605 results about "Color transformation" patented technology

The invention discloses a pavement crack detection method based on a Yolov8 model, and belongs to the technical field of crack detection. Comprising the following steps: constructing a pavement crack segmentation data set: acquiring a road crack image through an unmanned aerial vehicle, performing data enhancement processing of geometric transformation and color transformation on the image in combination with a public data set, performing Gaussian filtering denoising on a noise image, and performing crack labeling by using Label; based on a YOLOv8-Seg model, improvement is carried out by introducing a PKIblock multi-scale convolution kernel, generalizing an efficient layer aggregation network GELAN module, an EMA attention mechanism and replacing a spatial pyramid pooling layer SPPF into a SimSPPF, and a road crack recognition model YOLOv8-RCI is constructed; and performing crack detection and instance segmentation on the unmanned aerial vehicle image by using the trained YOLOv8-RCI model, and outputting a crack position and mask information. Through the improvement in the four aspects, the detection segmentation performance of the model is improved, and the model meets the requirement of real-time detection.

An information processing apparatus includes an obtaining unit which obtains first color information from an image that includes a pixel representing color information of a first color and a pixel representing color information of a second color. A determination unit determines whether the obtained first color information includes second color information. A conversion unit executes first color conversion processing on the image. A correction unit, in a case where a color difference between the third color and the fourth color is less than a predetermined threshold, corrects a conversion parameter in the first color conversion processing such that a color obtained by converting the first color is a seventh color which is different from the third color and whose color difference from the fourth color is greater than the color difference between the third color and the fourth color.

The invention provides a flow velocity identification method and device based on an improved U-Net network model, and belongs to the technical field of flow velocity measurement, and the method comprises the steps: carrying out the sampling of collected river image data, and obtaining the sampling image data; randomly cutting the sampling image data according to a preset size to obtain a cut image; performing color transformation on the cut image according to a preset random probability to obtain an image sequence, the color transformation including at least one of luminosity transformation, contrast transformation, saturation transformation and tone transformation; and inputting the image sequence into an improved U-Net network model to carry out flow velocity identification so as to obtain a flow velocity prediction result of the river channel. According to the flow velocity identification method based on the improved U-Net network model, the time sequence information and the texture information of the river channel video frame are extracted through the improved U-Net network model, and then the corresponding flow velocity value is output, so that the identification precision and the identification efficiency of the flow velocity can be improved.

The invention provides an image defogging enhancement and intelligent perception collaborative optimization method based on stream matching, and the method comprises the steps: obtaining a foggy input image, and constructing an ordinary differential equation for defining image transformation; the input image is input into a fog perception vector field, the fog perception vector field comprises an atmospheric scattering purifier and a defogging perception color lookup table, and the atmospheric scattering purifier is used for extracting multi-scale features from the foggy input image to generate clearer output; the defogging perception color lookup table adaptively adjusts the image color through a nonlinear color transformation mechanism; and solving the ordinary differential equation through an RK4 solver, iteratively updating the foggy input image at each time step, and ensuring that the input image can be stably converted into a clear image from an initial foggy state. The technical problems that in the prior art, the existing method is forced to reduce the model capacity due to the calculation efficiency constraint in the ultra-high-definition image defogging, so that the fog concentration estimation is incomplete, and the perception quality and the calculation efficiency cannot be considered at the same time are solved.

The invention discloses a figure scene generation system based on AI interaction. The figure scene generation system comprises a user interaction design module, a figure image shooting module, a figure image analysis and processing module, a figure image processing module, an image integration and correction module, an image generation module and a management database. The figure image shooting module is used for acquiring a user image and a microstructure of a skin surface by using a high-definition camera, the microstructure comprises a skin glossiness reference value, a wrinkle level reference value, pore characteristics and pigmentation, and the user image contains a hair coverage rate; according to the method, an algorithm is used for calculating pore features, color conversion is carried out on a microstructure to obtain pigmentation, a user age evaluation correlation coefficient is obtained through calculation of skin glossiness, a wrinkle level, the pore features, the pigmentation and a hair coverage rate, and a more accurate age evaluation result is provided by improving an age prediction method. The features of skin texture, pigmentation and the like can be quantified more accurately, so that the accuracy of age assessment is improved.

An image processor for a medical observation device includes a color conversion function, The image processor is configured to retrieve an input pixel of a digital input color image and a location of the input pixel in the input color image, and apply the color conversion function to the input pixel to generate an output pixel in a digital output color image. The color conversion function depends on the location of the input pixel.

