusion coefficient matrix which corresponds to the source images; and carrying out weighted fusion on the source images by utilizing the fusion coefficient matrix of the source images and generating an image after fusion. The utilization of the invention can lead the image after the fusion to fully reflect the respective main information of all the source images.

The invention provides an image feature extraction system and method based on Talbot effect optical convolution. An optical convolution image processing system is composed of an optical system, a laminated grating, a time-sharing switching system and a detector. The optical system comprises an objective lens, an ocular lens system and a source image and is used for realizing conjugate reduction imaging of an object image. The laminated grating system can generate a Talbot self-imaging effect on a grating Talbot distance, and then optical convolution processing can be carried out on an incidentlight field by utilizing a Moire fringe effect. The time-sharing switching system can realize time-sharing switching of gratings with different periods and different phases, thereby realizing opticalconvolution operation with different convolution parameters and extracting different incident image features. According to the method, image processing is carried out by using optical convolution, sothat the calculation energy consumption can be obviously reduced and the calculation time is saved. According to the scheme, the structure system is compact, and operations such as image filtering can be performed by effectively utilizing optical convolution.

The invention discloses a photo angle correction method based on digital image processing. The photo angle correction method comprises the following steps: inputting a source image; inputting four control points of a quadrilateral region needing angle correction into the source image; extracting an area needing to be corrected from the source image; deriving a projection transformation formula based on a central projection transformation principle; finding original image pixel point coordinates corresponding to the new image pixel point coordinates according to the transformation parameters; assigning a value to the new graph through nearest neighbor interpolation; and outputting corrected images. According to the invention, the quadrilateral area can be quickly and effectively projected into the rectangular area for angle correction of the image.

The invention provides a static gesture recognition method based on wavelet transform low-frequency information and an Xception network. The method comprises the steps of: obtaining a static gesture source image and a preset type label, and forming a sample training set; extracting low-frequency information of the static gesture source image; establishing an Xception network model which comprises an input layer, a middle layer and an output layer; with the low-frequency information of the static gesture source image used as input of the input layer, circularly processing an output result of the input layer for eight times through the middle layer, and finally outputting the result through the output layer; based on the output result of the Xception network model and the preset type label, training the Xception network model to obtain a trained static gesture recognition model; and finally, for a to-be-recognized static gesture source image, extracting the low-frequency information of the static gesture source image through the step S2, and taking the low-frequency information as the input of the trained static gesture recognition model to obtain a recognition result.