2678 results about "Grey level" patented technology

A two-dimensional image is displayed and a grey level image is drawn on said two-dimensional image defining a depth map. A stereo image pair is generated based on the depth map and an anaglyph image of the stereo image pair is displayed. Edits of the depth map are displayed by anaglyph image. A plurality of projection frames are generated based on the depth map, and interlaced and printed for viewing through a micro optical media. Optionally, a layered image is extracted from the two-dimensional image and the plurality of projection frames have an alignment correction shift to center the apparent position of the image. A measured depth map is optionally input, and a stereo pair is optionally input, with a depth map calculated based on the pair. The user selectively modifies the calculated and measured depth map, and the extracted layers, using painted grey levels. A ray trace optionally modifies the interlacing for optimization to a particular media.

This invention discloses one display method, which divides the relative original grey values into higher and lower grey values and divides the secondary pixel area into two sets in same color suitable for high and low second grey values; each set displayed grey values are computed from itself pixel and near higher grey value or lower grey value through different weigh proportion to solve the problem if different vision angles.

The invention discloses a method for using gray scale compensation to improve photo-etching exposure energy uniformity, with wide application in non-mask photo-etching machine which uses spatial light modulator as image generator. The non-mask photo-etching machine provided with a spatial light modulator as image generator uses the gray scale modulation of the spatial light modulator, according to the image light strength distribution information of photo-etching objective lens collected by a CCD to modulate the light output of each pixel unit of the spatial light modulator to change the emission light field distribution on the image plane of the photo-etching objective lens. The invention uses the light strength distribution measured in the integration of some time or uses the energy distribution of the light emitted from each image plane position in a certain exposure time to make the exposure energy of each position uniform on the image plane. The invention can effectively reduce the design and assembly hardness of the lighting system of traditional photo-etching machine and reach better exposure energy uniformity.

The invention relates to a process for the registration of two different images of the same object consisting of breaking down each of the images into space components representing the distribution of the grey levels of the image, applying a phase registration method to the components to bring about a correspondence between the components of one image with those of the other image, summating all the results of the bringing into correspondence and detecting, in the image resulting from said sum, the maximum grey level defining the transformation between the two initial images.

Provided is a haze monitoring method based on computer vision. The monitoring method includes the steps: collecting data of pre-set far and near target regions which are dark in color in a scene, and giving haze monitoring results based on comparison of the computation of target object visual features and sample images under different haze conditions. Visual features expressing an image comprises color features containing pixel color saturation mean value and blue component mean value, shape features containing feature point number and edge pixel number, textural features containing grey level co-occurrence matrix features and wavelet transform sub-band coefficients, and feature vectors expressing differences between a far target object and a near target object. According to the haze monitoring method based on computer vision, a direct measurement method by means of visual features which is closely associated to manual observation of the haze in principle is put forward, comprehensive monitoring of haze conditions in an entire region is achieved easily, and high-precision monitoring results can be guaranteed with enough sample data.

Method for detecting textural defects in an image. The image, which may have an irregular visual texture, may be received. The image may be decomposed into a plurality of subbands. The image may be portioned into a plurality of partitions. A plurality of grey-level co-occurrence matrices (GLCMs) may be determined for each partition. A plurality of second-order statistical attributes may be extracted for each GLCM. A feature vector may be constructed for each partition, where the feature vector includes the second order statistical attributes for each GLCM for the partition. Each partition may be classified based on the feature vector for the respective partition. Classification of the partitions may utilize a one-class support vector machine, and may determine if a defect is present in the image.

The invention discloses a method and system for eliminating an afterimage defect of a static-state image display area, and is applied to a self-luminous display apparatus. The static-state image display area comprises at least two sub pixels of the same type yet with different grayscale values. The method comprises: obtaining the first grayscale value of a sub pixel of a reference type corresponding to the static-state image display area, wherein the reference type is any one from RGB types, and the first grayscale value is the maximum grayscale value in the grayscale values of all the sub pixels of the reference type; according to the first grayscale value, determining a second grayscale value, the second grayscale value being greater than or equal to the first grayscale value; and driving a reference sub pixel to work continuously for corresponding reference compensation time, and closing a sub pixel whose grayscale value is equal to the second grayscale value, wherein the reference sub pixel is any one sub pixel of the reference type, whose grayscale value is smaller than the second grayscale value, and the reference compensation time is the continuous work time of the reference sub pixel. By using the technical scheme provided by the embodiments of the invention, once an image of the self-luminous display apparatus generates the afterimage defect problem, the problem can be rapidly eliminated.

The invention relates to a method for detecting surface defects of a dustproof cover of a bearing based on machine vision, which comprises the following steps: a, obtaining a gray level image of a to-be-detected bearing; b, carrying out separation on the gray level image so as to obtain a ring image of the dustproof cover of the bearing; c, carrying out grey level transformation and adaptive median filtering preprocessing on the ring image; d, carrying out threshold segmentation on the ring image by using a maximum interclass variance method, extracting an edge of the ring image of the dustproof cover of the bearing after threshold segmentation by using a Roberts edge detection operator; e, calculating the numbers of which the numerical values are 1 in the image area every two degrees for the ring image of the dustproof cover of the bearing; f, providing a template bearing image, and obtaining a deflection angle sigma through calculating; g, carrying out separation on the image so as to obtain character areas and non-character areas of the ring image of the dustproof cover of the bearing; and h, carrying out surface defect judgment on corresponding character areas and non-character areas in the ring image of the dustproof cover of the bearing according to the number of connected areas and the defect area. By using the method disclosed by the invention, automatic detection can be achieved, the visual detection workload of artificial detection is reduced, the detection efficiency is improved, and the method is safe and reliable.