An imaging device includes: an imaging sensor configured to capture a subject image to generate image data; a storage configured to store a plurality of color conversion data each defining a corresponding relationship between color information of an image before and after color conversion; an output unit configured to output a live view screen based on the image data; an operation unit configured to receive a user operation; and a controller configured to designate first color conversion data and second color conversion data from the plurality of color conversion data, in accordance with the user operation. The live view screen presents a live view image resultant of image processing of applying the first color conversion data and the second color conversion data to the image data.

Provided are a color converting substrate and a display device including same. The color converting substrate includes: a base portion in which a first light transmission area, a first light blocking area, and a second light transmission area, which are sequentially and closely arranged in a first direction, are defined; a first wavelength converting pattern located on the base portion and configured to wavelength-covert a first color light into a second color light; a second wavelength converting pattern located on the base portion and configured to wavelength-convert the first color light into a third color light; and a light transmission pattern located on the base portion and configured to transmit the first color light.

There is provided with an information processing apparatus. A first obtaining unit obtains first color information from a first image, which includes a pixel representing color information of a first color defined in a first color gamut and a pixel representing color information of a second color defined in the first color gamut. A first correction unit, in a case where a color difference between a third color defined in a second color gamut and a fourth color defined in the second color gamut is less than a predetermined threshold, corrects a first conversion parameter for the color conversion processing such that a color obtained by converting the first color is a fifth color. A conversion unit performs color conversion processing in which the corrected first conversion parameter is used on a second image different from the first image.

Aspects of hair simulation, hair classification, and networks therefor including aspects to train such networks are provided. A classifier model alleviate the impact of human bias where the modeling of the real label distribution and annotators' biases are separated by incorporating annotator confusion matrices into a baseline model. The model was trained using a consistency-based semi-supervised learning framework. With the use of only 1000 labeled data, the final classifier model achieved a classification accuracy that was 20% higher than a human professional annotator. The model is useful as a color classifier to train generative models for hair color translation. There is provided a generative model for hair simulation (e.g. via VTO) that is guided during training by a hair classifier model. Further provided is a color mapping network to process an input image and target hair color for the generative model to define the hair simulation.

A color conversion substrate includes: a base part in which a first light-transmitting area and a second light-transmitting area are defined; a first stack disposed on the base part and a second stack disposed on the first stack; a first wavelength conversion pattern overlapping the second light-transmitting area, and disposed on the second stack, where the first wavelength conversion pattern converts light of a first color into light of a second color; and a light-transmitting pattern overlapping the first light-transmitting area and disposed between the first stack and the second stack, where portions of the first stack and the second stack in the second light-transmitting area are in direct contact with each other to constitute a blue light reflective layer.

Devices having a reflective geometry are provided. The device includes a color conversion layer including luminescent material. The color conversion layer having a first side and a second side and a substrate having a first side and a second side. The second side of the color conversion layer located on the first side of the substrate. The device including an LED light source located remotely from the color conversion layer where the LED light source is optically coupled and / or radiationally connected to the first side of the color conversion layer. The device includes at least one of: (a) the substrate has a reflectivity of at least 20%, (b) a reflective layer located between the substrate and the color conversion layer, or (c) a back reflective layer located on the second side of the substrate. The devices are especially useful for lighting and display applications. Articles including the device are also provided.

Methods for actively managing remnant voltage on backplane electrodes when driving an electrophoretic display, especially with short waveforms, such as used for scrolling, pinch-zoom, pulldown menus, and even video. The methods track the remnant voltage changes for each backplane electrode during a series of image updates and use same color transitions to either improve the optical quality state of the display pixel or to decrease the remnant voltage at the display pixel. Thus, it is not necessary to employ full reset pulses, which typically drive a backplane electrode to both extreme voltage states and appear very “flashy” to a user.

A display device includes: a substrate that includes first to third light emitting areas and a light blocking area that surrounds the first to third light emitting areas; a light emitting layer that includes first to third light emitting layers disposed in the first to third light emitting areas, respectively; and a color conversion layer that includes a first bank disposed in the first light emitting area on the light emitting layer, overlaps an edge of the first light emitting layer, and includes a first opening that exposes a central portion of the first light emitting layer, a second bank disposed in the light blocking area on the light emitting layer, contacts a side surface of the first bank, and includes a material different from the first bank, and a first color conversion pattern disposed inside the first opening.

A display device according to an embodiment includes a display panel, and a color conversion layer disposed on the display panel, wherein the color conversion layer includes a quantum dot and a scatterer, the scatterer includes a first particle having a first diameter, and the first diameter is from about 100 nm to about 180 nm.

