Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

31 results about "RGB color model" patented technology

The RGB color model is an additive color model in which red, green and blue light are added together in various ways to reproduce a broad array of colors. The name of the model comes from the initials of the three additive primary colors, red, green, and blue.

Three-dimensional human body posture estimation method and device

ActiveCN108830150AEliminate accuracy effectsAccurately obtain coordinate informationBiometric pattern recognitionNeural architecturesColor imageHuman body
The invention discloses a three-dimensional human body posture estimation method and device. The method comprises the following steps of S1, using a monocular camera to collect the depth images and the RGB color images of a human body at different angles; S2, constructing a human body skeleton key point detection nerve network based on the RGB color images, and obtaining a key point labeling image; S3, constructing hand joint node 2D-3D mapping network; S4, calibrating the depth image of the human body at the same angle and the key point labeling image, and then carrying out three-dimensionalpoint cloud color conversion on the corresponding depth image so as to obtain a colored depth image; S5, based on the key point labeling image and the colored depth image, using a preset learning network to predict the corresponding position of the labeled human body skeleton key point in the depth image; and S6, combining the outputs of the step S3 and the step S5 to achieve the refined estimation of three-dimensional human body posture estimation.
Owner:北京微链道爱科技有限公司

Automatic fast segmenting method of tumor pathological image

The invention discloses an automatic fast segmenting method of a tumor pathological image. The method comprises the following steps: firstly filtering a tumor original pathological image through the adoption of a Gaussian pyramid algorithm to respectively obtain pathological images with equal resolution, double resolution, fourfold resolution, eightfold resolution and 16-fold resolution; determining an initial region of interest containing the tumor on the equal resolution image through a RGB color model and morphological close operation; iteratively optimizing the initial regions of interest from the equal resolution to the fourfold resolution through the adoption of bhattacharyya distance; judging that the contribution of the RGB color model to the tumor region of interest has been reduced to zero when the bhattacharyya distance achieves a set threshold value; performing the self-adaptive high resolution selection of the deep precise segmentation through the adoption of a convergence exponent filtering algorithm, thereby further segmenting under the most suitable high resolution; and finally segmenting out a normal tissue and a tumor tissue in the tumor region of interest through the adoption of a bag of words model based on random projection. The method disclosed by the invention has the features of being accurate, fast and automatic.
Owner:NANTONG UNIVERSITY

Method for controlling POV display device to display images and animation

The invention provides a method for controlling a POV display device to display images and animation. The method for displaying color images comprises the following steps that firstly, a round interesting area obtained from an image represented by an RGB color model serves as an image to be displayed; secondly, the image to be displayed is modularized in the radial direction and converted into a set of data which can operate on the display device and control light-emitting intensity of LED lamps; thirdly, the data are sent to the display device in a wireless mode, the display device extracts the data, and the LED lamps are controlled to display the image to be displayed in the rotating process. By means of the method for controlling the POV display device to display the images and the animation, free wireless switching between the images and the animation can be achieved for the display device, a user can zoom the images or the animation displayed by the display device, change the display angle, the content, the hue and the like of the images or the animation, and user experience is greatly improved.
Owner:CHENGDU CHENDIAN INTELLIGENT TECH

Device and method of self-learning skin-color model based hand portion tracking

Provided are a device and a method self-learning skin-color model based hand portion tracking. The device of self-learning skin-color model based hand portion tracking comprises a preprocessing unit which is used for extracting a hand candidate area from an image in a frame and obtaining an initial hand area HINIT through a morphologic detection, a self-learning unit which is used for self-learning using the hand waiting area and the initial hand area HINIT to obtain a hand area HFINAL after self-learning of the frame, and a subsequent processing unit which is used for processing the hand area HFINAL after original frame self-learning to obtain a hand outline and finger tip positions. The self-learning unit comprises a hand tracker, a hand recognizer and a P-N learning device. The self-learning skin-color model based hand portion tracking method includes a preprocessing step, self-learning and P-N classifying steps and a subsequent processing step. The self-learning and P-N sorting step includes a hand tracking step, a hand recognizing step and a P-N learning and sorting classifying step. According to the device and the method of self-learning skin-color model based hand portion tracking, robustness is good and hand tracking is stable and accurate when a hand passes through heavy interference areas such as a face or when a hand is sheltered.
Owner:SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV

Visualization method for Munsell colour model computer

A Munsell color model computer visual method belonging to the computer color conversion and display technology field, comprises creating a Munsell color model database; converting three exciting values (x, y, Y0) of the Munsell color model database into a form of (X, Y, Z), and replacing the (x, y, Y0) data in the original database by data of the (X, Y, Z) form; selecting key color samples in an RGB color model to make an experiment color chart, adding the three exciting values (X, Y, Z) of the experiment color chart and Munsell values (H, V, C) in the database; converting the three exciting values (X, Y, Z) in the database into an RGB form, and replacing the (X, Y, Z) data in the database by data (R, G, B) in the RGB form; filtering and washing sample data of the database; educating a mapping mathematical model of the RGB model and the Munsell model; and constructing a Munsell color visual display interface. The invention is capable of accurately reproducing the Munsell color system on a computer display, with a color visual maximal error Delta Eab equal to 0.64.
Owner:SHANGHAI JIAO TONG UNIV

Method and device for detecting ripeness of fruits and vegetables

The invention discloses a method and device for detecting ripeness of fruits and vegetables. The method comprises the following steps: obtaining video information of fruits and vegetables; performing image enhancement processing on the obtained video information to improve the identification of the colors of the fruits and vegetables in the image; converting the image after the enhancement processing from a three-primary color light mode into an HSV color attribute mode to obtain the tone of the fruits and vegetables in the image; and detecting the ripeness of the fruits and vegetables in the image according to the tone of the fruits and vegetables in the image. By adoption of the method and device for detecting the ripeness of fruits and vegetables provided by the invention, since the video information of the fruits and vegetables can be processed to obtain the tone of the fruits and vegetables in the image so as to detect the ripeness of the fruits and vegetables, the accuracy of detecting the ripeness of the fruits and vegetables is improved.
Owner:CHINA AGRI UNIV

Interactive lighting effect portable light illuminating devices and system thereof

ActiveUS20170048951A1Improved and more diverse zone assignment capabilityExpand coverageElectrical apparatusElectroluminescent light sourcesControl signalControl system
Portable light illuminating device with RF receiver along with interactive lighting effect control system with RF transmitter via wireless data transmissions are provided. RF data burst are captured to illuminate LEDs disposed in portable light illuminating device selectively in accordance with illuminating color and zone assignment data and matching nested hierarchical zone codes, which can be assigned for seating location within one seating zone, several seating zones, and segment within one seating zone. Improvisational manual illuminating color control change for any zone assignment for color control signal can be generated and converted to set of RGB color codes as well as color control signals extracted from sound track using color show control software from PC / laptop can be encoded and sequenced using lighting controller to be transmitted to wireless RF transmitter for broadcasting as data burst. DMX controller and PC / Laptop can also be part of the interactive lighting effect control system.
Owner:LUMIC TECH INC

Low Profile Flexible Light Bar Tachometer

The presented invention is a low profile light bar tachometer display which includes a plurality of RGB LEDs or similar RGB color model light-emitting devices organized and arrayed in a segmented, flexible tachometer case that can be manipulated and contoured to conform to the top of the dash assembly of an automobile or any surface deemed suitable for the needs of the driver of an automobile. The lights provide a highly visible, illuminated, color changing display, so the driver can immediately assess the engine's RPM, power band, redline, or maximum torque from the change in light color or light position. The light array provides a repeatable, reliable and adjustable indication of the usable range of the engine's rpm, but does not indicate actual rpm.
Owner:STAFFANOU MATTHEW STEVENS

Method for determining mixing time of multiphase flow by using RGB color model

InactiveCN105910996AAccurately select the number of mixed uniform pixelsAccurately determineColor/spectral properties measurementsImaging processingBlend time
The invention discloses a method for determining mixing time of multiphase flow by using a RGB color model, belonging to the technical field of metallurgical energy engineering. The method determines macroscopic mixing time of multiphase flow on the basis of statistical mean square deviation, average change rate and the RGB color model for image processing and is mainly applied to chemical engineering for determination of the mixing time of multiphase flow and evaluation of mixing effect. The method is simple and convenient, has high practical value and provides a reliable and practical method for evaluation of mixing time of chemical and metallurgical stirring equipment and theoretical guidance of designing of a stirring reactor.
Owner:KUNMING UNIV OF SCI & TECH

Fast local threshold segmentation method for fruit surface defect detection

The invention discloses a fast local threshold segmentation method for fruit surface defect detection. An RGB color image of a fruit is obtained, the RGB color image of the fruit is subjected to background removal and converted into a grayscale image, a target image is formed, the target image is converted into an integral image, the integral image is used for calculation, the target image is processed to obtain a target binary image, hole filling and median filtering processes are conducted in sequence to obtain a fruit surface defect image, and according to the fruit surface defect image, a defect result is obtained. The detection method is accurate and practical and can effectively avoid brightness rectifying of the nearly spherical fruit image, the image calculation speed is high, the application range is wide, and the method had great application value.
Owner:ZHEJIANG UNIV

