33results about How to "Keep the edges" patented technology

The invention discloses an image processing method and device and electronic equipment. The image processing method comprises that edge-maintaining filtering is carried out on a first image based on an original image to obtain a filtering image; and a second image based on the original image is fused with a third image based on the filtering image to obtain a fusion image. Thus, texture details ofthe original image can be maintained to certain extent while noise is eliminated and the edges are maintained, image distortion due to the fact that a flat area is too smooth can be avoided, the fusion image approaches the reality more, and the image quality can be improved effectively.

The invention relates to a fusion method of SAR (Synthetic Aperture Radar) images and visible light images on the basis of NSCT (Non Subsampled Contourlet Transform). The fusion method is characterized by comprising the following steps of: firstly, carrying out NSCT decomposition on the SAR images and the visible light images respectively; then adopting different fusion rules to carry out fusion treatment on NSCT low-frequency and high-frequency subband coefficients, wherein according to the decomposition coefficient characteristics of noise and signals in an NSCT domain, carrying out hard-threshold denoising on the NSCT high-frequency subband coefficient of the SAR images under the maximum decomposition scale, then respectively adopting different fusion rules to carry out fusion processing on the NSCT high-frequency subband coefficient under the maximum decomposition scale and other decomposition scales by adopting the coefficients with threshold processing as the basis; and finally,carrying out NSCT reverse transformation on the fused NSCT coefficients and obtaining fused images. The fusion method takes denoising as the basis of the fusion rule design, considers noise suppression while fusion treatment is carried out, is simple and easy to operate, can be used for obtaining a good fusion effect and is especially more applicable to the SAR images and the visible light imageswith serious spot and noise pollution.

The invention relates to an image denoising method based on a Shearlet contraction and an improved TV model, wherein a TV-denoising model is improved and a novel mixed denoising method by combining the Shearlet contraction is proposed. The method organically combines the sparse representation capability of Shearlet for a high dimension function with the protection capability of the TV-denoising model for an edge, wherein the method obtains a first-denoising image through a hard threshold function contraction, and then improves fidelity terms of a total variation model, and then makes a second denoising of the false Gibbs effect of the first-denoising image by combing the improved total variation model. On the prerequisite of protecting important information such as edges, etc., the method effectively inhibits the false Gibbs oscillation caused by the Shearlet contraction, and realizes a better visual effect and a lower computation complexity.

The embodiment of the invention discloses a denoising method and a denoising device for near-infrared images. The method comprises the following steps of subjecting a to-be-processed near-infrared image to bad point identification, removing identified bad points to obtain a target image, and subjecting the target image to denoising treatment by adopting the combination of multiple spatial filters. According to the embodiments of the invention, the above near-infrared image is subjected to bad point treatment and then the image obtained after the bad point treatment is subjected to denoising treatment by adopting the combination of multiple spatial filters. In this way, not only the background noise of the near-infrared image is effectively suppressed, but also the edge and detail information of the near-infrared image is maximally preserved. The quality of the near-infrared image is improved.

The invention discloses a method for detecting impulse noise by utilizing differential images in three directions and then eliminating the image impulse noise through filtration by multiple windows. The method comprises the followings steps: (1) detecting positions of the impulse noise; (2) carrying out multiple-window self-adaptive filtration; and (3) cyclically detecting and filtering for several times. In the invention, the positions of the impulse noise are detected by utilizing the main features of the impulse noise, the impulse noise points are processed by combining the multiple-windowself-adaptive filtration, and the filtration is cyclically detected for several times so as to eliminate the impulse noise as much as possible, and image detail information is reserved. As long as animpulse noise image is input, a good filtering effect can be obtained. The invention can be used in the aspects of image restoration, reconstruction, and the like and can quickly restore the image quality.