The invention discloses a non-contact heart rate estimation method and system based on multi-modal signal fusion, and relates to the technical field of image processing, and the method comprises the steps: positioning a region of interest in a face video, extracting HSV and Lab color space signals, and fusing the HSV and Lab color space signals; suppressing ambient light interference through background brightness compensation to obtain a color conversion signal and normalizing the color conversion signal; adjusting the bandwidth filtering signal of a band-pass filter by using the historical heart rate to generate an rPPG signal; performing time domain and frequency domain analysis on the rPPG signal, and performing weighted averaging by combining two results to obtain a heart rate estimation value; a historical data smoothing strategy is adopted to correct a heart rate estimation result to ensure accuracy. According to the method, high-precision non-contact heart rate estimation is realized through extraction and fusion of HSV and Lab color space signals, background brightness compensation, signal normalization and processing of human face video signals based on a historical heart rate adjustment band-pass filter.

To provide an image processing apparatus that appropriately executes settings of a color conversion method and application of the set color conversion method to image data.SOLUTION: An image processing apparatus comprises: area setting means that sets, on an image represented by input image data, a first area used for settings of a color conversion method for image data, and a second area not used for the settings of the color conversion method; color conversion method setting means that, when the first area and the second area are included on the image as a result of the settings performed by the area setting means, sets the color conversion method on the basis of the image data of the first area set by the area setting means; and generation means that determines the color conversion method set by the color conversion setting means, as a color conversion method to be applied to an area including the first area and at least part of the second area on the image, and generates image data after the color conversion by using the determined color conversion method.SELECTED DRAWING: Figure 3

A method for processing image data may include: obtaining a raw input image that is captured under an input illumination; obtaining a target illumination from a user input; obtaining an intermediate image having colors captured under a reference illumination, from the raw input image, based on a first color transform that maps the input illumination to the reference illumination in an illumination dataset of raw sensor images that are captured under a plurality of different illuminations; and obtaining an output image having colors captured under the target illumination, from the intermediate image, based on a second color transform that maps the reference illumination in the illumination dataset to the target illumination.

The invention discloses a defect detection method and system based on image processing and deep learning, and relates to the field of laser welding image processing, and the method comprises the following steps: obtaining a first image, and obtaining a second image based on convolution operation and hierarchical aggregation recognition of context features and shadow removal in the first image; converting the source color of the second image into a target color to obtain a third image; eliminating light influencing feature extraction on the basis of separating and processing the illumination component and the reflection component of the third image, and obtaining a fourth image; based on histogram equalization, converting the fourth image into an RGB channel, and obtaining a fifth image; positioning the defect position of the fifth image based on a ResNet and Unet hybrid network; environmental factors influencing image defect detection are processed through shadow removal, color neutralization, brightness neutralization and contrast enhancement, defect detection is performed by using a deep learning network, and the influence of a complex environment on a detection effect is solved.

A display device can include a substrate on which a plurality of subpixels are defined, a plurality of light-emitting elements at least one of which is disposed in a corresponding subpixel of the plurality of subpixels on the substrate, and a plurality of color conversion blocks disposed on at least one light-emitting element among the plurality of light-emitting elements and configured to convert a wavelength of light emitted from the at least one light-emitting element. The plurality of color conversion blocks include a plurality of color conversion particles, a plurality of magnetic particles, and a dielectric material configured to surround the plurality of color conversion particles and the plurality of magnetic particles. Therefore, it is possible to enhance the light emitting efficiency and the color uniformity for each subpixel.

An ink composition includes a plurality of quantum dots, a liquid monomer, an initiator, and optionally an organic solvent, wherein the plurality of quantum dots includes: a first quantum dot including a first ligand, and a second quantum dot including a second ligand different from the first ligand, and the ink composition is configured to emit a first light.

The invention discloses a data enhancement method, a training method and a system for a target detection model. The data enhancement method comprises the following steps: for a target image marked with a target object bounding box, generating a mask image corresponding to the target image by using a semantic segmentation model so as to separate a foreground region from a background region in the target image; based on the mask image, a first image used for representing the foreground area is extracted from the target image, color conversion processing is performed on the first image to obtain a plurality of second images, and each second image is used for representing the foreground area and has a color attribute different from that of the first image; respectively generating corresponding enhanced images based on the plurality of second images, and adding the target image and the plurality of enhanced images into a training data set for training a target detection model; wherein each enhanced image in the plurality of enhanced images is correspondingly provided with a target object bounding box consistent with the target image. In this way, the recognition capability of the model on samples without colors is enhanced.