The invention discloses a face recognition method and system based on a large-scale face database. The recognition method comprises the following steps: obtaining a recognition image; image preprocessing: carrying out illumination compensation, graying, filtering denoising and normalization processing on an image to be detected to obtain a high-quality grey level image; face detection: detecting and positioning a face in a scene image, and separating the face from a background; characteristic extraction and expression: describing and modeling a face mode, and expressing the face by a characteristic vector; face matching: utilizing a similarity between the characteristic vector used for calculating the face image to be detected and a training sample to obtain discrimination information; and outputting a result. The face recognition method and system based on the large-scale face database not only improves the speed and the performance of face recognition under a large-scale database. Meanwhile, the face recognition method and system can be conveniently applied to the recognition field of other modes including facial expression recognition, face tracking and the like.

A method and apparatus for detecting a joint between workpieces is provided. At least one light line is recorded by the light section method to detect the three-dimensional course of the joint and a grey-level image of the joint is also recorded. The grey-level image is evaluated to assess the quality of the joint.

The embodiment of the invention discloses a mura phenomenon compensation method of a display panel. The method comprises the steps of compressing an area interval with n*m pixels, and storing a preset mura compensation value corresponding to one of first pixels in each area; according to a compensation value of the preset mura, conducting linear interpolation calculation to obtain mura compensation values of other pixels except the first pixel in the same area, and conducting mura compensation on the display panel; after the display panel conducts the mura compensation, obtaining information that a mura phenomenon still exists in the Xth area, wherein the Xth area belongs to the area formed by compressing the area interval with n*m pixels of the display panel; obtaining a final gray-scale compensation curve formula; according to the preset mura compensation value and the final gray-scale compensation curve formula, calculating supplementary mura compensation values corresponding to other pixels except the first pixel in the Xth area; conducting mura compensation on the Xth area again. The embodiment of the invention further discloses the display panel. By adopting the mura phenomenon compensation method of display panel and the display panel, the mura phenomenon compensation method of the display panel has the advantages that nonuniform brightness of a picture of the display panel can be alleviated.

The invention provides a colorized night vision image brightness enhancement method applicable to an automotive assisted driving system. The method comprises the following steps of: firstly, transforming a night vision colorized image from a red, green and blue (RGB) space to a luma and chroma (YUV) space to overcome the shortcoming of color distortion caused by direct processing of the night vision colorized image in the RGB space; then processing a brightness component image by using an S-curve correction Retinex algorithm so as to enhance the detail and the brightness of the image; enhancing the brightness component image by a selective nonlinear grey level mapping method and keeping good shadow information; and finally, performing weighed fusion on the two enhanced images by a weighed fusion method and inversely transforming the weighed fusion brightness component image and a UV component image to the RGB space for displaying. The enhanced image acquired by the method keeps the necessary shadow information and has the detail and the brightness applicable to vision observation; and the night vision colorized image has a good enhancement effect.

Disclosed is a method of determining at least one three-dimensional (3D) geometric parameter of an imaging device. A two-dimensional (2D) target image is provided having a plurality of alignment patterns. The target image is imaged with an imaging device to form a captured image. At least one pattern of the captured image is compared with a corresponding pattern of the target image. From the comparison, the geometric parameter of the imaging device is then determined. The alignment patterns include at least one of (i) one or more patterns comprising a 2D scale and rotation invariant basis function, (ii) one or more patterns comprising a 1D scale invariant basis function, and (iii) one or more patterns having a plurality of grey levels and comprising a plurality of superimposed sinusoidal patterns, the plurality of sinusoidal patterns having a plurality of predetermined discrete orientations. Also disclosed is a two-dimensional test chart for use in testing an imaging device, the test chart comprising a plurality of alignment patterns, at least one of said alignment patterns including one of those patterns mentioned above.

The invention discloses a method and a system for improving visual angle complexion color shift of a liquid crystal display. The method is as follows: comparing gamma curves of front angles and squint angles of red, green and blue after adjustment according to initial white balanced voltage with 0-255 gray scale chrominance; and changing the partial pressure proportion of white balanced voltage of the blue according to color shift results so that color shift values of the squint angles of complexion pictures of the liquid crystal display can be within a range of specification requirements all the time. By means of the method, the color shift values of the squint angles of the complexion pictures of the liquid crystal display can be within the range of the specification requirements all the time.

The invention discloses a gender identification method and system based on a face image. The method includes the following steps that firstly, the face image is preprocessed; the face image is converted into a grey level image firstly, then a face area image is cut from the whole image according to the positions of the eyes to obtain the face area image, and finally de-noising processing is performed on the face area based on histogram equalization; secondly, a composite LBP is used for performing feature extraction, a zoom LBP is used for conducting zoom and multiple setting on the image, then a multi-scale LBP is used for dividing the face image into a plurality of areas according to different sizes of LBP histogram areas, LBP feature extraction is performed on the image and each divided area, and all LBP histogram features are combined together to serve as multi-scale LBP features of the image; thirdly, gender identification is performed based on an SVM model. According to the gender identification method and system, the gender of the face can be identified according to the face image, and the identification accuracy is improved.