The invention belongs to the technical field of architectural ceramics, and particularly discloses a ceramic dry granular glaze, a crystal diamond flash ceramic tile and preparation methods of the ceramic dry granular glaze and the crystal diamond flash ceramic tile. The ceramic dry granular glaze comprises the following raw materials zirconium-containing transparent frit dry granules and zircon sand, wherein a zirconium source of the zirconium-containing transparent frit dry granules is zirconium oxychloride. The crystal diamond flash ceramic tile comprises a green body layer and a cover glaze layer, wherein the cover glaze layer is formed by firing the ceramic dry granular glaze. According to the invention, the zirconium-containing transparent dry granular glaze is adopted as basic glaze, the zircon sand particles are added, and a small amount of uniformly distributed zirconium exists in the zirconium-containing transparent dry granular glaze, so that zirconium in a glaze melt is in a melting saturation state, and high-temperature melting of the added zircon sand particles in the glaze melt can be effectively prevented. Meanwhile, zirconium silicate crystals formed in the cooling process of the zirconium-containing transparent dry granular glaze take zircon sand particles as devitrification carriers, so that the zircon sand particles further grow, the crystal morphology edges and corners are clearer, and the prepared ceramic dry granular glaze can present a diamond-like flashing effect under the illumination condition.

The invention discloses a polarimetric SAR classification method on the basis of NSCT and discriminative dictionary learning and mainly solves the problems of low classification accuracy and low classification speed of an existing polarimetric SAR image classification method. The polarimetric SAR classification method comprises the following implementing steps: 1, acquiring a coherence matrix of a polarimetric SAR image to be classified and carrying out Lee filtering on the coherence matrix to obtain the de-noised coherence matrix; 2, carrying out Cloude decomposition on the de-noised coherence matrix and using three non-negative feature values of decomposition values and a scattering angle as classification features; 3, carrying out three-layer NSCT on the classification features and using a transformed low-frequency coefficient as a transform domain classification feature; 4, using the transform domain classification feature and combining a discriminative dictionary learning model to train a dictionary and a classifier; 5, using the dictionary and the classifier, which are obtained by training, to classify a test sample so as to obtain a classification result. The polarimetric SAR classification method improves classification accuracy and increases a classification speed and is suitable for image processing.

The invention provides an image denoising method based on super pixel clustering and sparse representation to solve a technical problem of a low denoised image peak signal to noise ratio and detain information loss of an existing image donoising method. The method comprises the steps of (1) inputting an image to be denoised, (2) carrying out super pixel segmentation and super pixel clustering on the image and obtaining multiple clusters of similar super pixels, (3) carrying out image block extraction and dictionary training on each cluster of similar super pixels, (4) calculating the sparse coefficient of each image block under a corresponding dictionary, (5) searching the similar image block of each image block and calculating the sparse coefficient weighted sum of similar image blocks, (6) restraining the sparse decomposition process of each image block by using the sparse coefficient weighted sum of the similar image blocks, and obtaining a new sparse coefficient, (7) judging whether a current number of iterations is larger than a maximum number of iterations Lambda or not, executing a step (8), otherwise adding 1 to the number of iterations, and executing the step (5), and (8) reconstructing the image to be denoised , and obtaining a denoised image.

The invention relates to a filtering and denoising system and a filtering and denoising method for video data. An interframe data processing module, a frame data caching module and a frame data output control module are connected to form a data path, subtraction is carried out between the previous frame data and the current frame, a result worked out by the operation is multiplied by a filtering coefficient and then added by the current frame, so that the filtered current frame data are worked out, the frame data caching module comprises a DDR2 (Double Data Rate 2) memory, and has two caches, each cache caches the data of a frame of video image, so that the invention can be adapted to the denoising of the video images of an object moving at low speed, the time-weighted average of the image signals is worked out according to the frame period, so that the image signals are almost not affected, consequently, not only can the edges in the images be kept well, but also noise can be greatly reduced, and thereby the purpose of improving the signal-to-noise ratio of the images is achieved.

The invention provides a control method, an apparatus, an imaging device, an electronic device and a readable storage medium, wherein, the method is applied to the imaging device, and the imaging device comprises a color camera and a black-and-white camera. The control method comprises the following steps of: controlling the color camera to take a color image with high dynamic range; controlling the black-and-white camera to capture the black-and-white image with low dynamic range; synthesizing the black-and-white image and the color image to obtain the target image. The method can simultaneously preserve the high dynamic range of the target image and the edge and detail of the target image so as to avoid the misplacement or blurring of the edge of the moving object and improve the shooting experience of the user.