Iterative global adaptive image enhancement method

The invention relates to an iterative global adaptive image enhancement method, and provides the iterative global adaptive image enhancement method so as to solve the defect that an existing image enhancement method needs to set reasonable parameters manually, which is very hard to realize. The method comprises the following steps: inputting RGB color images; converting the RGB color images into HSV data; carrying out inverse gamma transformation on V-channel data of the HSV data to obtain corrected image data; with the corrected data being as an initial value of iteration, carrying out low-light gray stretching, and then, carrying out high-light gray stretching; judging whether the absolute value of the difference of iteration parameters of current iteration and previous iteration is smaller than or equal to a preset threshold value; if so, carrying out gamma correction on the result obtained through iteration, and if not, returning to the previous step for iteration continuously; and carrying out RGB transform on the result obtained after gamma correction, and displaying the enhanced image in a displayer. The iterative global adaptive image enhancement method is suitable for image enhancement tools.
Owner:HARBIN UNIV OF SCI & TECH

Method and system for processing RGB color image

The invention provides a method and system for processing an RGB color image. The method comprises: obtaining a to-be-processed RGB color image; converting the to-be-processed RGB color image into an HSL color space unit; obtaining an L channel value by using the HSL color space unit obtained by conversion and carrying out rain removing processing on the L channel value to obtain an L channel value after the rain removing processing; and restoring an HSL color space unit containing the L channel value after the rain removing processing so as to obtain an RGB color image after the rain removing processing. With the method and system, raindrop removing on the RGB color image is realized.
Owner:SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI

Broken line graph broken line segmentation method and device

The invention relates to a broken line graph broken line segmentation method and device; the method comprises the following steps: c, converting a RGB color model of a broken line graph of N detectedlegends into a LAB space model, respectively obtaining a LAB value of each legend in the broken line graph and a LAB value of each pixel in the broken line graph; d, carrying out Euclidean distance calculation for the LAB value of each legend in the broken line graph and the LAB value of each pixel in the broken line graph, thus forming N aberration distribution maps, wherein one legend is matchedwith one aberration distribution map ; finding the minimum value in each aberration distribution map, setting a segmentation threshold according to the minimum value, and segmenting a rough broken line corresponding to the aberration distribution map in the aberration distribution map according to the segmentation threshold. The method and device can provide a simple and effective solution for the broken line segmentation problem, thus using the shortest program operation time to realize the best effect of a segmentation result.
Owner:ABC FINTECH CO LTD

Method for eliminating highlighter marks in digital text image

The invention relates to a method for eliminating highlighter marks in a digital text image. The method comprises the steps of carrying out comparative analysis on RGB color model three-primary color constituents of the image of a black-and-white character electronic document and common highlighter marks, selecting a maximum component value of three color component values of a pixel and outputting the maximum component value as the gray value of the pixel, converting a gray text image file with the highlighter marks into a text image file with the highlighter marks eliminated, and finally obtaining a black-and-white text image file with the highlighter marks eliminated. Therefore, the highlighter marks in the document are eliminated fast and effectively.
Owner:HUAQIAO UNIVERSITY

Method for forming pseudo-color image from 16-bit data

The invention discloses a method for forming a pseudo-color image from 16bit data, which comprises the following steps: firstly, constructing an RGB color model cube, and constructing a spiral curve in the RGB color model cube; then, a fourth-dimensional channel A is added, and a mapping function is constructed; and finally, performing color mapping on the 16-bit data according to the mapping function obtained in the step 2, and performing channel fusion to obtain a pseudo-color image. According to the method, the data is converted into the pseudo-color image, observation is easy, abnormal information of the data can be clearly obtained, the method is applied to the field of X-ray nondestructive testing and the like, the digital matrix is converted into the image, and the abrasion positionis rapidly and accurately obtained.
Owner:XIAN UNIV OF TECH

DEM data color matching and drawing method and device

InactiveCN103544735AAvoid the problem of color confusion and unsightly drawingImprove visual effects3D modellingColor wheelVisual perception
The invention provides a DEM data color matching and drawing method and device. The method comprises the steps of acquiring the elevation values of all pixel points in DEM data, determining an h value, an s value and a v value of the current pixel point according to the correspondence between the elevation value and the preset elevation value of the current pixel point and an HSV color wheel, calculating a red R value, a green G value and a blue B value of a RGB color model of the current pixel point according to the determined h value, the determined s value and the determined v value, using the calculated R value, the calculated G value and the calculated B value as the color matching values of the current pixel point and drawing the DEM data according to the color matching values of each pixel point. By means of the DEM data color matching and drawing method and device, a drawing vision effect is enhanced, and user experience is improved.
Owner:浙江数维科技有限公司