A setting unit sets a first partial area and a second partial area in a first image. A conversion unit, in a case where the first image is determined to be an image obtained by scanning the printed image, executes color conversion processing for converting a first color, which is included in the first image and is defined by a first color gamut, into a second color, which is defined by a second color gamut. A first correction unit corrects a conversion parameter in the color conversion processing such that a color obtained by converting the first color is a color different from the second color. The first correction unit corrects, for the first partial area, the conversion parameter and corrects, for the second partial area, the conversion parameter.

Aspects of hair classification, and networks therefor are provided including aspects to train such networks. There is provided a classifier model to alleviate the impact of human bias where the modeling of the real label distribution and annotators' biases are separated by incorporating annotator confusion matrices into a baseline model. To further improve the model performance leveraging unlabeled data, the model was trained using a consistency-based semi-supervised learning framework. With the use of only 1000 labeled data, the final classifier model achieved a classification accuracy that was 20% higher than a human professional annotator. The trained model can be used for a wide range of downstream tasks, including being used as a color classifier to train generative models for hair color translation.

The invention relates to efficient color conversion using multiple lookup tables. Disclosed are systems and techniques for efficient color conversion. The techniques include receiving a first lookup table (LUT), a corresponding first range, a second LUT, and a corresponding second range. The first range is smaller than the second range. The techniques include receiving first color data of a first color space from a first computer system component. The techniques include, in response to determining that the first color data is within a first range corresponding to the first LUT, converting the first color data of the first color space to second color data of a second color space using the first LUT. The techniques include providing second color data of a second color space to a second computer system component.

A display device includes a light-emitting substrate, a counter substrate, multiple color conversion layers and, a patterned distributed Bragg reflector. The counter substrate is disposed opposite to the light-emitting substrate, and has multiple sub-pixel regions. Each of the sub-pixel regions has a sub-pixel width. The color conversion layers are disposed between the light-emitting substrate and the counter substrate. The patterned distributed Bragg reflector is disposed on one side of the color conversion layers, and has multiple openings. Each of the openings has an opening width greater than or equal to 1 μm and less than the sub-pixel width.

An image processing method for converting a color space of input image data including color information is provided. The image processing method includes: preprocessing the input image data according to a frequency thereof to generate a preprocessed result; and color-converting the preprocessed result to generate output image data. The color space of the input image data is different from a color space of the output image data.

To provide a display panel.SOLUTION: A display panel includes a display region, an insulating film, and a sealing film. The display region includes a pixel, and the pixel includes a display element and a color conversion layer. The insulating film covers the display element, the sealing film includes a region where a color conversion layer is sandwiched between the region and the insulating film. Also, the sealing film is provided with a region in contact with the insulating film outside the display region. The display element includes a first layer, a second layer, a third layer, and a fourth layer. The first layer comprises a first material and a second material, the second layer comprises a third material, the third layer comprises a luminescent material and a fourth material, and the fourth layer comprises a fifth material and a sixth material. The first material has a HOMO level between -5.7 eV and -5.4 eV inclusive, the second material has an acceptor property, the third material has a lower HOMO level than the first material, and the fourth material has a lower HOMO level than the third material. The fifth material has a HOMO level of -6.0 eV or higher, and the sixth material is an organic complex of an alkali metal or an alkaline earth metal.SELECTED DRAWING: Figure 3

A display panel (10, 20) is provided, comprising a circuit substrate (100), a first light-emitting element (210), a first color-conversion layer (310), a first color filter layer (320), a second light-emitting element (220), and an encapsulation layer (330, 330A). The first light-emitting element (210) is configured to emit blue light and / or ultraviolet light. The first color-conversion layer (310) covers the first light-emitting element (210) and is configured to convert blue light and / or ultraviolet light into red light. The first color filter layer (320) covers and contacts an upper surface (110t, 310t, 330t) of the first color-conversion layer (310). The second light-emitting element (220) is configured to emit blue light.The encapsulation layer (330, 330A) surrounds the first light-emitting element (210), the first color conversion layer (310), the first color filter layer (320) and the second light-emitting element (220).

Disclosed is a display device including: a substrate; the transistor is arranged on the substrate; a light emitting element electrically connected to the transistor; an encapsulation layer disposed over the light emitting element; a spacer disposed on the encapsulation layer and defining a first opening, a second opening, and a third opening; a first color conversion layer disposed in the first opening; a second color conversion layer disposed in the second opening; and a transmissive layer disposed in the third opening, in which the separator is made of a metal material, and a distance from a center of a portion of the separator to the first color conversion layer is equal to a distance from the center of the portion of the separator to the transmissive layer.