The invention discloses a multi-modal image fusion method based on a convolution analysis operator. The method comprises the following steps of 1, decomposing a source image through fast Fourier transform, and respectively obtaining a low-frequency component and a high-frequency component; 2, fusing low-frequency components; 3, fusing high-frequency components; and 4, reconstructing an image according to the fusion structure of the low-frequency component and the fusion result of the high-frequency component. The method is advantaged in that the image features are better expressed, the reconstruction quality of the fused image is obviously improved, and an edge in the reconstructed image is better reserved.

The invention discloses an intima-media segmentation method for dual-channel intravascular ultrasound images, which comprises the following steps: 1) collecting blood vessel intima-media ultrasound images, artificially delineating intima-media boundaries, and establishing training and testing sample sets; 2) carrying out anisotropic diffusion filtering processing on the images of the training sample set; 3) superimposing the filtered new images and the original images to form a dual-channel image; 4) establishing a depth learning segmentation model, pooling the maximum neighborhood gradient, and inputting a training set for training; 5) carrying out anisotropic diffusion filtering on the image of the testing set, composing the filtered image and the original image into a dual-channel image, inputting the trained depth learn segmentation model, and segmenting to obtain the segmented blood vessel intima boundary. The method of the invention can accurately and effectively extract the blood vessel intima region.

The invention discloses a morphological attribute filtering multimode fusion imaging method, which comprises the steps of performing morphological attribute filtering operation on a to-be-fused infrared image, solving an adaptive segmentation threshold, and performing binarization to obtain an infrared image weight map; carrying out edge preserving filtering on the infrared image weight map; calculating according to the infrared image weight graph to obtain a visible light image weight graph, and respectively constructing an image pyramid for the visible light image to be fused, the infrared image to be fused, the infrared image weight graph and the visible light image weight graph; fusing the visible light image, the infrared image and the weighted image pyramid to be fused to obtain fusion, and reconstructing to obtain a final fusion result. According to the morphological attribute filtering multi-mode fusion imaging method, quick and stable multi-mode fusion imaging can be performedby utilizing an image processing means, a fusion imaging result can effectively reserve a salient target in an infrared image and edge and texture details in a visible image, Meanwhile, the morphological attribute filtering multi-mode fusion imaging method has the advantages of high calculation efficiency and good universality.

The invention relates to a video data filtering and denoising system and method; the video data filtering and denoising system is characterized in that an interframe data processing module, a frame data buffer module and a frame data output control module are connected into a data path; the data of two previous frames and the data of a current frame respectively are multiplied by filtering coefficients for obtaining sums; the obtained sums are averaged to obtain the data of the current filtered frame; the frame data buffer module is formed by a DDR2 (Double Data Rate 2) memory which is provided with three cache regions, wherein each cache region respectively caches the data of a video image of one frame, thereby being capable of adapting to the denoising of a video image of a low-speed moving object; and by carrying out temporal weighted average on the image signal according to a frame period, the edge of the image can be very well reserved with hardly any influence on an image signal, and the noise can greatly lowered, thereby achieving the purpose of improving the signal-to-noise ratio of an image.

The invention is suitable for the field of image processing, and provides a method and device for smoothening a disparity map and electronic equipment. The method comprises the following steps: initializing A(z, y), B(x, y) and F(x, y) into all-zero matrixes; acquiring all pixel points (x<k>, y<k>) satisfying S(x, y)=k in S(x, y); making A(x<k>, y<k>)=M(x<k>, y<k>), B(x<k>, y<k>)=1; computing all A(x<k>-i, y<k>-i) and T(x<k>, y<k>) taking x<k>, y<k> as a center; computing the sum of all B(x<k>-i, y<k>-i) taking x<k>, y<k> as a center to obtain the quantity T(x<k>, y<k>) of all the pixel points satisfying S(x, y); and computing F(x<k>, y<k>) according to T(x<k>, y<k>) and T(x<k>, y<k>). Through adoption of the method and device for smoothening the disparity map and the electronic equipment, the smoothness or continuity of disparity is realized, and the sudden change or discontinuity of an object edge is kept.