RGBY-based shadow elimination method

The invention discloses an RGBY-based shadow elimination method. Firstly, background difference of a gray Y channel and a high threshold of a sampling threshold method in a fixed background are used for extracting a rough moving target and a shadow thereof; in combination with a gray low threshold and an RGB color model, Gaussian blur is carried out on an RGB channel in a light spot extracted by the high threshold; and recursive integral processing is then carried out, and RGB after integral processing is converted into a Y signal. According to the shadow elimination method provided by the invention, the performance is excellent; the adaptability is strong; the shadow part in a contour of the moving object extracted in the fixed background can be quickly and accurately eliminated in various conditions; influences from the shadow are eliminated; and thus, the coordinate precision of the moving object in the fixed background is improved.
Owner:国网吉林省电力有限公司延边供电公司 +1

Method and device for acquiring oily region in face image

The invention belongs to the technical field of image processing, and specifically discloses a method and a device for acquiring an oily region in a face image. The method comprises the following steps of: carrying out fuzzy processing on the obtained first image containing a human face to obtain a second image which is blurred, and identifying a skin color region of the human face in the first image based on pixel parameters of the first image and the second image under an RGB color model; and secondly, calculating and acquiring a highlight region in the skin color region, and determining that the highlight region is the target oily region in the first image. According to the method, the oily region in the portrait image is effectively identified, the highlight region in the background cannot be mistakenly recognized as the oily region, the implementation process of the method is simple, complex calculation is not needed, and the method has wide application prospects.
Owner:CHENDU PINGUO TECH

Image processing method and mobile terminal

The invention provides an image processing method and a mobile terminal, and relates to the technical field of communication. The method comprises the steps of acquiring a three-primary color model image; performing normalization processing on the three-primary color model image to acquire brightness channel data, chroma channel data and concentration channel data; separately computing the brightness channel data, the chroma channel data and the concentration channel data in parallel, and combining computing results to acquire an output image. According to the method provided by the invention,image processing performance and effect are enhanced, and thus the processing speed of the mobile terminal is improved, and power consumption of the mobile terminal is reduced.
Owner:VIVO MOBILE COMM CO LTD

Foreign matter detection method and system based on yellow foreign matter defects

The invention relates to the technical field of image processing, in particular to a foreign matter detection method and system based on yellow foreign matter defects. The method comprises the following steps: image acquisition: photographing a detected object by using an industrial camera to generate a to-be-detected image; calculating suspicious defects: sequentially extracting R, G and B color component values of each pixel point in the to-be-detected image through an RGB color model, and calculating the suspicious defects by using a suspicious defect calculation model according to the R, G and B color component values; judging a foreign matter point: judging the distribution condition of the suspicious defects through a foreign matter point judgment model, and marking the suspicious defects meeting the foreign matter point judgment model as foreign matter points; performing foreign matter point feedback: when the foreign matter point is judged to appear, sending out foreign matter point information; and performing foreign matter prompting: prompting personnel according to the foreign matter point information. The invention aims to provide the foreign matter detection method and system based on the yellow foreign matter defects aiming at the defects in the prior art, so the production efficiency is improved.
Owner:NEWTRY COMPOSITE

A foreign object detection method and system based on yellow foreign object defects

The present invention relates to the technical field of image processing, in particular to a foreign object detection method and system based on yellow foreign object defects; the method includes image acquisition: using an industrial camera to take pictures of the detected object to generate an image to be detected; suspicious defect calculation: sequentially through the RGB color model Extract the R, G, and B color component values ​​of each pixel in the image to be detected, and use the suspicious defect calculation model to calculate suspicious defects according to the R, G, and B color component values; The distribution of defects is judged, and the suspicious defects that meet the foreign object point judgment model are marked as foreign object points; foreign object point feedback: when it is judged that there are foreign object points, foreign object point information is sent; foreign object prompt: according to the foreign object point information, personnel hint. The object of the present invention is to provide a foreign matter detection method and system based on yellow foreign matter defects to improve production efficiency.
Owner:NEWTRY COMPOSITE

Method and system for measuring monocular line-of-sight range of wearable glasses based on logo

The invention discloses a wearable glasses monocular visibility range measuring method and system based on identifiers. The wearable glasses monocular visibility range measuring method and system comprises a pure color identifier set, a position setting device, a visibility range application server and wearable glasses. Each pure color identifier of the pure color identifier set is printed through one RGB color, and the back faces of the pure color identifiers are printed with RGB color codes. A user of the position setting device reads the RGB color codes on the back faces of the pure color identifiers at any indoor position, the pure color identifiers are pasted on the ground or a wall, and the coordinates of the pure color identifiers on the ground or the wall are associated with the RGB color codes, and transmitted to the visibility range application server. The wearable glasses are used for transmitting data to the visibility range application server, and receiving information of the visibility range application server. The visibility range application server comprises a service control device and an indoor image device and is used for sending corresponding messages to the user of the wearable glasses according to scenes and figures within the visibility range after the visibility range is obtained.
Owner:泰州祥云软件开发有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products